Cooperative Communications with Relay Selection for QoS Provisioning in Wireless Sensor Networks

Cooperative communications have been demonstrated to be effective in combating the multiple fading effects in wireless networks, and improving the network performance in terms of adaptivity, reliability and network throughput. In this paper, we investigate the use of cooperative communications with adaptive relay selection for resource-constrained wireless sensor networks, and propose QoS-RSCC, a QoS-support multi-agent reinforcement learning based relay selection scheme for cooperative communications. In QoS-RSCC, optimal relays, in terms of outage probability and channel efficiency, are selected distributedly from multiple relaying candidates for the intermediate routers along the multi-hop route, without the needs of prior knowledge of the wireless network model and centralized control. We compare the network performance of QoS-RSCC with CRP [1], and investigate the impacts of network traffic load, channel bit error rate, and node's mobility on the network performance. Simulation results show that QoS-RSCC can achieve a near-optimal performance on both diversity gains and channel efficiency, and fits well in dynamic environments.