Domain

MACHINE LEARNING

Machine Learning (ML) is a branch of artificial intelligence

that enables computers to learn from data and make
decisions or predictions without being explicitly
programmed for every task. It focuses on creating
algorithms that improve over time as they are exposed to
more data.

02
Abstract
Quantum Machine Learning (QML) enhances
resource management in 6G by combining
lightweight hybrid attention networks with
optimization frameworks like GA, PSO, and DE.
The system reduces latency, increases
throughput, improves energy efficiency, and
enhances prediction accuracy.

03
Introduction
 Overview of the Project :
Introduces a quantum-inspired machine learning framework for dynamic resource allocation in 6G wireless networks. This
system aims to overcome classical machine learning limitations and improve 6G network performance and sustainability.

3
Introduction
 Problem Statement:
As 6G networks aim to support massive data traffic, ultra-low latency, and energy-efficient communication, traditional machine learning
models like CNNs and SVR face limitations such as high computational cost, poor scalability, and slow response in real-time environments .

4
Introduction
 Objectives of the Project:

To develop an efficient quantum machine

learning-based framework for dynamic resource
allocation in 6G wireless networks. It aims to
overcome the limitations of classical ML models
by using a lightweight hybrid attention network
using Genetic Algorithm , Particle Swarm
Optimization and Differential Evolution
Algorithm.

5
Literature Review
Author Technique/ Performance
S.
Name & Title of the Paper Algorithm Metrics Limitations
No
Year Implemented Considered

1 Ahmed et al. Energy-Efficient Quantum- Inspired Scheduling Task completion

(2024) Scheduling In Iot Evolutionary delays, algorithm time, energy
Networks Using Algorithms complexity consumption,
Quantum Inspired system
Evolutionary throughput
Algorithms
2 Ashwin et al. Efficient Resource Quantum- Enhanced Short coherence Bandwidth,
(2023) Management In 6g Resource times, and latency, energy
Wireless Management susceptibility to budget, channel
Communication Algorithm noise gain, number of
users

3 Bhattac et al. Deep Learning Deep Q- Learning High Spectrum

(2022) For computational availability, trust
Secure Spectrum cost, exploration- factor, node
Allocation exploitation trade- density, learning
For Clustered off rate
Cognitive M2m
Communication
 Literature Review
4 Gong et al. Optimization Driven Hierarchical Deep Convergence Backscatter link
(2022) Hierarchical Learning Reinforcement Learning complexity, energy quality, energy state
For Wireless Powered harvesting
Backscatter inefficiency

5 Pruthvi kumar AI Enhanced Hybrid AI- Quantum Hardware Qubit count, error
et al. (2022) Quantum Assisted Algorithm immaturity, rate, user demand,
Wireless integration SNR
Communication For complexity
6g Wireless
Technology
6 Sharrif et al. A Meta Hybrid Cryptographic- Infrastructure cost, Encryption
(2023) Reinforcement Steganographic Model complexity strength,
Learning Based embedding rate
Virtual Machine
Placement Algorithm

7 Sykot et al. Multi-Layered Hybrid Cryptographic- Infrastructure cost, Encryption

(2023) Security System: Steganographic Model complexity, latency strength,
Integrating Quantum overhead embedding rate, key
Key length
Distribution, AES
 Literature Review
7 Talasila et al. The Hybrid Model Of AES & RSA & LSB Vulnerable to Pixel bit depth, key
(2022) Lsb Technique In Steganography steganalysis if not size, payload size
Image Steganography optimized
Using Aes And Rsa
Algorithms

8 Teja et al. Enhancing Dual Layer LSB Steganographic LSB depth, AES
(2023) Steganography detectability block size, PSNR
Security: A Dual
Layer
Approach With Lsb
And Aes Algorithm
9 Wang et al. Comprehensive Multiple Quantum Quantum device Qubit usage,
(2022) Review Of Algorithms (QFT, limitations, encryption time,
Quantum Image QPKE, QRC) scalability image size
Encryption Methods:
Design, Analysis And
Optimization

