Abstract
Consensus in ad hoc networks is fundamental for coordinating tasks such as cooperative sensing, learning, and data fusion. Till now, designing algorithm to tackle consensus problem primarily faces two critical challenges: The first is the imperfection of communication links between nodes, and the second is the unavailability of central node collecting network information. To address these challenges, this paper investigates the consensus problem under unreliable communications and develops a distributed weight matrix optimization approach to improve consensus performance. Specifically, we quantitatively analyze the impact of mixing weights on consensus error over unreliable communications. Guided by this analysis, we formulate a stochastic eigenvalue optimization problem to optimize the weight matrix for maximizing consensus performance. Typically, solving such problem in a distributed manner is impractical. However, by leveraging the inherent structure of the problem, a novel distributed projected subgradient-based algorithm is developed to obtain the optimal weight matrix. Simulation results validate the effectiveness of the proposed approach under different network configurations. The proposed method also shows robust performance when benchmarked against existing schemes, making it well-suited for deployment in large-scale distributed networks.
Funding Information
  • Sichuan Science and Technology Program (2024ZYD0036)
  • National Key Laboratory of Wireless Communications Foundation

This publication has 40 references indexed in Scilit: