Int. J. Computer Applications in Technology, Vol. 22, Nos.

2/3, 2005 53

Intelligent computer
applications in the energy
sector: a literature review
from 1990 to 2003

K. Metaxiotis* and A. Kagiannas

Department of Electrical and Computer Engineering,
National Technical University of Athens, 9, Iroon Polytechniou str.,
Zografou 15773, Athens, Greece
Fax: +30 1 7723550 E-mail: Kmetax@[Link]
E-mail: ekagian@[Link]
*Corresponding author

Abstract: Intelligent computer applications (ICA) to solve complicated practical problems

in various sectors are becoming more and more widespread nowadays. This paper surveys
the application of intelligent systems in the energy sector using a literature review and
classification of papers from 1990 to 2003 with keyword index in order to explore how
intelligent methodologies and applications have developed in this period. Based on the
scope of 247 papers of intelligent energy technologies this paper surveys and classifies ICA
in the energy sector using the four categories of: expert systems, neural networks, genetic
algorithms, fuzzy-logic-based systems, together with their applications for different
problem domains in the specific sector. The paper concludes by sharing thoughts and
estimations on ICA future prospects in the energy sector.

Keywords: artificial intelligence; intelligent computer applications; energy; survey.

Reference to this paper should be made as follows: Metaxiotis, K. and Kagiannas, A.

(2005) ‘Intelligent computer applications in the energy sector: a literature review from 1990
to 2003’, Int. J. Computer Applications in Technology, Vol. 22, Nos. 2/3, pp.53–64.

Biographical notes: Dr. Kostas Metaxiotis is an Electrical and Computer Engineer, Senior
Researcher of the National Technical University of Athens (NTUA) and Lecturer in the
Hellenic Open University. He has wide experience in database systems and expert systems
design and development, artificial intelligence, evaluation methods for information
systems, object-oriented knowledge modelling, inference mechanisms, knowledge
management, e-business. Since 1996 he participates in various projects funded by the
European Commission as IT Consultant. He has published more than 50 papers in
international journals such as Journal of Knowledge Management, Applied Artificial
Intelligence, Journal of Intelligent Manufacturing, Management Decision, Electronic
Government, Journal of Information and Knowledge Management.

Kagiannas is an Electrical and Computer Engineer of the National Technical University of

Athens (NTUA) with a PhD degree in energy policy making. His research focuses on
energy policy analysis, including energy planning, energy modelling, regulatory reform of
the energy sector, energy economics, energy management, and promotion of new and
renewable energy technologies. He is involved in the delivery of numerous courses in
NTUA, at the under- and post-graduate levels, including energy management and
environmental policy, energy and project management, and financial management for
engineers. He has delivered numerous professional training courses in energy experts
concerning modern financial mechanisms for energy-efficient projects, energy planning,
energy modelling, and regulation of electricity markets. He has delivered seven
announcements in national and international scientific conferences and published eight
papers in international scientific journals.

Copyright © 2005 Inderscience Enterprises Ltd.

54 K. METAXIOTIS AND A. KAGIANNAS

1 INTRODUCTION references cited below present an impressive record of the

achievement of the researchers in applying the expert
Energy is one of the most important basic inputs of systems technology in the energy sector (David and
economical and industrial development. Nowadays there is Zhao, 1991; Jwo et al., 1995; Shin and Park, 1993;
an ever-increasing concern and interest in important issues Adapa, 1994a, 1994b; Balu et al., 1992; Kono et al., 1991;
like sustainable development, rational use of energy, Hung et al., 1998; Lara-Rosano et al., 1994, 1995;
effective use of renewable energy sources, successful Lara-Rosano and Valverde, 1998; Godfrin, 1995;
energy planning, energy efficiency, optimisation of energy Kezunovic et al., 1993; Minakawa et al., 1995; Sherwali and
consumption, environmental protection. Application of Crossley, 1994; Yongli et al., 1994; Protopapas, 1991;
intelligent technologies in the energy sector has been an Yang et al., 1995; Lee et al., 1990; Hasan et al., 1994;
active area of research for about a decade and significant Eickhoff et al., 1992; McDonald et al., 1991; Vale and
successes have been achieved. Intelligent computer Moura, 1993; Enns et al., 1994; Fauquembergue et al., 1993;
applications (ICA) have attracted much effort to explore Kezunovic et al., 1991; Stedall et al., 1994; Esp et al., 1994;
their concepts, architectures, methodologies, tools and real Bernard and Durocher, 1994; Khosla and Dillon, 1994;
world implementations. As a part of ICA research in the Mansour et al., 1994; Yu et al., 1990; Vale et al., 1997, 1998;
energy sector, this paper focuses on surveying intelligent Ho et al., 1990; Rahman and Hazim, 1993, 1996; Markovic
systems development through a literature review and and Fraissler, 1993; Kandil, 2001; Kim et al., 1995;
classification of papers from 1990 to 2003 in order to Chiu et al., 1997; Metaxiotis et al., 2003; Adibi et al., 1994;
explore the intelligent methodologies and applications in the Darnault et al., 1990; Hotta et al., 1990;
energy sector from that period. Kakimoto et al., 1991, 1995a, 1995b; Ma et al., 1992;
The literature survey is based on a search for the keyword King et al., 1994; Kirschen and Volkmann, 1991;
indexes ‘intelligent energy systems’ and ‘intelligent energy Koeing, et al., 1995; Brunner et al., 1993; Nagata et al., 1995;
technologies’ on the web of science, from which 1,171 were Park and Lee 1995; Rumpel et al., 1992; Azzam and
found on December 18, 2003. The search was restricted to Nour, 1995, 1996; Chang et al., 1991; Chokri et al., 1996;
the keywords mainly to produce a manageable data file, but Lachs et al., 1990; Le, 1995; Matsuda et al., 1990;
also on the proposition that if the terms appeared in the Singh et al., 1993; Mohamedi et al., 1994; Christie et al., 1990;
keywords, the papers were likely to focus clearly on the Salma and Chikhani, 1992; Laframboise et al., 1995;
topic. After topic filtering, there were only 247 papers Ananthapadmanabha et al., 1996; Le and Negnevitsky, 1997;
related to ICA in the energy sector and 229 of them Le and Piekutowski, 1993; Godart and Puttgen, 1991;
concerned the artificial intelligence. Based on the scope of Doi and Uemura, 1998; Vajpai et al., 2001; Ouyang and
these 247 papers, this paper surveys and classifies ICA in Shahidehpour, 1990; Li et al., 1993; Salam et al., 1991;
the energy sector using the four categories of: expert systems, Tong et al., 1991; White, 1990; Zitouni and Irving, 1999;
neural networks, genetic algorithms, fuzzy-logic-based Melli and Sciuba, 1997; Padhy, 2000; Dillon and
systems, together with their applications for different Laughton, 1990). The technology of expert systems and its
problem domains in the specific sector. This review thus applications are categorised in Table 1.
aims to create a big knowledge base for the operations
researcher, introducing him/her to specific areas of Table 1 Expert systems and its applications
intelligent computer applications in the energy sector and
Experts systems/applications Authors
indicating other areas fertile for research.
The rest of the paper is organised as follows. Sections 2–5 Energy planning Hung et al. (1998)
present the survey results based on the above-mentioned Energy efficiency Lara-Rosano et al.
categories, respectively. Sections 6 and 7 present some (1998)
discussion, extending to suggestions for future development Alarm processing, system Vale et al. (1998)
of ICA in the energy sector. diagnosis, control and security
Electric load forecasting Metaxiotis et al. (2003)
Power system restoration Vale et al. (1997)
Reactive power/voltage control Vajpai et al. (2001)
2 EXPERT SYSTEMS AND ITS APPLICATIONS
Unit commitment Padhy (2000)
Expert systems (ES), one of the most commercially
successful branches of artificial intelligence, are Table 1 clearly shows that a large number of papers have
knowledge-intensive computer programs that capture the appeared dealing with various aspects of energy and power
human expertise in specific domains of knowledge. For this, engineering. In addition, several surveys of ES applications
human knowledge must be modelled or presented in a way have been made (Dillon and Laughton, 1990; Lai, 1998;
that a computer can process. An expert system can Liu et al., 1994; Ypsilantis and Yee, 1990; Lubarkii et al.,
support decision making by asking relevant questions and 1991; Bretthauer et al., 1992). The main advantages of
explaining the reasons for adopting certain actions. The ES are:
INTELLIGENT COMPUTER APPLICATIONS IN THE ENERGY SECTOR: A LITERATURE REVIEW FROM 1990 TO 2003 55

