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

Abstract

Network 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.

QoS-Aware Energy Management and Node Scheduling Schemes for Sensor Network-Based Surveillance Applications

“…The learning parameters such as the current residual energy, recharging frequency, and the solar radiations influence the node selection process. In the approach proposed in [155], a Q-learning strategy is applied to generate cover sets for dynamic sensor networks. Each sensor node in the generated cover set learns from the network and can adjust its communication range in order to conserve energy.…”

Self-Learning Power Control in Wireless Sensor Networks

“…Le et al [ 49 ] use Q-learning for topology control, applied to sensor nodes in order to keep the connectivity of the network with k -degree. The nodes exchange information regarding the transmission power used and communication range.…”

An Energy Efficient Reinforcement Learning Based Clustering Approach for Wireless Sensor Network

“…In D-LEACH, the energy of sensor nodes has been balanced by adjusting the threshold function, which is set according to the radius of nodes [11]. Usage of the Machine Learning (ML) approach has also been observed in the earlier research articles mentioned in several recent research articles [13,30,31]. Though the usage of ML is still there, this paper improves the ML-based Reinforcement Learning (RL) by using a feedback-based mechanism.…”

“…Reinforcement Learning (RL) is a subfield of machine learning and seeks to use computer programs to create rules from large data sets. Using the RL approach [30], the agent is selected based on the action/rule performed, and in return, a reward point is received from the outside environment. Based on the reward point, the rules are modified and can achieve optimal results.…”