Accelerating Distributed Average Consensus in Wireless Sensor Networks via GNN-Based Broadcast Probability Optimization
- 22 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 9, 2247-2252
Abstract
Achieving efficient distributed average consensus is crucial for collaborative applications in wireless sensor networks (WSNs). Traditional gossip-based methods encounter difficulties in balancing communication efficiency and consensus rate, especially in dynamic and resource-constrained wireless environments. To overcome these challenges, a graph neural network (GNN), specifically the message passing neural network (MPNN) framework, is proposed to optimize node broadcast probabilities for the probabilistic broadcast gossip scheme. By employing MPNN with attention mechanisms, the proposed method dynamically allocates broadcast probabilities based on both local node characteristics and global network topologies. Extensive simulations reveal that the proposed method significantly surpasses heuristic and optimization-based baselines, achieving a substantial reduction in communication costs. These results highlight the potential of GNNs in advancing distributed consensus protocols for WSNs.Keywords
Funding Information
- National Natural Science Foundation of China (62101141, 62102096)
- Guangdong Basic and Applied Basic Research Foundation (2024A1515011823)
- Guangzhou Basic and Applied Basic Research Foundation (2024A04J4297, 2024A04J4298)
This publication has 17 references indexed in Scilit:
- Rethinking Distributed Average Consensus for Wireless Networks: A Low-Cost Approach to Broadcast Probability OptimizationIEEE Internet of Things Journal, 2024
- Logarithmically Quantized Distributed Optimization Over Dynamic Multi-Agent NetworksIEEE Control Systems Letters, 2024
- A Fully Distributed LTI Estimation Scheme Over Directed Graph TopologiesIEEE Control Systems Letters, 2024
- On the Convergence of Decentralized Federated Learning Under Imperfect Information SharingIEEE Control Systems Letters, 2023
- Distributed Consensus in Wireless Networks With Probabilistic Broadcast SchedulingIEEE Signal Processing Letters, 2023
- Privacy-Preserving Average Consensus Via Edge DecompositionIEEE Control Systems Letters, 2022
- Average-Consensus Tracking of Sensor Network via Distributed Coordination Control of Heterogeneous Multi-Agent SystemsIEEE Control Systems Letters, 2018
- Interior Point Methods for Nonlinear Optimization2010
- Fast linear iterations for distributed averagingSystems & Control Letters, 2004
- Universal approximation bounds for superpositions of a sigmoidal functionIEEE Transactions on Information Theory, 1993