• it is permanent and consistent Table 2 Neural networks and its applications

• it can be easily transferred or reproduced
Neural Authors
• it can be easily documented. networks/applications
The main disadvantage of ES is that it suffers from a Energy planning Chandrashekara et al.
knowledge bottleneck because it is unable to learn or adapt (1999)
to new situations. Renewable energy systems Kalogirou (2001)
Alarm processing, system Rementeria et al. (1995)
diagnosis, control and
security
3 NEURAL NETWORKS AND ITS APPLICATIONS
Electric load forecasting Alsayegh (2003)
Power system restoration Rahim and Al-Baiyat (2000)
Neural networks (NNs) are an information processing
technique based on the way biological nervous systems, Reactive power/voltage Das et al. (2001)
control
such as the brain, process information. Composed of a large
Unit commitment Yalcinoz and Short (1998)
number of highly interconnected processing units (neurons)
connected into networks, a neural network system uses the
human-like technique of learning by example to resolve In addition, several surveys of NN applications have been
problems. Every neuron applies an input, activation and an made (Vankayala and Rao, 1993; Novosel and King, 1994;
output function to its net input (sum of weighted input Bann et al., 1996; Kalogirou, 1999). The main advantages
signals) to calculate its output. The neural network is of NN technology are:
configured for a specific application, such as data • it is fast
classification or pattern recognition, through a learning • it possesses learning ability
process called ‘training’. Just as in biological systems, • it adapts to the data
learning involves adjustments to the synaptic connections • it is robust
that exist between the neurons. In other words, the ‘learnt’ • it is appropriate for nonlinear modelling.
information is stored in the form of numerical values, called
‘weights’, which are assigned to the connections among the These advantages suggest the use of NNs for voltage
processing units of the network. The technology of expert security monitoring and control. Despite the advantages of
systems and its applications are categorised in Table 2 the NN technology, there are some disadvantages too:
(David and Zhao, 1990; Chandrashekara et al., 1999; • its large dimensionality
Kalogirou et al., 1996a, 1996b; 1997, 1999; Kalogirou and • the choice of training methodology
Panteliou, 2000; Kalogirou, 2000, 2001; Lalot, 2000; Alawi • the ‘black-box’ representation of NNs (they lack
and Hinai, 1998; Mohandes et al., 1998; Kemmoku et al., explanation capabilities)
1999; Kalogirou and Bojic, 2000; Fukuyama and Ueki, • the fact that results are always generated even if the
1991; Fukuyama et al., 1992; Karunakaran and Karady, input data are unreasonable.
1991; Khosla and Dillon, 1994; Christie et al., 1990;
Daneshdoost, 1990; Vankayala and Rao, 1992; Rementeria
et al., 1995; Lee et al., 1990, 1991; Park et al., 1991; Peng et 4 GENETIC ALGORITHMS AND ITS APPLICATIONS
al., 1992; Ho et al., 1992; Lu et al., 1993; Chen et al., 1993;
Kariniotakis et al., 1993; Papalexopoulos et al., 1994; 1994; Genetic algorithms (GAs) represent a powerful and robust
Czernichow et al., 1995; Mandal et al., 1995; Sforna and approach for developing heuristics for large-scale
Proverbio, 1995; Kiartzis et al., 1995; Dash et al., 1995; combinatorial optimisation problems. The motivation
Islam et al., 1995; Sharaf and Lie, 1995; Srinivasan et al., underlying GAs can be expressed as follows: Evolution has
1995; Al-Rashid and Paarmann, 1996; Chow and Leung, been remarkably successful in developing complex and
1996; Prudenzi, 1996; Bakirtzis, 1996; Kiartzis et al., 1997; well-adapted species through relatively simple evolutionary
Ramanathan et al., 1997; Sforna, 1998; Papadakis et al., mechanisms. A natural question is the following: What
1998; Drezga and Rahman, 1998; Kodogiannis and ideas can we adapt from our understanding of evolution
Anagnostakis, 1999; Mastorocostas et al., 2000; Yao et al., theory so as to solve problems in other domains? This
2000; Zhang and Dong, 2001; Chen et al., 2001; Liang, fundamental question has many different answers because
2002; Alfuhaid, et al., 1997; Khotanzad et al., 1998; of the richness of evolutionary phenomenon. Holland (1975)
Vermaak and Botha, 1998; Yoo and Pimmel, 1999; and DeJong (1975) provided the first answer to this question
Hobbs et al., 1998; Alsayegh, 2003; Kuroda et al., 1993; by introducing the concept of GA as a general search
Zhou et al.,1996; Rahim and Al-Baiyat, 2000; Aggarwal technique which mimics biological evolution, with the survival
and Song, 1998a, 1998b; Aggarwal and Song, 1997; of the fittest individuals and a structured, yet randomised,
Santoso and Tan, 1990; Roy and Goswami, 1996; information exchange like in population genetics.
Ching-Tzong and Chien-Tung, 1995; Gu and Rizy, 1996; A GA encodes the problem into a set of strings, each of
Abdul-Rahman and Shahidehpour, 1995; Das et al., 2001; which is composed of several bits, then operates on the
Sasaki et al., 1992; Ouyang and Shahidehpour, 1992; strings to simulate the process of evolution. In contrast to
He and David, 1995; Yalcinoz and Short, 1998). the local search algorithms, such as neighbourhood search,
56 K. METAXIOTIS AND A. KAGIANNAS

tabu search and simulated annealing, which work only on 5 FUZZY LOGIC AND ITS APPLICATIONS
one feasible solution, GAs consider a population of
individuals. Working with a population allows us to be able Fuzzy logic (FL) is a superset of conventional (Boolean)
to study the structures and the properties inherent in various logic that has been extended to handle the concept of partial
kinds of individual so that we can identify and explore good truth – truth values between ‘completely true’ and
solutions more efficiently. During the execution, GAs select ‘completely false’. It was introduced by Dr Lotfi Zadeh of
the strings which have higher fitness values to survive, UC/Berkeley in the 1960s as a means to model the
eliminate those with lower fitness from the population, and uncertainty of natural language. Professor Zadeh stated
combine the survivals with a structured but information (1965) that rather than regarding fuzzy theory as a single
exchange to generate new individuals and renew the theory, we should regard the process of ‘fuzzification’ as a
population. methodology to generalise any specific theory from a crisp
The technology of genetic algorithms and their (discrete) to a continuous (fuzzy) form. By the term
applications are categorised in Table 3 (Romero and Binato, ‘fuzziness’ Professor Zadeh meant classes in which there is
1998; Lee and Yang, 1998; Youssef, 2001; Gil and Da no sharp transition from membership to non-membership.
Silva, 2001; Lee and Park, 1995; Wu et al., 1998; Duan and For example, the class of tall men is a fuzzy set.
Yu, 2002; Zhu, 2002; El-Sharkh and El-Keib, 2003; Das In general, FL is a form of artificial intelligent that can
and Patvardhan, 2003; Mantawy et al., 2003; Zhang et al., deal with non-quantifiable concepts. It enables software
2000; Weber and Overbye, 1999; Richter et al., 1999; Wen developers easily to programme computers that can simulate
et al., 2001; Iba, 1994; Lai et al., 1994; El-Sharkawi and the vagueness and uncertainty of terms like ‘old’ and
Huang, 1994; Youssef and El-Naggar, 2000; Su and Lii, ‘smart’ – terms inherent in human reasoning and
1999, 2002; Heine and Neumann, 1994; Maifeld and thought-processes. In FL, unlike standard conditional logic,
Sheble, 1994; Yang et al., 1995; Chen et al., 2001; Ghose the truth of any statement is a matter of degree. For
et al., 1999; Miu et al., 1997; Haida and Akimoto, 1991; example, for the rule ‘if (weather is cold) then (heat is on)’,
Urdaneta et al., 1999; Bansal et al., 2003; Kazarlis et al., both variables, ‘cold’ and ‘on’, map to ranges of values.
1996; Mantawy et al., 1999; Orero and Irving, 1996, 1998; Fuzzy systems rely on membership functions to explain to
Shehle and Briting, 1995; Dasgupta and McGregor, 1994; the computer how to calculate the correct value between 0
Kim et al., 1997; Yang et al., 1997; Mantawy et al., 1999; and 1. The degree to which any fuzzy statement is true is
Xia et al., 2000; Padhy, 2003). denoted by a value between 0 and 1.
The approach of fuzzy logic and its applications are
Table 3 Genetic algorithms and their applications categorised in Table 4 (Beccali et al., 1998; Venkatesh
et al., 2001; Gungor and Arikan, 2000; Sozen et al., 2004;
Neural networks/applications Authors
Ramakrishna and Rao, 1995; Karnavas and Papadopoulos,
Energy planning Mantawy et al. (2003) 2002; Lu et al., 2001; Sarfi and Solo, 2002; Abyaneh and
Bidding strategies in energy Wen and Kumar David Karegar, 2003; Bi et al., 2003; Srinivasan et al., 1994; Dash
market (2001) et al., 1996; Hsu and Ho, 1992; Abdul-Rahman and
Alarm processing, system Su and Lii (2002) Shahidehpour, 1994; Venkatesh et al., 1999a, 1999b;
diagnosis, control and security Tamimi and Egbert, 2000; Liang and Cheng, 2002;
Electric load forecasting Chen et al. (2001) Tomsovic, 1992; Lu and Hsu, 1997; Su and Lin, 2001,
Reactive power/voltage Bansal et al. (2003) 1996; Saric et al., 1997; Ng et al., 2000; Chung and
control Da-Zhong, 2002; Satpathy et al., 2002; Morris et al., 2003;
Unit commitment Padhy (2003) Su and Hsu, 1991; Padhy, 2000)

The advantages of GA over traditional techniques are: Table 4 Fuzzy logic and its applications

• GA needs only rough information of the objective Neural networks/applications Authors

function and places no restrictions such as Energy planning Gungor and Arikan (2000)
differentiability and convexity on the objective function Renewable energy systems Sozen et al. (2004)
• the method works with a set of solutions from one
Alarm processing, system Bi et al. (2003)
generation to the next, and not a single solution, thus
diagnosis, control and
making it less likely to converge on local minima security
• the solutions developed are randomly based on the
Electric load forecasting Liang and Cheng (2002)
probability rate of the genetic operators such as
mutation and crossover; the initial solutions thus would Reactive power/voltage Morris et al. (2003)
control
not dictate the search direction of a GA.
Unit commitment Padhy (2000)
On the other hand, one disadvantage of GA technology is
that it requires a tremendous amount of time. Alander
(1996) has presented an extended bibliography of GA in In addition, several surveys of FL applications have been
power systems. made (Song and Johns, 1997, 1998; Mamoh et al., 1995).
INTELLIGENT COMPUTER APPLICATIONS IN THE ENERGY SECTOR: A LITERATURE REVIEW FROM 1990 TO 2003 57

