Reinforcement learning based connectivity restoration in wireless sensor networks

Connectivity is a critical prerequisite for the effective operation of data gathering and forwarding procedures in Wireless Sensor Networks (WSNs). Failure of several sensor nodes in the network makes the base station incapable of receiving data from all the portions of the target area. Multiple partitions that are unable to communicate with one another are formed. Such networks are repaired using additional mobile relays. These relays cooperatively work together to create links among the partitions. In order to complete their task, they require a quick, communication-efficient, and machine learning-based approach. Reinforcement learning has evolved as a very efficient approach with long-term solutions in solving such problems. In this work, we propose a Reinforcement Learning-based Connectivity Restoration (RLCR) method that applies an intelligent machine learning algorithm for collaborative movement and connection establishment among partitions using relay nodes. It takes into account the actions of other agents and is capable of learning complicated multi-agent coordinating strategies. In a subsequent step, relay selection and connectivity maintenance have also been included. In RLCR, relays search for isolated partitions while maintaining communication with one another. Besides, we use Python to simulate the procedure and compare the results to various current methodologies. The experimental analysis illustrates that the proposed RLCR method performs better than the standard algorithms.