Enhanced deep learning-based optimization model for the optimal energy efficiency-oriented Cognitive Radio Networks

Abstract

Cognitive Radio Networks (CRNs) offer a promising solution to spectrum scarcity by enabling secondary users (SUs) to utilize unused spectrum allocated to primary users (PUs). However, optimizing energy efficiency (EE) while protecting PUs from interference remains a significant challenge. This paper presents a novel approach using an Enhanced Long Short-Term Memory (ELSTM) model, fine-tuned by the Red Panda Optimization (RPO) algorithm, to optimize CRN parameters such as transmission time, transmission power, and sensing time. The motivation behind this work is to enhance EE in CRNs without compromising PU protection, driven by the increasing demand for efficient spectrum utilization in wireless communications. The key contributions of this study include the introduction of the ELSTM-RPO model, which is the first of its kind in CRNs, providing systematic optimization of crucial parameters, and outperforming state-of-the-art methods in terms of EE and spectrum utilization. This work sets a new benchmark for energy-efficient CRNs, offering superior performance and robustness across various network scenarios.

Keywords

• Cognitive Radio Networks
• Optimal Energy Efficiency
• Enhanced Long Short-Term Memory Model
• Red Panda Optimization
• Transmission Time
• Transmission Power