Adapa, R. (1994a) ‘Expert system applications in power system

6 LIMITATIONS
planning and operations’, IEEE Power Engineering Reviews,
Vol. 14, No. 2, pp.15-18.
Firstly, a literature review for the broad category of ICA in Adapa, R. (1994b) ‘Expert systems in power system planning and
the energy sector is a difficult task due to the extensive engineering: transient stability input and output data analysis’,
background knowledge needed for studying, classifying and IEEE Power Engineering Reviews, Vol. 14, No. 2, pp.12–14.
filtering papers. Adibi, M., Kafka, R. and Milanicz, D. (1994) ‘Expert system
requirements for power system restoration’, IEEE
This paper makes a broad literature review on ICA from Transactions Power Systems, Vol. 9, No. 3, pp.1592–1600.
1990 to 2003 in order to explore the intelligent Aggarwal, R. and Song, Y. (1997) ‘Artificial neural networks in
methodologies and applications in the energy sector in this power systems, Part 1: general introduction to neural
period. Indeed, the categorisation of technologies and their computing’, IEE Power Engineering Journal, Vol. 11, No. 3,
applications is based on the keyword index on this research. pp.129–134.
Aggarwal, R. and Song, Y. (1998a) ‘Artificial neural networks in
Therefore, this is the first limit of this paper. power systems, Part 2: types of artificial neural networks’, IEE
Secondly, some other academic journals listed in the Power Engineering Journal, Vol. 12, No. 1, pp.41–47.
science citation index as well as other practical reports or Aggarwal, R. and Song, Y. (1998b) ‘Artificial neural networks in
proceedings of very old conferences are not included in this power systems, Part 2: examples of applications in power
survey. These would have provided more complete systems’, IEE Power Engineering Journal, Vol. 12 No. 6,
pp.279–287.
information to explore ICA in the energy sector. Thirdly, Alander, J. (1996) An Indexed Bibliography of Genetic Algorithms
non-English publications are not considered in this survey to in Power Engineering, Report Series 94-1: Power,
determine the effects of different cultures on the 21 February.
development of ICA. Alawi, S. and Hinai, H. (1998) ‘An ANN-based approach for
Finally, it should be stressed that the definition of ICA is predicting global radiation in locations with no direct
measurement instrumentation’, Renewable Energy, Vol. 14,
not complete because other methodologies, such as Nos. 1–4, pp.199–204.
evolutionary computing or data mining (Sforna, 2000) were Alfuhaid, A., El-Sayed, M. and Mahmoud, M. (1997) ‘Cascaded
not included in the survey. Moreover, sub-sectors such as artificial neural networks for short-term load forecasting’,
nuclear sector (Nissan, 1998) or petroleum industry IEEE Transactions on Power Systems, Vol. 12, No. 4,
(Alvarado et al., 2004) were not also included in this review. pp.1524–1529.
Al-Rashid, Y. and Paarmann, L. (1996) ‘Short-term electric load
forecasting using neural network models’, Proceedings of the
39th Midwest Symposium on Circuits and Systems, Iowa State
7 CONCLUSIONS University, Ames, Iowa.
Alsayegh, O. (2003) ‘Short-term load forecasting using seasonal
artificial neural networks’, International Journal of Power and
This paper is based on a literature review on Intelligent
Energy Systems, Vol. 23, No. 3, pp.137–142.
Computer Applications in the energy sector from 1990 to Alvarado, M. and Cantu, F. (2004) ‘Autonomous agents and
2003 using a keyword index search. We conclude that ICA computational intelligence: the future of AI application for
tend to develop towards expert orientation and ICA petroleum industry’ Editorial, Expert Systems with
development is a problem-oriented domain. Applications, Vol. 26, pp.3–8.
Ananthapadmanabha, T., Kulkarni, A., Rao, A., Rao, K. and
Real-life energy system problems may neither fit the
Parthasarathy, K. (1996) ‘Knowledge-based expert system for
assumptions of a single intelligent (or AI) technique nor be optimal reactive power control in distribution system’,
effectively solved by the strengths and capabilities of a Electrical Power and Energy Systems, Vol. 18, No. 1,
single technique. The approach to deal with these complex pp.27–31.
real-world problems is to integrate the use of two or more Azzam, M. and Nour, M. (1995) ‘Expert system for voltage
control of a large-scale power system’, Modelling,
techniques in order to combine their different strengths and
Measurement Control A: General Physics, Electronics,
overcome each other’s weaknesses, to generate hybrid Electrical Engineering, Vol. 63, Nos. 1–3, pp.15–24.
solutions. The application of hybrid systems in the energy Azzam, M. and Nour, M. (1996) ‘An expert system for voltage
sector is a novel development and represents a future trend control of a large-scale power system’, Energy Conversion and
in ICA research. Management, Vol. 37, No. 1, pp.81–86.
Bakirtzis, A. (1996) ‘A neural network short term load forecasting
model for the Greek power system’, IEEE Transactions on
Power Systems, Vol. 11, pp.858–863.
REFERENCES Balu, N., Adapa, R., Cauley, G., Lauby, M. and Maratukulam, D.
(1992) ‘Review of expert systems in bulk power system
Abdul-Rahman, K. and Shahidehpour, M. (1994) ‘Reactive power planning and operation’, Proceedings IEEE, Vol. 80, No. 5,
optimization using fuzzy load representation’, IEEE pp.727–731.
Transactions on Power Systems, Vol. 9, No. 2, pp.898–905. Bann, J., Irisarri, G., Kirschen, D., Miller, B. and Mokhtari, S.
Abdul-Rahman, K. and Shahidehpour, M. (1995) ‘AI approach to (1996) ‘Integration of artificial intelligence applications in the
optimal VAR control with fuzzy reactive loads’, IEEE EMS: issues and solutions’, IEEE Transactions on Power
Transactions on Power Systems, Vol. 10, No. 1, pp.88–97. Systems, Vol. 11, No. 1, pp.475–482.
Abyaneh, H. and Karegar, H. (2003) ‘A new model of overcurrent Bansal, R., Bhatti, T. and Kothari, D. (2003) ‘Artificial
relay characteristics based on fuzzy logic’, International intelligence techniques for reactive power/voltage control in
Journal of Power and Energy Systems, Vol. 23, No. 3, power systems: a review’, International Journal of Power and
pp.163–167. Energy Systems, Vol. 23, No. 2, pp.81–89.
58 K. METAXIOTIS AND A. KAGIANNAS

