ADAPTIVE REINFORCEMENT LEARNING-BASED ROUTING ALGORITHM FOR ENERGY-EFFICIENT IOT WIRELESS SENSOR NETWORKS

Abstract

The article proposes an adaptive routing algorithm for improving energy efficiency in wireless sensor networks within Internet of Things environments. The proposed approach is based on reinforcement learning and enables sensor nodes to dynamically adapt routing decisions according to network conditions and residual node energy. The algorithm uses the Q-learning method to determine optimal transmission paths and minimize total energy consumption of the network. Simulation experiments were conducted using the NS-3 network simulation environment. The obtained results demonstrate that the proposed approach reduces energy consumption, increases network lifetime, and improves data transmission reliability in comparison with classical routing protocols such as LEACH and PEGASIS. The results confirm the effectiveness of reinforcement learning methods for adaptive routing in dynamic IoT environments.