DeepMPR: Enhancing Opportunistic Routing in Wireless Networks through Multi-Agent Deep Reinforcement Learning
This addresses the challenge of reducing network overhead and computational demands in dynamic wireless environments like MANETs/VANETs, representing an incremental improvement over existing heuristic methods.
The paper tackles the problem of selecting multi-point relaying (MPR) sets for efficient multicast routing in wireless networks by proposing DeepMPR, a multi-agent deep reinforcement learning approach that outperforms the OLSR MPR algorithm without requiring neighbor announcement messages.
Opportunistic routing relies on the broadcast capability of wireless networks. It brings higher reliability and robustness in highly dynamic and/or severe environments such as mobile or vehicular ad-hoc networks (MANETs/VANETs). To reduce the cost of broadcast, multicast routing schemes use the connected dominating set (CDS) or multi-point relaying (MPR) set to decrease the network overhead and hence, their selection algorithms are critical. Common MPR selection algorithms are heuristic, rely on coordination between nodes, need high computational power for large networks, and are difficult to tune for network uncertainties. In this paper, we use multi-agent deep reinforcement learning to design a novel MPR multicast routing technique, DeepMPR, which is outperforming the OLSR MPR selection algorithm while it does not require MPR announcement messages from the neighbors. Our evaluation results demonstrate the performance gains of our trained DeepMPR multicast forwarding policy compared to other popular techniques.