A distributed coverage hole recovery approach based on reinforcement learning for Wireless Sensor Networks

摘要

In Wireless Sensor Networks (WSNs), various anomalies may arise and reduce their reliability and efficiency. For example, Coverage Hole can occur in such networks due to several causes, such as damaging events, sensors battery exhaustion, hardware failure, and software bugs. Modern trends to use relocation of deployed sensor nodes when the manual addition of nodes is neither doable nor economical in many applications have attracted attention. The lack of central supervision and control in harsh and hostile environments have encouraged researchers to shift from centralized to distributed node relocation schemes. In this paper, a new game theory approach based on reinforcement learning to recover Coverage Holes in a distributed way is proposed. For the formulated potential game, sensor nodes can recover Coverage Holes using only local acquaintances. To reduce the coverage gaps, the combined action of node reposition and sensing range adjustment is chosen by each sensor node. The simulation results prove that, unlike previous methods, the proposed approach can sustain a network overall coverage in the presence of random damage events. (C) 2020 Elsevier B.V. All rights reserved.