Maximizing Throughput of Decentralized Wireless Sensor Network Using Reinforcement Learning

Abstract

A reinforcement learning algorithm with the aim to increase the throughput of a Wireless Sensor Network (WSN) and decrease latency in a decentralized manner. WSNs are collections of sensor nodes that gather environmental data, where the main challenges are the limited power supply of nodes and the need for decentralized control. A distributed resource allocation algorithm for cellular MIMO networks by adopting a Reinforcement Learning (RL) approach. We use RL methods which employ Growing Self Organizing Maps to deal with the huge and continuous problem space. The goal of the algorithm is to maximize the network throughput in a fair manner. Indeed, the algorithm maximizes the throughput until fairness violation does not exceed an adjustable threshold.