Abstract

Consensus is one of the fundamental distributed control technologies for collaboration in multi-agent systems such as collaborative handling in intelligent manufacturing. In this paper, we study the problem of resilient average consensus for multi-agent systems with misbehaving nodes. To protect consensus value from being influenced by misbehaving nodes, we address this problem by detecting misbehaviors, mitigating the corresponding adverse impact, and achieving the resilient average consensus. General types of misbehaviors are considered, including attacks, accidental faults, and link failures. We characterize the adverse impact of misbehaving nodes in a distributed manner via two-hop communication information and develop a deterministic detection compensation based consensus (D-DCC) algorithm with a decaying fault-tolerant error bound. Considering scenarios wherein information sets are intermittently available due to link failures, a stochastic extension named stochastic detection compensation based consensus (S-DCC) algorithm is proposed. We prove that D-DCC and S-DCC allow nodes to asymptotically achieve resilient accurate average consensus and unbiased resilient average consensus in a statistical sense, respectively. Then, the Wasserstein distance is introduced to analyze the accuracy of S-DCC. Finally, extensive simulations are conducted to verify the effectiveness of the proposed algorithms.

中文翻译：

---

在多智能体系统中实现弹性平均共识：检测和补偿方法

摘要

共识是多智能体系统协作的基本分布式控制技术之一，例如智能制造中的协作处理。在本文中，我们研究了具有行为不当节点的多代理系统的弹性平均共识问题。为了保护共识价值免受不当行为节点的影响，我们通过检测不当行为、减轻相应的不利影响并实现弹性平均共识来解决这个问题。考虑一般类型的不当行为，包括攻击、意外故障和链路故障。我们通过两跳通信信息以分布式方式描述行为不当节点的不利影响，并开发了一种具有衰减容错错误界限的基于确定性检测补偿的共识（D-DCC）算法。考虑到由于链路故障而导致信息集间歇性可用的场景，提出了一种称为基于随机检测补偿的共识（S-DCC）算法的随机扩展。我们证明D-DCC和S-DCC分别允许节点在统计意义上渐进地实现弹性准确平均共识和无偏弹性平均共识。然后引入Wasserstein距离来分析S-DCC的准确性。最后，进行了大量的仿真来验证所提出算法的有效性。