Date of Award

6-11-2024

Document Type

Thesis

School

School of Computing

Programme

Ph.D.-Doctoral of Philosophy

First Advisor

Prof.R.Muthaiah

Keywords

Wireless Networks, Artificial Intelligence, Spectrum Sensing and Allocation

Abstract

Cognitive radio (CR) refers to intelligent radio technology that scans its environment to optimize spectrum use and adjusts its parameters accordingly. It employs a communication system that is aware of its surroundings, including spectrum usage and availability. A key aspect of CR is identifying idle channels by analyzing traffic patterns using effective learning strategies.

However, CRNs face challenges such as cross-layer design issues, spectrum sensing errors, hidden node problems, and complex spectrum management. Spectrum sensing is critical for accessing unused radio spectrum while minimizing interference. Efficient sensing techniques must be cost-effective, fast, and capable of detecting weak primary signals. Although researchers have proposed effective methods for spectrum utilization, significant complexities and errors persist.

Recent advancements aim to enhance spectrum sensing and allocation in CRNs. One approach involves the Enhanced Threshold-Based Energy Detection (ETBED) method, which uses a dynamic threshold based on signal ratio. The Modified Black Widow Optimization Algorithm (MBWO) further refines the threshold calculation, combining dynamic threshold detection with MBWO for improved performance. For spectrum allocation, the Enhanced Deep Reinforcement Learning Approach (EDRLA) integrates Deep Reinforcement Learning (DRL) and Adaptive xiii War Strategy (AWS).

This approach leverages historical channel utilization data to train models on channel and time correlations, with the Q-table updated using AWS. Additionally, the Modified Gannet Optimization Algorithm Entropy Detection (MGOAED) improves energy efficiency in CRNs. By incorporating the Oppositional Function (OF) into the Gannet Optimization Algorithm (GOA), the solution initialization process is enhanced, allowing CRNs to achieve better energyefficient operation.

Download

Share

COinS