Beccali, M., Cellura, M. and Ardente, D. (1998) ‘Decision making Darnault, P., Fandino, J., Bigeon, J., Sabonnadiere, J., Mondon, E.,
in energy planning: the electre multicriteria analysis approach Harmand, Y. and Pierrat, L. (1990) ‘An expert system as a
compared to a fuzzy-sets methodology’, Energy Conversion guide for information synthesis and decision making in the
and Management, Vol. 39, Nos. 16–18, pp.1869–1881. restoration of power system after a blackout’, Electricite de
Bernard, J. and Durocher, D. (1994) ‘Expert system for fault France, Bulletin de la Direction des Etudes el Recherches,
diagnosis integrated in existing SCADA systems’, IEEE Serie B, Reseaux Electriques, Materiels Electriques, Vol. 4,
Transactions on Power Systems, Vol. 9, No. 1, pp.548–554. pp.29–43.
Bi, T., Wen, F., Ni, Y. and Wu, F. (2003) ‘Distributed fault section Das, B. and Kumar Verma, P. (2001) ‘Artificial neural
estimation system using radial basis function neural network network-based optimal capacitor switching in a distribution
and its companion fuzzy system’, Electrical Power and Energy system’, Electric Power System Research, Vol. 60, No. 2,
Systems, Vol. 25, pp.377–386. pp.55–62.
Bretthauer, G., Handschin, E. and Hoffmann, W. (1992) ‘Expert Das, D. and Patvardhan (2003) ‘A new hybrid evolutionary
systems application to power systems – state-of-the-art and strategy for reactive power dispatch’, Electric Power Systems
future trends’, IFAC Symposium on Control of Power Plants Research, Vol. 65, No. 2, pp.83–90.
and Power Systems, Munich, Germany, pp.463–468. Dasgupta, D. and McGregor, D. (1994) ‘Thermal unit commitment
Brunner, T., Nejdl, W., Schwarzjirg, H. and Sturm, M. (1993) using genetic algorithm’, IEE Proc. Generation, Transmission
‘On-line expert system for power system diagnosis and & Distribution, Vol. 141, No. 5, pp.459–464.
restoration’, Intelligent Systems Engineering, Vol. 2, No. 1, Dash, P., Liew, A. and Rahman, S. (1995) ‘Peak load forecasting
pp.5–24. using a fuzzy neural network’, Electric Power Systems
Chandrashekara, A., Ananthapadmanabha, T. and Kulkarni, A. Research, Vol. 32, pp.19–23.
(1999) ‘A neuro-expert system for planning and load Dash, P., Liew, A. and Rahman, S. (1996) ‘Fuzzy neural network
forecasting of distribution systems’, Electrical Power and and fuzzy expert system for load forecasting’, IEE Proc.
Energy Systems, Vol. 21, pp.309–314. Generation, Transmission and Distribution, Vol. 143, No. 1,
Chang, C., Sutanto, D. and Lachs, W. (1991) ‘Automatic control of pp.106–114.
voltage instability by an expert system utilising pattern David, A. and Zhao, R. (1990) Advances in AI Applications for
recognition techniques’, 3rd International Conference on Power System Planning, IEE Press, Brighton, UK.
Power System Monitoring and Control, IEE Press, London, David, A. and Zhao, R. (1991) ‘An expert system with fuzzy sets
UK. for optimal planning’, IEEE Transactions on Power Systems,
Chen, G., Li, K., Chung, T., Sun, H. and Tang, G. (2001) Vol. 6, No. 2, pp.59–65.
‘Application of an innovative combined forecasting method in DeJong, K.A. (1975) An Analysis of the Behaviour of a Class of
power system load forecasting’, Electric Power Systems Genetic Adaptive Systems, Doctoral Dissertation, University of
Research, Vol. 59, pp.131–137. Michigan.
Chen, S., Yu, D. and Moghaddamio, A. (1993) ‘Weather sensitive Dillon, T. and Laughton, M. (1990) Expert System Applications to
short-term load forecasting using nonfully connected artificial Power Systems, Prentice Hall International, UK.
neural network’, IEEE Transactions on Power Systems, Vol. 7, Doi, A. and Uemura, K. (1998) ‘Knowledge-based operation
No. 3, pp.1098–1105. guidance method for voltage and reactive power control in
Ching-Tzong, S. and Chien-Tung, L. (1995) ‘Application of a power system’, IFAC Symposium on Planning and Operation
neural network and heuristic model for voltage-reactive power of Electric Energy Systems, Rio de Janeiro, Brazil,
control’, Electric Power System Research, Vol. 34, No. 3, pp.457–462.
pp.143–148. Drezga, I. and Rahman, S. (1998) ‘Input variable selection for
Chiu, C., Kao, L. and Cook, D. (1997) ‘Combining a neural ANN-based short-term load forecasting’, IEEE Transactions
network with a rule-based expert system approach for on Power Systems, Vol. 13, pp.1238–1244.
short-term power load forecasting in Taiwan’, Expert Systems Duan, G. and Yu, Y. (2002) ‘Problem-specific genetic algorithm
with Applications, Vol. 13, No. 4, pp.299–305. for power transmission system planning’, Electric Power
Chokri, B., Rabei, M. and Dai, D. (1996) ‘An integrated power Systems Research, Vol. 61, No. 1, pp.41–50.
system global controller using expert system’, Canadian Eickhoff, F., Handschin, E. and Hoffmann, W. (1992) ‘Knowledge
Conference on Electrical and Computer Engineering, Calgary, based alarm handling and fault location in distribution
Canada, p.2. networks’, IEEE Transactions on Power Systems, Vol. 7,
Chow, T. and Leung, C. (1996) ‘Neural network based No. 2, pp.770–776.
short term load forecasting using weather compensation’, El-Sharkawi, M. and Huang, S. (1994) ‘Application of
IEEE Transactions on Power Systems, Vol. 11, No. 4, genetic-based neural networks to power system static security
pp.1736–1742. assessment’, Proc. ISAP, No. 1, pp.423–429.
Christie, R., Talukdar, S. and Nixon, J. (1990) ‘A hybrid expert El-Sharkh, M. and El-Keib, A. (2003) ‘An evolutionary
system for security assessment’, IEEE Transactions on Power programming-based solution methodology for power
Systems, Vol. 5, No. 4, pp.1503–1509. generation and transmission maintenance scheduling’, Electric
Chung, T. and Da-Zhong, F. (2002) ‘Fuzzy logic controller for Power Systems Research, Vol. 65, No. 1, pp.35–40.
enhancing oscillatory stability of AC/DC interconnected power Enns, M., Budler, L., Cease, T., Elnweihi, A., Guro, E. and
system’, Electric Power Systems Research, Vol. 61, No. 3, Kezvmovic, M. (1994) ‘Potential applications of expert
pp.221–226. systems to power system protection’, IEEE Transactions on
Czernichow, T., Germond, A., Dorizzi, B. and Caire, P. (1995) Power Delivery, Vol. 9, No. 2, pp.720–728.
‘Improving recurrent network load forecasting’, IEEE Esp, D., Ekwue, A., Macqueen, J. and Vaughan, B. (1994)
International Conference ICNN’95, Perth, Western Australia, ‘AHFA – a real-time expert system for the incremental
Vol. 2, pp.899–904. diagnosis of multiple faults on a transmission network using
Daneshdoost, M. (1990) ‘Neural network approach to power the sequence and timing of switching indications’, Proceedings
system security’, Proc. Optical Engineering, Midwest, International Conference on Control, Vol. 1, No. 389,
Rosemont, USA, pp.270–275. pp.141–152.
INTELLIGENT COMPUTER APPLICATIONS IN THE ENERGY SECTOR: A LITERATURE REVIEW FROM 1990 TO 2003 59

Fauquembergue, P., Maizener, A., Parant, J., Perrot, L. and Hotta, K., Nomura, H., Takemoto, H., Suzuki, K., Nakamura, S.
Bertrand, H. (1993) ‘Monitoring of protection system behavior and Fukui, S. (1990) ‘Implementation of a real-time
using an expert system which analyses substations sequential expert system for a restoration guide in a dispatching center’,
events recordings field experience at Electricite de France’, 5th IEEE Transactions on Power Systems, Vol. 5, No. 3,
International Conference on Developments in Power System pp.1032–1038.
Protection, Vol. 368, pp.42–45. Hsu, Y. and Ho, K. (1992) ‘Fuzzy expert systems. An application
Fukuyama, Y. and Ueki, Y. (1991) ‘Development of an expert to short-term load forecasting’, IEE Proc. Generation,
system for analyzing faults in power system using artificial Transmission and Distribution, Vol. 139, No. 6, pp.471–477.
neural network based waveform recognition’, IEEE Int. Hung, C., Batanov, D. and Lefevre, T. (1998) ‘KBS and
Symposium on Circuits and Systems, Part 2 (of 5), Singapore, macro-level systems: support of energy demand forecasting’,
pp.1137–1140. Computers in Industry, Vol. 37, pp.87–95.
Fukuyama, Y., Ueki, Y. and Kaneko, K. (1992) ‘Development of Iba, K. (1994) ‘Reactive power optimization by genetic algorithm’,
an expert system for analyzing faults in power systems based IEEE Transactions on Power Systems, Vol. 9, No. 2,
on waveform recognition by artificial neural networks’, pp.685–692.
Electrical Engineering Japan, Vol. 112, No. 3, pp.735–742. Islam, S., Al-Alawi, S. and Ellithy, K. (1995) ‘Forecasting
Ghose, T., Goswami, S. and Basu, S. (1999) ‘Solution of capacitor monthly electric load and energy for a fast growing utility
placement problem in distribution system using modified using an artificial neural network’, Electric Power Systems
genetic algorithm’, Journal of the Institution of Engineers Research, Vol. 34, No. 1, pp.1–9.
(India) of Electrical Engineering, Vol. 79, No. 1, pp.178–181. Jwo, W., Liu, C., Liu, C. and Hsiao, Y. (1995) ‘Hybrid expert
Gil, H. and Da Silva, E. (2001) ‘A reliable approach for solving system and simulated annealing approach to optimal reactive
the transmission network expansion planning problem using power planning’, IEE Proc. Generation, Transmission and
genetic algorithms’, Electric Power Systems Research, Distribution, Vol. 42, No. 4, pp.381–385.
Vol. 58, No. 1, pp.45–51. Kakimoto, N., Lin, B. and Hayashi, M. (1991) ‘Expert system for
Godart, T. and Puttgen, H. (1991) ‘A reactive path concept applied initial stage restoration from system blackout of EHV power
within a voltage control expert system’, IEEE Transactions on system’, Electrical Engineering Japan, Vol. 111, No. 1,
Power Systems, Vol. 6, No. 2, pp.787–793. pp.95–107.
Godfrin, P. (1995) ‘Operational expert system to analyse and Kakimoto, N., Lin, B. and Sugihara, H. (1995a) ‘Expert system for
locate faults occurring on MV networks’, Proceedings IEEE dispatch control in restoration of EHV power system after
Power Industry Computer Application Conference, Salt Lake complete blackout’, Electrical Engineering Japan, Vol. 3,
City, USA. pp.15–29.
Gu, Z. and Rizy, D. (1996) ‘Neural network for combined control Kakimoto, N., Lin, B. and Sugihara, H. (1995b) ‘Expert system for
of capacitance banks and voltage regulators in distribution voltage control in restoration of EHV power system following
systems’, IEEE Transactions on Power Systems, Vol. 11, complete blackout’, Electrical Engineering Japan, Vol. 115,
No. 4, pp.1921–1928. No. 1, pp.35–50.
Gungor, Z. and Arikan, F. (2000) ‘A fuzzy outranking method in Kalogirou, S. (1999) ‘Applications of artificial neural networks in
energy policy planning’, Fuzzy Sets and Systems, Vol. 114, energy systems: a review’, Energy Conversion &
pp.115–122. Management, Vol. 40, pp.1073–1087.
Haida, T. and Akimoto, Y. (1991) ‘Voltage optimization using Kalogirou, S. (2000) ‘Forced circulation solar domestic water
genetic algorithm’, 3rd Symposium on Expert System heating systems long-term performance prediction’, Applied
Applications to Power Systems, Tokyo, Japan, pp.375–380. Energy, Vol. 66, No. 1, pp.63–74.
Hasan, K., Ramsay, B. and Moyes, I. (1994) ‘Object oriented Kalogirou, S. (2001) ‘Artificial neural networks in renewable
expert systems for real-time power system alarm processing, energy systems applications: a review’, Renewable and
Part I, selection of a toolkit; Part II, application of a toolkit’, Sustainable Energy Reviews, Vol. 5, pp.373–401.
Electrical Power Systems Research, Vol. 30, No. 1, pp.69–75, Kalogirou, S. and Bojic, M. (2000) ‘Artificial neural networks for
77–82. the prediction of the energy consumption of a passive solar
He, Y. and David, A. (1995) ‘Advances in global optimization for building’, Energy – The International Journal, Vol. 25, No. 5,
generation expansion planning’, IEE Proc. Generation, pp.479–491.
Transmission and Distribution, Vol. 142, No. 4, pp.423–428. Kalogirou, S. and Panteliou, S. (2000) ‘Thermosyphon solar
Heine, S. and Neumann, I. (1994) ‘Optimal load forecast models domestic water heating systems long-term performance
using an evolutionary algorithm’, Proceedings of the 2nd prediction using artificial neural networks’, Solar Energy,
European Congress on Intelligent Techniques and Soft Vol. 69, No. 2, pp.163–174.
Computing, Aachen, Germany, pp.1690–1694. Kalogirou, S., Neocleous, C. and Schizas, C. (1996a) ‘Artificial
Ho, K., Hsu, Y. and Yuan, C. (1992) ‘Short term load forecasting neural networks in modeling the heat-up response of a solar
using a multilayer neural network with an adaptive learning steam generation plant’, Proc. Int. Conf. EANN’96, London,
algorithm’, IEEE Transactions on Power Systems, Vol. 7, UK.
No. 1, pp.259–266. Kalogirou, S., Neocleous, C. and Schizas, C. (1997) ‘Artificial
Ho, K., Hsu, Y., Chen, C., Lee, T., Liang, C., Lai, T. and Chen, K. neural networks for the estimation of the performance of a
(1990) ‘Short term load forecasting of Taiwan power system parabolic trough collector steam generation system’, Proc. Int.
using a knowledge-based expert system’, IEEE Transactions Conf. EANN’97, Stockholm, Sweden, p.3.
on Power Systems, Vol. 5, No. 4, pp.1214–1221. Kalogirou, S., Panteliou, S. and Dentsoras, A. (1996b) ‘Modelling
Hobbs, B., Halman, U., Jitprapaikulsarn, S., Konda, S. and of solar domestic water heating systems using artificial neural
Maratukulam, D. (1998) ‘Artificial neural networks for networks’, Solar Energy, Vol. 65, No. 6, pp.335–342.
short-term forecasting: accuracy and economic value’, Kalogirou, S., Panteliou, S. and Dentsoras, A. (1999) ‘Artificial
Neurocomputing, Vol. 23, pp.71–84. neural networks used for the performance prediction of a
Holland, J. (1975) Adaption in Natural and Artificial Systems, thermosyphon solar water heater’, Renewable Energy, Vol. 18,
University of Michigan Press, MI. No. 1, pp.87–99.
60 K. METAXIOTIS AND A. KAGIANNAS

