Energy-Efficient Routing Algorithm for Wireless Sensor Networks: A Multi-Agent Reinforcement Learning Approach

Efficient energy management is essential in Wireless Sensor Networks (WSNs) to extend network lifetime and ensure reliable data transmission. This paper presents a novel method using reinforcement learning-based cluster-head selection and a hybrid multi-hop routing algorithm, which leverages Q-learning within a multi-agent system to dynamically adapt transmission paths based on the energy distribution across sensor nodes. Each sensor node is modeled as an autonomous agent that observes local state parameters, such as residual energy, distance to sink, hop count, and hotspot proximity, and selects routing actions that maximize long-term energy efficiency. After computing the optimal paths, each sensor aggregates sensed data and forwards it through intermediate nodes to a selected transmitter node, chosen based on the highest remaining State of Charge (SoC), thereby avoiding premature node depletion. To promote efficient learning, a carefully designed reward function incentivizes balanced load distribution, hotspot avoidance, and energy-aware forwarding while maintaining signal quality. The learning process occurs either in a decentralized manner or via a cloud-based controller that offloads computation in large-scale deployments. Moreover, the RL-driven routing decisions are fused with classical graph-based methods, Minimum Energy Routing Algorithm (MERA) and Minimum Spanning Tree (MST), to optimize energy consumption and load balancing. Simulations confirm that the proposed approach significantly improves node survival rate, reduces SoC variance, and enhances network resilience, making it a scalable and adaptive solution for energy-constrained WSNs in dynamic sensor deployments and IoT applications.