Optimal path selection using reinforcement learning based ant colony optimization algorithm in IoT-Based wireless sensor networks with 5G technology

The Internet of Things (IoTs) expanded quickly, giving rise to numerous services, apps, electronic devices with integrated sensors, and associated protocols, which are still being developed today. By enabling physical objects to communicate with each other and share important information while making decisions and carrying out their essential jobs, the IoTs enable them to see, hear, think, and execute crucial tasks. Wireless sensor networks (WSN), which act as the IoT's permanent layer, are essential for fifth-generation (5G) communications, which need the IoT to be considerably helped. A WSN comprises many sensor nodes that track and transmit data to the sink. Every round's data transmission ends at the sink (or base station). This work presents a Proximal Policy Optimization based Ant Colony Optimization (PPO-ACO) algorithm for optimal path selection in WSN. The proposed algorithm combines the strengths of both PPO with a reinforcement learning (RL) method, and ACO, a swarm intelligence method, to address the stochastic nature of the network and the complex trade-off between energy efficiency and security. The PPO component learns the policy for path selection based on the sampled rewards, while the ACO component updates the pheromone levels to guide the search toward the optimal path. Compared to the state-of-the-art, our simulation findings show that the suggested PPO-ACO algorithm performs better in terms of the number of active nodes. The average residual energy of the suggested algorithm decreases later than existing algorithms, indicating its higher efficiency.