Kandil, M. (2001) ‘The implementation of long-term forecasting Kuroda, K., Takegoshi, Y., Yamashita, Y., Ito, M. and Fukui, S.
strategies using a knowledge-based expert system: Part II’, (1993) ‘Verification of a knowledge-based restoration
Electric Power Systems Research, Vol. 58, No. 1, pp.19–25. guidance system in a local dispatching centre’, International
Kariniotakis, G., Kosmatopoulos, E. and Stavrakakis, G. (1993) Journal of Electrical Power and Energy Systems, Vol. 15,
‘Load forecasting using dynamic high-order neural networks’, No. 3, pp.185–192.
Proceedings of IEEE-NTUA Joint International Power Lachs, W., Zhu, Y., Sutanto, D. and Morrison, I. (1990)
Conference, pp.801–805. ‘Automatic control of system voltage stability by an expert
Karnavas, Y. and Papadopoulos, D. (2002) ‘AGC for autonomous system’, Proceedings 10th Power Systems Computation
power system using combined intelligent techniques’, Electric Conference, Butterworths, London, UK.
Power Systems Research, Vol. 62, No. 3, pp.225–239. Laframboise, J., Ferland, G., Chikhani, A. and Salma, M. (1995)
Karunakaran, R. and Karady, G. (1991) ‘Artificial neural networks ‘An expert system for reactive power control of a distribution
as a dispatcher’s aid in alarm processing’, Proc. 1st Int. Forum system, Part 2: system implementation’, IEEE Transactions on
on Applications of Neural Networks to Power, pp.169–173. Power Delivery, Vol. 10, No. 3, pp.1433–1441.
Kazarlis, S., Bakirtzis, A. and Petrides, V. (1996) ‘A genetic Lai, L. (1998) Intelligent System Applications in Power
algorithm solution to the unit commitment problem’, IEEE Engineering, John Wiley and Sons, London, UK.
Transactions on Power Systems, Vol. 11, No. 1, pp.83–92. Lai, L., Che, F., Chu, K., Rajroop, P. and Wang, X. (1994) ‘Design
Kemmoku, Y., Orita, S., Nakagawa, S. and Sakakibara, T. (1999) neural networks with genetic algorithms for fault section
‘Daily insolation forecasting using a multi-stage neural estimation’, Proc. 29th Universities Power Engineering
network’, Solar Energy, Vol. 66, No. 3, pp.193–199. Conference, Part 2 (of 2), Galway, Ireland.
Kezunovic, M., Fromen, C. and Sevcik, D. (1993) ‘Expert system Lalot, S. (2000) ‘Identification of the time parameters of solar
for transmission substation event analysis’, IEEE Transactions collectors using artificial neural networks’, Proc. Eurosun
on Power Delivery, Vol. 8, No. 4, pp.1942–1949. 2000.
Kezunovic, M., Watson, K., Don Russell, B., Heller, P. and Lara-Rosano, F. and Valverde, N. (1998) ‘Knowledge-based
Aucoin, M. (1991) ‘Expert system applications to protection, systems for the energy conservation programs’, Expert Systems
substation control and related monitoring functions’, Electrical with Applications, Vol. 14, pp.25–35.
Power Systems Research, Vol. 21, No. 1, pp.71–86. Lara-Rosano, F., Kemper, N. and Hernandez, O. (1995) ‘EXILCO:
Khosla, R. and Dillon, T. (1994) ‘Neuro-expert system approach to an expert system for lighting systems analysis and design in
power system problems’, International Journal of Engineering commercial buildings and hotels’, Proceedings 1995
Intelligent Systems for Electrical Engineering and International Symposium on Artificial Intelligence, Monterrey,
Communications, Vol. 2, No. 1, pp.71–78. Mexico, pp.193–198.
Khotanzad, A., Afkhami-Rohani, R. and Maratukulam, R. (1998) Lara-Rosano, F., Kemper, N., Mojica, R., Olivas, C. and Ortiz, O.
‘ANNSTLF: artificial neural network short-term load (1994) ‘SECOM: an expert system for the design of energy
forecaster – generation three’, IEEE Transactions on Power efficient compressed air facilities in the industry’, Proceedings
Systems, Vol. 13, No. 4, pp.1413–1422. of 3rd IASTED International Conference on Computer
Kiartzis, S., Bakirtzis, A. and Petridis, V. (1995) ‘Short-term load Applications in Industry, Cairo, Egypt, pp.203–205.
forecasting using neural networks’, Electric Power Systems Le, T. and Negnevitsky, M. (1997) ‘Expert system application for
Research, Vol. 33, No. 1, pp.1–6. voltage and VAR control in power transmission and
Kiartzis, S., Kehagias, A., Bakirtzis, A. and Petridis, V. (1997) distribution systems’, IEEE Transactions on Power Systems,
‘Short-term load forecasting using a Bayesian combination Vol. 12, No. 3, pp.1392–1397.
method’, Electrical Power & Energy Systems, Vol. 19, No. 3, Le, T. and Piekutowski, M. (1993) ‘An expert system for voltage
pp.171–177. control and reactive power compensation planning in the HEC
Kim, H., Hayashi, Y. and Nara, K. (1997) ‘An algorithm for system’, 4th Symposium on Expert System Applications to
thermal unit maintenance scheduling through combined use of Power Systems, Melbourne, Australia.
GA, SA and TS’, IEEE Transactions on Power Systems, Le, T., Negnevitsky, M. and Piekutowski, M. (1995) ‘Expert
Vol. 12, No. 1, pp.329–335. system application for voltage control and VAR
Kim, K., Park, J., Hwang, K. and Kim, S. (1995) ‘Implementation compensation’, International Journal of Engineering
of hybrid short-term load forecasting system using artificial Intelligent Systems for Electrical Engineering and
neural networks and fuzzy expert systems’, IEEE Transactions Communications, Vol. 3, No. 2, pp.79–85.
on Power Systems, Vol. 10, No. 3, pp.603–610. Lee, K. and Park, Y. (1995) ‘Optimization method for reactive
King, A., McDonald, J., Burt, G., Spiller, J., Brooke, D. and power planning by using a modified simple genetic algorithm’,
Samwell, R. (1994) ‘Power system restoration using expert IEEE Transactions on Power Systems, Vol. 10, No. 4,
systems’, Proceedings 29th Universities Power Engineering pp.1843–1850.
Conference, Part 1 (of 2), pp.224–227. Lee, K. and Yang, F. (1998) ‘Optimal reactive power planning
Kirschen, D. and Volkmann, T. (1991) ‘Guiding a power system using evolutionary algorithms: a comparative study for
restoration with an expert system’, IEEE Transactions on evolutionary programming, evolutionary strategy, genetic
Power Systems, Vol. 6, No. 2, pp.558–566. algorithm and linear programming’, IEEE Transactions on
Kodogiannis, V. and Anagnostakis, E. (1999) ‘A study of Power Systems, Vol. 13, No. 1, pp.101–108.
advanced learning algorithms for short-term load forecasting’, Lee, K., Cha, Y. and Ku, C. (1991) ‘A study on neural networks
Engineering Applications of Artificial Intelligence, Vol. 12, for short term load forecasting’, Proceedings of ANNPS’91,
pp.159–173. Seattle, pp.26–30.
Koeing, S., Mohr, L., Krost, G., Rumpela, D. and Spanel, U. Lee, K., Cha, Y. and Park, J. (1990) ‘Artificial neural network
(1995) ‘Expert system in training power system restoration at methodology for short term load forecasting’, NSF Workshop
the Stadtwerke Duisberg AG’, International Journal of on Artificial Neural Network Methodology in Power System
Engineering Intelligent Systems for Electrical Engineering and Engineering, Clemson University, SC.
Communications, Vol. 3, No. 3, pp.175–183. Lee, S., Yoon, S., Yoon, M. and Jang, J. (1990) ‘Expert system
Kono, Y., Doi, A. and Omichi, Y. (1991) ‘Development of a for protective relay setting of transmission systems’, IEEE
knowledge-based system for voltage/reactive power operation Transactions on Power Delivery, Vol. 5, No. 2,
planning’, Electr. Eng. Japan, Vol. 111, No. 6, pp.25–35. pp.1202–1208.
INTELLIGENT COMPUTER APPLICATIONS IN THE ENERGY SECTOR: A LITERATURE REVIEW FROM 1990 TO 2003 61