10 Wang et al. Quantum Quantum Local Hardware- Threshold window

(2023) Segmentation Threshold dependent, sensitive size, pixel value
Algorithm For to quantum noise distribution
Neqr Image Using
Local
Adaptive Thresholds
 Literature Review
11 Xiong et al. Energy Efficiency Joint RIS- SWIPT RIS phase shift RIS configuration,
(2023) Maximization In Optimization Algorithm complexity, energy power splitting ratio
Ris-Assisted Swipt beamforming
Networks limitations

12 Xu et al. Meta Reinforcement Meta-RL & Policy Slow adaptation to VM type, service
(2023) Learning-Based Gradient abrupt workload latency, resource
Virtual Machine demand
Placement Algorithm
In Mobile Edge
Computing
13 Kim Quantum Computing- Quantum- Inspired Hardware Node density,
et al(2022) Inspired Genetic Genetic Algorithm dependency, energy
Algorithm For scalability issues consumption,
routing efficiency

14 Hassan Quantum computing Quantum- Inspired Quantum hardware Network

et al.(2022) approaches for Optimization limitations, throughput, latency,
network optimization Algorithms algorithm energy efficiency
in complexity
5G
 Literature Review
15 Nguyen Energy-Efficient Quantum- Inspired Algorithm Energy
et al.(2023) Resource Resource Management convergence issues, consumption, node
ManagementIn Algorithms hardware lifetime, data
Wireless Sensor requirements throughput
Networks Using
Quantum- Inspired
Algorithms
16 Duong Quantum- Inspired Quantum- Inspired ML Data privacy Resource allocation
et al.(2022) Machine Learning Framework concerns, model efficiency, energy
Framework For interpretability consumption,
Energy-Efficient network throughput
Resource Allocation
In
18 Patel Hybrid Quantum- Integration Energy efficiency,
et al.(2022) Hybrid Quantum- Classical Algorithms challenges, signal quality,
Classical Algorithms computational system reliability
For overhead
Energy-Efficient
Wireless
Communications
19 Kim Quantum- Quantum- Inspired Coordination Spectrum
et al.(2022) InspiredMulti- Agent Multi- Agent complexity, utilization,
Reinforcement Reinforcement convergence issues interference
Learning Learning management, agent
cooperation
 Literature Review
20 Li et al. (2023) Quantum- Inspired Quantum- Inspired Deep Model training time, Power control
Deep Learning Learning Framework data requirements efficiency, network
Framework For Power capacity, signal
Control In quality
Ultra-Dense Networks
Existing System / Methodology
Used
• Existing wireless networks mostly use traditional
machine learning methods to manage resources.
But they often have trouble handling changing
user needs, unstable network signals, and
energy limits.

Algorithm used:
Convolutional Neural Networks(CNNs)
And Support Vector Regression (SVR).

12
Parameters
• Existing systems take into account various
parameters based on the specific application,
such as bandwidth, latency, energy budget,
channel gain, number of users, spectrum
availability.

13
Limitations
 Lacks adaptability for dynamic 6G networks
 High system complexity

 Energy efficiency challenges

 Struggles with ultra-low latency

 Security and privacy concerns

14
Proposed System / Methodology
The proposed system integrates Quantum Machine Learning
(QML) with a Lightweight Hybrid Attention Network (LHAN) to
efficiently extract features and predict optimal resource
allocation in 6G wireless networks. A hybrid optimization
engine using Genetic Algorithm (GA), Particle Swarm
Optimization (PSO), and Differential Evolution (DE)
dynamically allocates bandwidth, power, and channels to
improve throughput, reduce latency, and enhance energy
efficiency.

