REVIEW ON RESOURCE ALLOCATION FOR ENERGY HARVESTING- COGNITIVE RADIO NETWORKS
Main Article Content
The primary purpose of resource allocation (RA) in traditional wireless networks is to maximize the use of the available resources. The most important thing to focus on regarding this environment's significant aspects is efficient resource distribution between primary users (PU) and secondary users (SU). However, these spectrum allocation strategies result in underutilization. Cognitive radio networks (CRNs) have drawn much interest in this respect because of their potential to increase spectrum use. Effective spectrum management and resource distribution are generally necessary for CRNs. The SU shares the spectrum by aiding the main transmission when the energy is insufficiently strong to sustain direct communication between two PUs. Spectrum occupancy prediction, also known as channel state prediction, has been integrated into cognitive radio (CR) in recent years to help deal with spectrum resource shortage and boost spectrum usage effectiveness. This work overviews the most recent developments in spectrum resource allocation. Every technology relies heavily on machine learning. Machine learning algorithm train cognitive radio to predict free spectrum. Cognitive radio uses it to forecast open spectrum. Energy harvesting –Cognitive Radio Network (EH-CRN) is a viable way to overcome spectrum shortages and energy usage in wireless.