Li, S., Shahidehpour, S. and Wang, C. (1993) ‘Promoting the McDonald, J., Bun, M. and Young, J. (1991) ‘Alarm processing
application of expert systems in short-term unit commitment’, and fault diagnosis using knowledge based systems for
IEEE Transactions on Power Systems, Vol. 8, No. 1, transmission and distribution network control’, Proceedings
pp.286–292. IEEE Power Engineering Society Transmission and
Liang, R. and Cheng, C. (2002) ‘Short-term load forecasting by a Distribution Conference, IEEE Press, Dallas, USA.
neuro-fuzzy based approach’, Electrical Power & Energy Melli, R. and Sciuba, E. (1997) ‘A prototype expert system for the
Systems, Vol. 24, pp.103–111. conceptual synthesis of thermal processes’, Energy Conversion
Liang, R. and Cheng, C. (2002) ‘Short-term load forecasting by a and Management, Vol. 38, Nos. 15–17, pp.1737–1749.
neuro-fuzzy based approach’, Electrical Power and Energy Metaxiotis, Κ., Kagiannas, A., Askounis, D. and Psarras, J. (2003)
Systems, Vol. 24, pp.103–111. ‘Artificial intelligence in short term electric load forecasting: a
Liu, C., Ma, T., Liou, K. and Tsai, M. (1994) ‘Practical use of state-of-the-art survey for the researcher’, Energy Conversion
expert systems in power systems’, International Journal of and Management, Vol. 44, No. 9, pp.1525–1534.
Engineering Intelligent Systems for Electrical Engineering and Minakawa, T., Ichikawa, Y., Kunugi, M., Shimada, K., Wada, N.
Communications, Vol. 2, No. 1, pp.11–22. and Utsunomiya, M. (1995) ‘Development and implementation
Lu, C., Wu, H. and Vemuri, S. (1993) ‘Neural network based short of a power system fault diagnosis expert system’, IEEE
term load forecasting’, IEEE Transactions on Power Systems, Transactions on Power Systems, Vol. 10, No. 2, pp.932–939.
Vol. 8, No. 1, pp.337–342. Miu, K., Chiang, H. and Darling, G. (1997) ‘Capacitor placement,
Lu, F. and Hsu, Y. (1997) ‘Fuzzy dynamic programming approach replacement and control in large-scale distribution systems by
to reactive power/voltage control in a distribution substation’, a GA-based two-stage algorithm’, IEEE Transactions on
IEEE Transactions on Power Systems, Vol. 12, No. 2, Power Delivery, Vol. 12, No. 3, pp.1160–1166.
pp.681–688. Mohamedi, R., Belhadj, C., Lefebvre, S. and Do, X. (1994)
Lu, J., Nehrir, M. and Pierre, D. (2001) ‘A fuzzy logic-based self ‘Expert system for steady state voltage stability’, Proceedings
tuning power system stabilizer optimized with a genetic Canadian Conference on Electrical and Computer
algorithm’, Electric Power Systems Research, Vol. 60, No. 2, Engineering, IEEE Press, Part 2, No. 2, pp.697–701.
pp.77–83. Mohandes, M., Rehman, S. and Halawani, T. (1998) ‘Estimation
Lubarkii, Y., Nadtochii, V., Rabinovich, R., Ornov, V. and of global solar radiation using artificial neural networks’,
Portnoi, M. (1991) ‘Expert systems for power networks’, Renewable Energy, Vol. 14, Nos. 1–4, pp.179–184.
Electrical Technology, Vols. 1–3, pp.1–10. Morris, S., Dash, P. and Basu, K. (2003) ‘A fuzzy variable
Ma, T., Liu, C., Tsai, M., Rogers, R., Muchlinski, S. and Dodge, J. structure controller for STATCOM’, Electric Power Systems
(1992) ‘Operational experience and maintenance of an on-line Research, Vol. 65, No. 1, pp.23–34.
expert system for customer restoration and fault testing’, IEEE Nagata, T., Sasaki, H. and Yokoyama, R. (1995) ‘Power system
Transactions on Power Systems, Vol. 7, No. 2, pp.835–842. restoration by joint usage of expert system and mathematical
Maifeld, T. and Sheble, G. (1994) ‘Short-term load forecasting by programming approach’, IEEE Transactions on Power
a neural network and a refined genetic algorithm’, Electric Systems, Vol. 10, No. 3, pp.1473–1479.
Power Systems Research, Vol. 31, No. 3, pp.147–152. Ng, N., Salama, M. and Chikhani, A. (2000) ‘Capacitor
Mamoh, J., Ma, X. and Tomsovic, K. (1995) ‘Overview and allocation by approximate reasoning: Fuzzy capacitor
literature survey of fuzzy set theory in power systems’, IEEE placement’, IEEE Transactions on Power Systems, Vol. 15,
Transactions on Power Systems, Vol. 10, No. 3, pp.1676–1690. No. 1, pp.393–398.
Mandal, J., Sinha, A. and Parthasarathy, G. (1995) ‘Application of Nissan, E. (1998) ‘Intelligent technologies for nuclear power
recurrent neural network for short term load forecasting in systems: heuristic and neural tools’, Expert Systems with
electric power system’, IEEE International Conference Applications, Vol. 14, pp.443–460.
ICNN’95, Perth, Western Australia, Vol. 5, pp.2694–2698. Novosel, D. and King, R. (1994) ‘Using artificial neural networks
Mansour, M., El-Hadidy, M., Rizk, M. and Moustafa, Y. (1994) for load shedding to alleviate overloaded lines’, IEEE
‘Expert system enhanced by interfaced short circuit Transactions on Power Delivery, Vol. 9, No. 1, pp.425–433.
calculations for Egypt power network fault diagnosis’, Orero, S. and Irving, M. (1996) ‘A genetic algorithm for generator
Proceedings 7th Mediterranean Electrotechnical scheduling in power systems’, Electrical Power & Energy
Conference – MELECON, Part 3 (of 3), pp.901–906. Systems, Vol. 18, No. 1, pp.19–26.
Mantawy, A., Abdel-Magid, Y. and Selim, S. (1999) ‘Integrating Orero, S. and Irving, M. (1998) ‘A genetic algorithm modeling
genetic algorithms, tabu search and simulating annealing for framework and solution technique for short term optimal
the unit commitment problem’, IEEE Transactions on Power hydrothermal scheduling’, IEEE Transactions on Power
Systems, Vol. 14, No. 3, pp.829–836. Systems, Vol. 13, No. 2, pp.501–518.
Mantawy, A., Soliman, S. and El-Hawary, M. (2003) ‘The Ouyang, Z. and Shahidehpour, S. (1990) ‘Short-term unit
long-term hydro-scheduling problem – a new algorithm’, commitment expert system’, Electrical Power Systems
Electric Power Systems Research, Vol. 64, No. 1, pp.67–72. Research, Vol. 20, No. 1, pp.1–13.
Mantawy, A., Youssef, L. and Selim, S. (1999) ‘A new Ouyang, Z. and Shahidehpour, S. (1992) ‘A hybrid artificial neural
genetic-based tabu search algorithm for unit commitment network-dynamic programming approach to unit commitment’,
problem’, Electric Power Systems Research, Vol. 49, No. 2, IEEE Transactions on Power Systems, Vol. 7, No. 1,
pp.71–78. pp.236–242.
Markovic, M. and Fraissler, W. (1993) ‘Short-term load Padhy, N. (2000) ‘Unit commitment using hybrid models: a
forecast by plausibility checking of announced demand: an comparative study for dynamic programming, expert system,
expert-system approach’, European Transactions on Electrical fuzzy system and genetic algorithms’, Electrical Power &
Power Engineering/ETEP, Vol. 3, No. 5, pp.353–358. Energy Systems, Vol. 23, pp.827–836.
Mastorocostas, P., Theocharis, J., Kiartzis, S. and Bakirtzis, A. Padhy, N. (2003) ‘Genetic algorithm-based machine learning
(2000) ‘A hybrid fuzzy modeling method for short-term load classifier system model for short-term unit commitment
forecasting’, Mathematics and Computers in Simulation, problem’, International Journal of Power and Energy Systems,
Vol. 51, pp.221–232. Vol. 23, No. 1, pp.49–61.
Matsuda, S., Ogi, H., Nishimura, K., Okataku, Y. and Tamura, S. Papadakis, S., Theocharis, J., Kiartzis, S. and Bakirtzis, A. (1998)
(1990) ‘Power system voltage control by distributed expert ‘A novel approach to short-term load forecasting using fuzzy
systems’, IEEE Transactions on Industrial Electronics, neural networks’, IEEE Transactions on Power Systems,
Vol. 37, No. 3, pp.236–240. Vol. 13, pp.480–492.
62 K. METAXIOTIS AND A. KAGIANNAS