15
 Module Diagram:

16
Module Description
 Data Collection: Gathers real-time network
data
 Preprocessing: Cleans and normalizes data

 Feature Extraction: Uses LHAN

 Optimization: Combines GA, PSO, DE

 Feedback: Tracks metrics for continual

improvement

17
Algorithm
 Collect and preprocess input data
 Feature Extraction using Lightweight

Hybrid Attention Network (LHAN)

 Apply Genetic Algorithm operations

 Apply Particle Swarm Optimization update

 Apply Differential Evolution

 Select the best solution

 Deploy the optimized resource allocation

18
Performance Metrics
 LatencyReduction
 Throughput over Time

 Energy Efficiency

 Accuracy

19
Tools / System Requirements

Hardware Requirements
•Processor: Intel i3 or a higher equivalent processor
•RAM: 8 GB or higher
•Hard Disk: 500 GB or higher
Software Requirements
•Operating System: Windows 10
•Programming Language: Python 3.8
•IDE: Anaconda

20
System Implementation
Experimental Setup
The experimental setup includes setting up the

network with key factors like bandwidth, delay,

energy limits, signal quality, number of users, and
available spectrum.
It also involves using learning algorithms with set

learning speeds and checking how the system

performs when the number of network nodes and
trust levels change.

21
Comparison Chart
 Latency reduction

System Latency (ms)

Existing 110

Proposed 52

22
 Throughput over Time

System Throughput (Mbps)

Existing 165

Proposed QML 230

23
 Energy Efficiency

Energy Efficiency
System
(bits/Joule)

Existing 9

Proposed QML 15

24
 Accuracy

System Accuracy (%)

Existing(CNN) 80

Proposed QML 92

25
Results Discussion

 Comparison Table of Existing and Proposed System

Existing System Proposed System

Parameter

Latency High (~110 ms) Low (~52 ms)

Energy Efficiency Lower (~9 bits/Joule)

Higher (~15 bits/Joule)
Throughput Lower (~165 Mbps) Higher (~230 Mbps)

Prediction Accuracy Moderate (~80%)

Improved (~92%)
Scalability & Poor
Adaptability Excellent

26
Result
The project develops a QML-based framework to
optimize 6G resource allocation using GA,PSO,DE
hybrid algorithm. It improves latency, energy
efficiency, throughput, and accuracy compared to
traditional methods . The results show the system is
efficient, scalable, and suitable for future 6G
networks.

27
Screenshot

28
Conclusion
 The QML model worked well in a simulated
6G network. It was able to quickly adjust to
changes in the network, like more users or
weaker signals.
 The system reduced delays, increased data

speed, and saved energy. This shows that

QML can help future 6G networks become
faster, smarter, and more efficient.

29
Future Enhancement
 Inthe future, the system can use real-time
network data to improve accuracy. More
advanced quantum algorithms and security
features can also be added for better
performance.

30
References
 Ahmad F., Mahmood A., and Rashid M., “Energy- efficient
scheduling in IoT networks using quantum-inspired evolutionary
algorithms,” IEEE Internet Things J., vol. 9, no. 6, pp. 4248–4259,
March 2022.(Base paper)
 Ashwin M, Alqahtani A. S, Mubarakali .A and Sivakumar S, “A
resource management in 6G communication networks using hybrid
quantum deep learning model,” Computers and Electrical
Engineering, vol. 106, art. p108565, Mar. 2023.
 Bhattac harya P, Patel F, Alabdulatif A, Gupta R, Tanwar, Kumar N,
and sharma R, “A deep-Q learning scheme for secure spectrum
allocation and resource management in 6G environment,” IEEE
Trans. Netw. Serv. Manag., vol. 19, no. 4, pp. 4989–5005, Dec.
2022.

