Online Adversarial Stabilization of Unknown Networked Systems-Reference-Cited by-同舟云学术

Online Adversarial Stabilization of Unknown Networked Systems

Published:2023-02-27 Issue:1 Volume:7 Page:1-43
ISSN:2476-1249
Container-title:Proceedings of the ACM on Measurement and Analysis of Computing Systems
language:en
Short-container-title:Proc. ACM Meas. Anal. Comput. Syst.

Author:

Yu Jing¹^ORCID,Ho Dimitar¹^ORCID,Wierman Adam¹^ORCID

Affiliation:

1. California Institute of Technology, Pasadena, CA, USA

Abstract

We investigate the problem of stabilizing an unknown networked linear system under communication constraints and adversarial disturbances. We propose the first provably stabilizing algorithm for the problem. The algorithm uses a distributed version of nested convex body chasing to maintain a consistent estimate of the network dynamics and applies system level synthesis to determine a distributed controller based on this estimated model. Our approach avoids the need for system identification and accommodates a broad class of communication delay while being fully distributed and scaling favorably with the number of subsystems.

Funder

NSF

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Safety, Risk, Reliability and Quality,Computer Science (miscellaneous)

Link

https://dl.acm.org/doi/pdf/10.1145/3579452

Reference93 articles.

1. Yasin Abbasi-Yadkori and Csaba Szepesvári . 2011 . Regret bounds for the adaptive control of linear quadratic systems . In Proceedings of the 24th Annual Conference on Learning Theory. JMLR Workshop and Conference Proceedings, 1--26 . Yasin Abbasi-Yadkori and Csaba Szepesvári. 2011. Regret bounds for the adaptive control of linear quadratic systems. In Proceedings of the 24th Annual Conference on Learning Theory. JMLR Workshop and Conference Proceedings, 1--26.

2. Naman Agarwal , Brian Bullins , Elad Hazan , Sham Kakade , and Karan Singh . 2019 . Online control with adversarial disturbances . In International Conference on Machine Learning. PMLR, 111--119 . Naman Agarwal, Brian Bullins, Elad Hazan, Sham Kakade, and Karan Singh. 2019. Online control with adversarial disturbances. In International Conference on Machine Learning. PMLR, 111--119.

3. The size of the membership-set in a probabilistic framework

4. Distributed Q-Learning for Dynamically Decoupled Systems

5. Siavash Alemzadeh , Shahriar Talebi , and Mehran Mesbahi . 2021. D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems. arXiv preprint arXiv:2103.11572 ( 2021 ). Siavash Alemzadeh, Shahriar Talebi, and Mehran Mesbahi. 2021. D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems. arXiv preprint arXiv:2103.11572 (2021).

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Online Adversarial Stabilization of Unknown Linear Time-Varying Systems;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13

2. Online Adversarial Stabilization of Unknown Networked Systems;ACM SIGMETRICS Performance Evaluation Review;2023-06-26

3. Online Adversarial Stabilization of Unknown Networked Systems;Abstract Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems;2023-06-19