arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.01201math.OCcs.MAcs.SYeess.SY
收藏

多智能体系统分布式鲁棒优化及其有限时间收敛保证

Distributed robust optimization for multi-agent systems with guaranteed finite-time convergence

Xunhao Wu, Jun Fu

AI总结:

提出一种分布式算法,在有限时间内使多智能体系统收敛到满足全局最优精度要求的可行共识解,解决有界不确定性下的分布式鲁棒凸优化问题。

摘要:

针对在一致强连通网络下、受有界不确定性影响的分布式鲁棒凸优化问题(DRCO),提出了一种新颖的分布式算法,该算法能够在有限时间内收敛到一个可行的共识解,该解在特定精度内满足全局最优性。首先,开发了一种分布式下界计算过程,该过程基于将紧致不确定性集离散化为有限个点,从而对DRCO进行外部迭代逼近。其次,提出了一种分布式上界计算过程,该过程通过使用适当的正参数限制约束右端项,并在有限个点上强制执行紧致不确定性集,来迭代逼近DRCO。DRCO全局最优目标的下界和上界由这两个过程获得。第三,提出了两种分布式终止方法,通过探索上界与下界之间的间隙是否达到特定精度,使所有智能体同时停止更新。第四,证明了所有智能体在有限时间内收敛到一个在特定精度内满足全局最优性的可行共识解。最后,包含了一个数值案例研究,以说明该分布式算法的有效性。

英文摘要:

A novel distributed algorithm is proposed for finite-time converging to a feasible consensus solution satisfying global optimality to a certain accuracy of the distributed robust convex optimization problem (DRCO) subject to bounded uncertainty under a uniformly strongly connected network. Firstly, a distributed lower bounding procedure is developed, which is based on an outer iterative approximation of the DRCO through the discretization of the compact uncertainty set into a finite number of points. Secondly, a distributed upper bounding procedure is proposed, which is based on iteratively approximating the DRCO by restricting the constraints right-hand side with a proper positive parameter and enforcing the compact uncertainty set at finitely many points. The lower and upper bounds of the global optimal objective for the DRCO are obtained from these two procedures. Thirdly, two distributed termination methods are proposed to make all agents stop updating simultaneously by exploring whether the gap between the upper and the lower bounds reaches a certain accuracy. Fourthly, it is proved that all the agents finite-time converge to a feasible consensus solution that satisfies global optimality within a certain accuracy. Finally, a numerical case study is included to illustrate the effectiveness of the distributed algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