具有通信时延和有向网络的多智能体分布式优化  

Distributed optimization of multi-agent with communication delay and directed network

作　　者：杨正全[1,2] 潘小芳 张青[2] 陈增强 YANG Zheng-quan;PAN Xiao-fang;ZHANG Qing;CHEN Zeng-qiang(Airport Comprehensive Transportation Research Institute,Civil Aviation University of China,Tianjin 300300,China;College of Science,Civil Aviation University of China,Tianjin 300300,China;College of Artificial Intelligence,Nankai University of China,Tianjin 300350,China)

机构地区：[1]中国民航大学机场综合交通研究院,天津300300 [2]中国民航大学理学院,天津300300 [3]南开大学人工智能学院,天津300350

出　　处：《控制理论与应用》2021年第9期1414-1420,共7页Control Theory & Applications

基　　金：Supported by the National Natural Science Foundation of China(51778615);the Fund of the Airport Comprehensive Transportation Research Institute(Think Tank)and the Civil Aviation University of China(20JCZHJT-4).

摘　　要：本文对非平衡有向拓扑下一阶多智能体系统的分布式优化问题进行研究.研究的智能体在与邻居的通信过程中都有一个变化的时延.本文的目标是找到使得目标函数f(x)=Σ_(i=1 )/Nfi(xi)最小的智能体的状态.提出了一种基于有向图的拉普拉斯矩阵的零特征值对应的左特征向量和智能体的局部信息的控制器.在这项研究中,去掉了fi(xi)的梯度有界要求,并且不要求网络平衡.在某些假设下,所有智能体都达到相同的状态,同时最小化目标函数Σ_(i=1 )/N fi(xi).最后,通过数值模拟验证了本文的研究结果.This paper studies the distributed optimization problem for the first-order multi-agent systems in unbalanced directed topology.Each agent has a time delay in the communication process with its neighbors.Our goal is to find a state of the agent that minimizes the objective function f(x)=Σ_(i=1 )/Nfi(xi).A controller based on the left eigenvector corresponding to the zero eigenvalue of L of the graph G and the local information of each agent is proposed.In this study,the bounded requirement of the gradient of fi(xi)is removed,and it does not require the network to be balanced.Under some assumptions,all agents reach the same state while minimizing the objective function Σ_(i=1 )/Nfi(xi).Finally,a numerical simulation illustrates the results of this article.

关 键 词：通信时延 多智能体系统 分布式优化 非平衡有向网络 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]