Papalexopoulos, A., Hao, S. and Peng, T. (1994) ‘An Salam, M., Hamdan, A. and Nor, K. (1991) ‘Integrating an expert
implementation of a neural network based load forecasting system into a thermal unit-commitment algorithm’, IEE Proc.
model for the EMS’, IEEE Transactions on Power Systems, Generation, Transmission and Distribution, Vol. 138, No. 6,
Vol. 9, No. 4, pp.1956–1962. pp.553–559.
Papalexopoulos, A., How, S. and Peng, T. (1994) ‘An Salma, M. and Chikhani, A. (1992) ‘An expert system for reactive
implementation of a neural network based load forecasting power control of distribution systems, Part 1: system
model for the EMS’, IEEE/PES’94 Winter Meeting Paper, configuration’, IEEE Transactions on Power Delivery, Vol. 7,
pp.207–209. No. 2, pp.940–945.
Park, D., El-Sharkawi, M., Marks, I., Atlas, L. and Damborg, M. Santoso, N. and Tan, O. (1990) ‘Neural-net based real-time
(1991) ‘Electric load forecasting using an artificial neural control of capacitors installed on distribution systems’,
network’, IEEE Transactions on Power Systems, Vol. 6, No. 2, IEEE Transactions on Power Delivery, Vol. 5, No. 1,
pp.442–449. pp.266–272.
Park, Y. and Lee, K. (1995) ‘Application of expert system to Sarfi, R. and Solo, A. (2002) ‘Inclusion of human operator
power system restoration in local control center’, International interaction in performance optimization of power distribution
Journal on Electrical Power Energy Systems, Vol. 17, No. 6, operations using knowledge-based methods’, Electric Power
pp.407–415. Systems Research, Vol. 61, No. 3, pp.179–184.
Peng, T., Hubele, N. and Karady, G. (1992) ‘Advancement in the Saric, A. and Calovic, M. and Djukanovic, M. (1997) ‘Fuzzy
application of neural networks for short term load forecasting’, optimization of capacitors in distribution systems’, IEE Proc.
IEEE Transactions on Power Systems, Vol. 7, No. 1, Generation, Transmission and Distribution, Vol. 144, No. 5,
pp.250–258. pp.415–422.
Protopapas, C., Psaltiras, K. and Machias, A. (1991) ‘An expert Sasaki, H., Watanabe, M., Kubokawa, J. and Yorino, N. (1992)
system for substation fault diagnosis and alarm processing’, ‘A solution method of unit commitment by artificial neural
IEEE Transactions on Power Delivery, Vol. 6, No. 2, networks’, IEEE Transactions on Power Systems, Vol. 7,
pp.648–655. No. 3, pp.974–981.
Prudenzi, A. (1996) ‘A neural network based technique for Satpathy, P., Das, D. and Dutta Gupta, P. (2002) ‘A novel fuzzy
short-term forecasting of anomalous load periods’, IEEE index for steady state voltage stability analysis and
Transactions on Power Systems, Vol. 11, No. 4, pp.1749–1756. identification of critical busbars’, Electric Power Systems
Rahim, A. and Al-Baiyat, S. (2000) ‘Dynamic brake switching Research, Vol. 63, No. 2, pp.127–140.
strategies for stabilization of power systems using artificial Sforna, M. (1998) ‘NEUFOR: a tool for the online short-term load
neural networks’, Expert Systems with Applications, Vol. 18, forecasting correction’, Electric Power Systems Research,
No. 2, pp.101–109. Vol. 48, pp.25–30.
Rahman, S. and Hazim, O. (1993) ‘A generalized Sforna, M. (2000) ‘Data mining in a power company customer
knowledge-based approach to short term load forecasting’, database’, Electrical Power Systems Research, Vol. 55, No. 3,
IEEE Transactions on Power Systems, Vol. 8, No. 2, pp.201–209.
pp.508–514. Sforna, M. and Proverbio, F. (1995) ‘A neural network operator
Rahman, S. and Hazim, O. (1996) Load Forecasting for Multiple oriented short-term and online load forecasting environment’,
Sites: Development of an Expert System-Based Technique, Electric Power Systems Research, Vol. 33, pp.139–149.
Center for Energy and the Global Environment, Bradley Sharaf, A. and Lie, T. (1995) ‘A novel neuro-fuzzy based
Department of Electrical Engineering, Virginia Polytechnic self-correcting online electric load forecasting model’,
Institute and State University Blacksburg, VA 24061, USA. Electric Power Systems Research, Vol. 34, No. 2, pp.121–125.
Ramakrishna, G. and Rao, N. (1995) ‘Fuzzy logic framework for Shehle, G. and Briting, K. (1995) ‘Refined genetic
control of switched capacitors in distribution systems’, Proc. algorithm-economic dispatch example’, IEEE Transactions on
1995 Canadian Conf. Electrical and Computer Engineering, Power Systems, Vol. 10, No. 1, pp.227–132.
Part 2 (of 2), Montreal, Quebec, Canada, pp.676–679. Sherwali, H. and Crossley, P. (1994) ‘Expert system for fault
Ramanathan, R., Engle, R., Granger, C., Vahid-Araghi, F. and location on a transmission network’, Proceedings 29th
Brace, C. (1997) ‘Short run forecasts of electricity loads Universities Power Engineering Conference, Part 2 (of 2),
and peaks’, International Journal of Forecasting, Vol. 13, pp.751–754.
pp.161–174. Shin, J. and Park, Y. (1993) ‘Optimal long-term transmission
Rementeria, C., Rodriguez, C., Perez, J. and Martin, J. (1995) planning by expert system approach’, Proc. IEEE Region 10
‘Expert systems neural networks in power grid fault diagnosis: Con. Computer, Communication, Control and Power
an empirical comparison’, International Journal of Engineering, Part 2 (of 5), pp.713–717.
Engineering Intelligent Systems for Electrical Engineering and Singh, S., Raju, G. and Gupta, A. (1993) ‘Sensitivity based expert
Communications, Vol. 3, No. 1, pp.33–44. system for voltage control in power system’, International
Richter, C., Sheble, G. and Ashlock, D. (1999) ‘Comprehensive Journal on Electrical Power and Energy Systems, Vol. 3,
bidding strategies with genetic programming/finite state pp.131–136.
automata’, IEEE Transactions on Power Systems, Vol. 14, Song, Y. and Johns, A. (1997) ‘Applications of fuzzy
No .4, pp.1207–1212. logic in power systems, Part 1: general introduction to fuzzy
Romero, S. and Binato, S. (1998) ‘Power transmission network logic’, IEE Power Engineering Journal, Vol. 11, No. 5,
expansion planning by a hybrid genetic algorithm’, VI pp.219–222.
Symposium in electric Operational and Expansion Planning Song, Y. and Johns, A. (1998) ‘Applications of fuzzy logic in
(SEPOPE), Salvador-BA, Brazil. power systems, Part 3’, IEE Power Engineering Journal,
Roy, A. and Goswami, S. (1996) ‘Development of artificial neural Vol. 12, No. 6, p.3.
networks for solving capacitor control problem in distribution Sozen, A., Kurt, M., Akcayol, M. and Ozalp, M. (2004)
network’, 9th National Power Systems Conference, Kanpur, ‘Performance prediction of a solar driven ejector-absorption
India, pp.413–416. cycle using fuzzy logic’, Renewable Energy, Vol. 29, No. 1,
Rumpel, D., Krost, G. and Alder, T. (1992) ‘Training simulator pp.53–71.
with an advising expert system for power system restoration’, Srinivasan, D., Chang, C. and Liew, A. (1994) ‘Multiobjective
Proceedings IFAC Symposium on Control of Power Plants and generation scheduling using fuzzy optimal search technique’,
Power Systems, IFAC Symposia Series No. 9, Munich, IEE Proc. Generation, Transmission and Distribution,
Germany, pp.451–456. Vol. 141, No. 3, pp.233–242.
INTELLIGENT COMPUTER APPLICATIONS IN THE ENERGY SECTOR: A LITERATURE REVIEW FROM 1990 TO 2003 63

