Backpressure-based Mean-field Type Game for Scheduling in Multi-Hop Wireless Sensor Networks
Salah Eddine Choutri, Boualem Djehiche, Prajwal Chauhan, Saif Eddin Jabari
TL;DR
The paper tackles scalable scheduling in large-scale, multi-hop wireless sensor networks by extending backpressure with a mean-field term, formulating a non-cooperative Mean-Field Type Game (MFTG) that captures global congestion effects while preserving local queue dynamics. It derives a mean-field approximation of the queue evolution via exchangeability and the law of large numbers, yielding a limiting stochastic differential equation that reduces pairwise interactions to a tractable global term. Key contributions include (i) a novel MFTG model for decentralized transmission scheduling, (ii) a heuristic derivation of mean-field queue dynamics with justification under weak interactions, and (iii) numerical simulations on very large networks demonstrating congestion balancing and queue stabilization. The approach offers scalable, decentralized control for dense WSN deployments and lays groundwork for benchmarking against classical backpressure and interference-aware alternatives. Future work will explore heterogeneous topologies, adaptive learning, and interference constraints within the mean-field regime.
Abstract
We propose a Mean-Field Type Game (MFTG) framework for effective scheduling in multi-hop wireless sensor networks (WSNs) using backpressure as a performance criterion. Traditional backpressure algorithms leverage queue differentials to regulate data flow and maintain network stability. In this work, we extend the backpressure framework by incorporating a mean-field term into the cost functional, capturing the global behavior of the system alongside local dynamics. The resulting model utilizes the strengths of non-cooperative mean-field type games, enabling nodes to make decentralized decisions based on both individual queue states and system mean-field effects while accounting for stochastic network interactions. By leveraging the interplay between backpressure dynamics and mean-field coupling, the approach balances local optimization with global efficiency. Numerical simulations demonstrate the efficacy of the proposed method in handling congestion and scheduling in large-scale WSNs.