An Energy-Efficient Topology Control Algorithm Based on Reinforcement Learning for Wireless Sensor Networks

Abstract

International Journal of Control and AutomationVol. 10, No. 5 (2017), pp.233-244http//dx.doi.org/10.14257/ijca.2017.10.5.22ISSN: 2005-4297IJCACopyright ©2017SERSCAn Energy-Efficient Topology Control Algorithm Based on Reinforcement Learning for Wireless Sensor NetworksThien T. T. Le and Sangman MohDept. of Computer Engineering, Chosun University, Gwangju, South Koreathanhthien92003@yahoo.com, smmoh@chosun.comAbstractNetwork connectivity is a key issue in wireless sensor networks (WSNs). Nodes have to establish and maintain a connected topology in a WSN while dealing with interference and packet loss. Topology control techniques allow the network nodes to reduce their transmission power while preserving the network connectivity. In this paper, we present a reinforcement-learning-based communication range control (RL-CRC) algorithm to adaptively adjust the communication range at each sensor node while ensuring the network connectivity in dynamic WSNs. In the proposed RL-CRC, the reinforcement learning is exploited to discover neighbors with low interference, and the network topology is effectively obtained in presence of interference. The reinforcement learning based on the so-called Q-learning adapts to changes of node connectivity and, thus, the nodes discover their neighbors and then adaptively control their communication range accordingly. The simulation results show that RL-CRC reduces energy consumption significantly compared to the conventional schemes while maintaining almost the same average communication range and node degree.