Srinivasan, D., Chang, C. and Liew, A. (1995) ‘Demand Venkatesh, B., Sadasivam, G. and Khan, M. (1999b) ‘Optimal
forecasting using fuzzy neural computation, with special reactive power planning against voltage collapse using the
emphasis on weekend and public holiday forecasting’, successive multiobjective fuzzy LP technique’, IEE Proc.
IEEE Transactions on Power Systems, Vol. 10, No. 4, Generation, Transmission and Distribution, Vol. 146, No. 4,
pp.1897–1903. pp.343–348.
Stedall, B., Moore, P. and Johns, A. (1994) ‘Application of expert Venkatesh, B., Sadasivam, G. and Khan, M. (2001) ‘An efficient
systems in power system protection’, Proceedings 29th multi-objective fuzzy logic based successive LP method for
Universities Power Engineering Conference, Part 2 (of 2), optimal reactive power planning’, Electric Power Systems
pp.759–762. Research, Vol. 59, No. 2, pp.89–102.
Su, C. and Hsu, Y. (1991) ‘Fuzzy dynamic programming: an Vermaak, J. and Botha, E. (1998) ‘Recurrent neural networks for
application to unit commitment’, IEEE Transactions on Power short-term load forecasting’, IEEE Transactions on Power
Systems, Vol. 6, No. 3, pp.1231–1237. Systems, Vol. 13, No. 1, pp.126–132.
Su, C. and Lii, G. (1999) ‘Reliability planning for composite Weber, J. and Overbye, T. (1999) ‘A two-level optimization
electric power systems’, Electric Power Systems Research, problem for analysis of market bidding strategies’, Proc. IEEE
Vol. 51, No. 1, pp.23–31. Power engineering Society 1999 Summer Meeting, pp.682–687.
Su, C. and Lii, G. (2002) ‘Reliability design of distribution system Wen, F. and Kumar David, A. (2001) ‘A genetic algorithm based
using modified genetic algorithms’, Electric Power Systems method for bidding strategy coordination in energy and
Research, Vol. 60, No. 3, pp.201–206. spinning reserve markets’, Artificial Intelligence in
Su, C. and Lin, C. (1996) ‘A new fuzzy control approach to Engineering, Vol. 15, No. 1, pp.71–79.
voltage profile enhancement for power systems’, White, R. (1990) ‘Feasibility of an expert system for planning
IEEE Transactions on Power Systems, Vol. 11, No. 3, commitment schedules of generating units’, Proceedings 52nd
pp.1654–1659. American Power Congress, Illinois Institute of Technology,
Su, C. and Lin, C. (2001) ‘Fuzzy-based voltage/reactive power Chicago, USA.
scheduling for voltage security improvement and loss Wu, Q., Cao, Y. and Wen, J. (1998) ‘Optimal reactive power
reduction’, IEEE Transactions on Power Systems, Vol. 16, dispatch using an adaptive genetic algorithm’, Electrical
No. 2, pp.319–323. Power and Energy Systems, Vol. 20, No. 8, pp.563–569.
Tamimi, M. and Egbert, R. (2000) ‘Short term electric load Xia, Q., Song, Y., Zhang, B., Kang, C. and Xiang, N. (2000)
forecasting via fuzzy neural collaboration’, Vol. 56, No. 3, ‘Effective decomposition and co-ordination algorithms for unit
pp.243–248. commitment and economic dispatch with security constraints’,
Tomsovic, K. (1992) ‘A fuzzy linear programming approach to the International Journal of Electric Power Systems Research,
reactive power/voltage control problems’, IEEE Transactions Vol. 53, pp.39–45.
on Power Systems, Vol. 7, No. 1, pp.287–293. Yalcinoz, T. and Short, M. (1998) ‘Neural networks approach for
Tong, S., Shahidehpour, S. and Ouyang, Z. (1991) ‘A heuristic solving economic dispatch problem with transmission capacity
short-term unit commitment’, IEEE Transactions on Power constraints’, IEEE Transactions on Power Systems, Vol. 13,
Systems, Vol. 6, No. 3, pp.1210–1216. No. 2, pp.307–313.
Urdaneta, A., Gomez, J., Sorrentino, E., Flores, L. and Diaz, R. Yang, H., Chang, W. and Huang, C. (1995) ‘On-line fault
(1999) ‘A hybrid genetic algorithm for optimal reactive power diagnosis of power substation using connectionist expert
planning based upon successive linear programming’, system’, IEEE Transactions on Power Systems, Vol. 10, No. 1,
IEEE Transactions on Power Systems, Vol. 14, No. 4, pp.323–331.
pp.1292–1298. Yang, H., Huang, C. and Huang, C. (1995) ‘Identification of
Vajpai, J., Singhal, S. and Naizi, K. (2001) ‘Expert system based ARMAX model for short term load forecasting: an
on line optimal control of reactive power’, Proc. All India evolutionary programming approach’, Proceedings of the 1995
Seminar, Power Systems: Recent Advances and Prospects in IEEE Power Industry Computer Applications Conference
21st Century, Jaipur, India, pp.194–208. (PICA), Salt Lake City, USA, pp.325–330.
Vale, A. and Moura, A. (1993) ‘Expert system with temporal Yang, H., Yang, P. and Huang, C. (1997) ‘A parallel genetic
reasoning for alarm processing in power system control algorithm approach to solving the unit commitment problem:
centers’, IEEE Transactions on Power Systems, Vol. 8, No. 3, implementation on the transputer network’, IEEE Transactions
pp.1307–1314. on Power Systems, Vol. 12, No. 2, pp.661–669.
Vale, A., Santosm, J. and Ramos, C. (1997) ‘SPARSE – a prolog Yao, S., Song, Y., Zhang, L. and Cheng, X. (2000) ‘Wavelet
based application for the Portuguese transmission network: transform and neural networks for short-term electrical load
verification and validation’, PAP’97 – Practical Application in forecasting’, Energy Conversion & Management, Vol. 41,
Prolog, London, UK. pp.1975–1988.
Vale, Z., Ramos, C., Silva, A., Faria, L., Santos, J., Fernandes, M., Yongli, Z., Yang, Y., Hogg, B., Zhang, W. and Gao, S. (1994)
Rosado, C. and Marques, A. (1998) ‘SOCRATES – an ‘Expert system for power systems fault analysis’, IEEE
integrated intelligent system for power system control center Transactions on Power Systems, Vol. 9, No. 1, pp.503–509.
operator assistance and training’, International Conference on Yoo, H. and Pimmel, R. (1999) ‘Short term load forecasting using
Artificial Intelligence and Soft Computing (IASTED), Cancun, self-supervised adaptive neural network’, IEEE Transactions
Mexico. on Power Systems, Vol. 14, No. 2, pp.779–784.
Vankayala, V. and Rao, N. (1992) ‘Conceptual ANN-ES scheme Youssef, H. (2001) ‘Dynamic transmission planning using a
for power system security assessment and preventive control’, constrained genetic algorithm’, Electrical Power and Energy
Canadian Journal of Electrical & Computer Engineering, Systems, Vol. 23, pp.857–862.
Vol. 17, No. 1, pp.48–50. Youssef, H. and El-Naggar, K. (2000) ‘Genetic based algorithm
Vankayala, V. and Rao, N. (1993) ‘Artificial neural networks for security constrained power system economic dispatch’,
and their applications to power systems: a bibliographical Electric Power Systems Research, Vol. 53, No. 1, pp.47–51.
survey’, Electric Power Systems Research, Vol. 28, Ypsilantis, J. and Yee, H. (1990) ‘Survey of expert systems for
pp.67–79. SCADA-based power applications’, 4th Conference in Control
Venkatesh, B., Sadasivam, G. and Khan, M. (1999a) ‘Fuzzy logic Engineering, Gold Coast, Australia, pp.177–183.
based successive LP method for reactive power optimization’, Yu, D., Fu, L. and Vairavan, A. (1990) ‘A knowledge-based alarm
Electric Machines and Power Systems, Vol. 27, No. 10, processor for an energy management system’, IEEE
pp.1141–1160. Transactions on Power Systems, Vol. 5, No. 1, p.2.
64 K. METAXIOTIS AND A. KAGIANNAS

Zadeh, L. (1965) ‘Fuzzy sets’, Information and Control, Vol. 8, Zhou, B., Chowdhuym, N. and Slade, D. (1996) ‘A case-based
pp.338–353. intelligent agent for power system restoration’, Canadian
Zhang, B. and Dong, Z. (2001) ‘An adaptive neural-wavelet model Conference of Electrical & Computer Engineering, Calgary,
for short term load forecasting’, Electric Power Systems pp.369–372.
Research, Vol. 59, pp.121–129. Zhu, J. (2002) ‘Optimal reconfiguration of electrical distribution
Zhang, D., Wang, Y. and Luh, P. (2000) ‘Optimisation network using the refined genetic algorithm’, Electric Power
based bidding strategies in the deregulated market’, Systems Research, Vol. 62, No. 1, pp.37–42.
IEEE Transactions on Power Systems, Vol. 15, No. 3, Zitouni, S. and Irving, M. (1999) NETMAT: A Knowledge-Based
pp.981–986. Grid System Analysis Tool.