Distributed Data-Driven Control of Network Systems

作     者：Celi, Federico Baggio, Giacomo Pasqualetti, Fabio 

作者机构：Univ Calif Riverside Dept Mech Engn Riverside CA 92521 USA Univ Padua Dept Informat Engn I-35131 Padua Italy 

出 版 物：《IEEE OPEN JOURNAL OF CONTROL SYSTEMS》 (IEEE. Open. J. Control. Syst.)

年 卷 期：2023年第2卷

页      面：93-107页

核心收录：

基　　金：AFOSR [FA9550-19-1-0235  AFOSR-FA9550-20-1-0140  ARO W911NF-20-2-0267] 

主　　题：Trajectory Network systems Control systems Robustness Optimal control Data models Minimization Distributed control and optimization learning for control network analysis and control optimal control 

摘      要：Imperfect models lead to imperfect controllers and deriving accurate models from first principles or system identification is especially challenging in networked systems. Instead, data can be used to directly compute controllers, without requiring any system identification or modeling. In this paper we propose a strategy to directly learn control actions when data from past system trajectories is distributed among multiple agents in a network. The approach we develop provably converges to a suboptimal solution in a finite number of steps, bounded by the diameter of the network, and with a sub-optimality gap that can be characterized as a function of data, and that can be made arbitrarily small. We further characterize the robustness properties of our approach and give provable guarantees on its performance when data are affected by noise or by a class of attacks.