31
References
 Duong T.Q., Ansere J.A., Narottama B., and Shin H., “Quantum-
inspired machine learning framework for energy -efficient resource
allocation in wireless communication networks,” IEEE Trans.
Wireless Commun., vol. p21, no. 1, pp. 1234–1246, Jan. 2022.
 Gong S, Zou Y, Xu J, Hoang Y, Lyu Y, and Niyato D, “Optimization-
driven hierarchical learning framework for wireless powered
backscatter-aided relay communications,” IEEE Trans. Commun.,
vol. 21, no. 2, pp. 1378–1391, Feb. 2022.
 Hassan W., Khan M., and Ahmed S., “Quantum computing
approaches for network optimization in 5G and beyond,” IEEE
Network, vol. 36, no. 5, pp. p50–56, Sept./Oct. 2022.
 Kim S., and Park H., “Quantum-inspired multi-agent reinforcement
learning for spectrum sharing in wireless networks,” IEEE Wireless
Commun. Lett., vol. 11, no. 8, pp. 1620–1624, Aug. 2022.
32
References
 Li X., and Tang J., “Quantum-inspired deep learning framework for
power control in ultra-dense networks,” IEEE Trans. Veh. Technol.,
vol. 72, no. 5,pp. 5993–6004, May 2023.
 Nguyen T.D., Kim J.H., and Park S., “ Energy- efficient resource
Management in wireless sensor networks using quantum-inspired
algorithms,” Sensors, vol. 22, no. 4, pp. 1567, Feb. 2023.
 Patel D., and Mehta N., “Hybrid quantum-classical algorithms for
energy- efficient wireless communications,” IEEE Trans. Green
Commun. Netw., vol. 7, no. 4, pp. 1985–1996, Dec. 2022.
 Pruthvi Kumar , Neeralakeri M .K , Madhumathy M. P and Vinoth
Kumar V M, “AI-Enhanced Quantum-Assisted Wireless
Communication for 6G Networks,” Journal of Advancement in
Electronics Design, 2022.
33
References
 Sakir Mahoomed Abas, Salar Faisal Noori, Yuvaraj D, Shanmuga Priya S
“Quantum Computing -Inspired Genetic Algorithm For Network
Optimization In Wireless Sensor Networks”, Feb-2023.
 Sharifi M, Feghhi M .M, Azarnia G, Nouri S, Lee G, and Piran R.M, “
Channel estimation based on compressed sensing for massive systems
with Lens Antenna Array,” IEEE Access, vol. 11, pp. 79032, Jul. 2023.
 Sykot A, Azad MS, Tanha WR, Morshed BMM, Shubha SEU, Mahdy MRC
Multi-layered security system: Integrating quantum key distribution, AES
encryption, and steganography. Ain Shams Eng J. 2025;16(2):101499.
 Talasila S, Vijaya Kumar G, Vijaya Babu E, Nainika K, Veda Sahithi M,
Mohan P. The hybrid model of LSB—technique in image steganography
using AES and RSA algorithms. Lect Notes Netw Syst. 2023;845:449–
458(2022).

34
References
 Teja P, Kumar VP. Enhancing steganography security:A dual
layer approach with LSB and AES algorithm. Note Netw
Syst. 2023;697: 349–359.
 Wang J, Qiu J, Zhang Z. A comprehensive review of quantum
image encryption methods: Design, analysis, and optimization.
Quantum Inf Process. 2023;22(12):450.
 Wang L., & Liu W. (2023). Quantum segmentation algorithm for
NEQR images using local adaptive thresholds. Journal of Quantum
Information Processing, 22(10), 1–12.
 Xiong J, Lu Y, Fan P, D. W. K. Ng, and K. B. Letaief, “Energy
efficiency maximization in RIS-assisted SWIPT networks with
RSMA: A PPO- based approach,”IEEE J. Sel. Areas Commun., vol.
no. 5, pp. 1413–1430, May-2023.

35
References
 Xu Y and Jian C, “A meta reinforcement learning- based virtual
machine placement algorithm in mobile edge computing,” Cluster
Computing, pp. p1– 14, Jun. 2023.
 Feghhi M . M , Azarnia G, Nouri S, Lee G, and Piran R .M,
“Channel estimation based on compressed sensing for massive
systems with Lens Antenna Array,” IEEE Access, vol. 11, pp.
79032, Jul. 2023.

36
List of Publications

 Sathya T, Menaka S.R, Sathishkumar T, Dharani G, Balamurugan K

“REVOLUTIONING 6G WIRELESS NETWORKS THROUGH
ADVANCED QML TO OPTIMIZE RESOURCE MANAGEMENTAND
ENHANCE ENERGY EFFICIENCY: International Journal
of Innovative Research in Computer and Communication
Engineering, volume 12, issue 12, November 2024.

37
40
Thank
you
41