Energy enhancement using Multiobjective Ant colony optimization with Double Q learning algorithm for IoT based cognitive radio networks

Abstract

Internet of Things (IoT) is the efficient wireless communication in the modern era, energy efficiency is the primary issue that focuses mainly on the Cognitive network. Most of the CR networks are focusing on battery powdered to predominantly utilize the data dissipated in terms of spectrum sharing, dynamic spectrum access, routing and spectrum allocation. The clustering and data aggregation are the best efforts technique to enhance the energy modeling. Multiobjective Ant colony optimization (MOACO)and greedy based optimization proposed with Deep Reinforcement Learning with Double Q-learning algorithm. Most of the IoT bed models involve data aggregation and energy constrained devices with optimization techniques to enhance utilization. The cluster-based data utilization is proposed with the Q-learning algorithm and it enhances the inter cluster data aggregation. The network lifetime is improved with AI-based modeling with intra-network to enhance green communication. The simulation experiments showcase that the throughput, lifetime and jamming prediction is analyzed and enhances the energy using the MOACO, when compared to the artificial bee colony and genetic algorithm. The jamming activity at low, high moderate stages is analyzed using the AI and MOACO algorithms.