An adaptive online learning algorithm for distributed convex optimization with coupled constraints over unbalanced directed graphs

This paper investigates a distributed optimization problem over multi-agent networks subject to both local and coupled constraints in a non-stationary environment, where a set of agents aim to cooperatively minimize the sum of locally time-varying cost functions when the communication graphs are tim...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of the Franklin Institute Ročník 356; číslo 13; s. 7548 - 7570
Hlavní autori: Gu, Chuanye, Li, Jueyou, Wu, Zhiyou
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elmsford Elsevier Ltd 01.09.2019
Elsevier Science Ltd
Predmet:
Adaptive algorithms
Algorithms
Computational geometry
Computer simulation
Convexity
Coupling
Electric vehicle charging
Electric vehicles
Graph theory
Graphs
Machine learning
Multiagent systems
Nonstationary environments
Optimization
Studies
ISSN:0016-0032, 1879-2693, 0016-0032
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper investigates a distributed optimization problem over multi-agent networks subject to both local and coupled constraints in a non-stationary environment, where a set of agents aim to cooperatively minimize the sum of locally time-varying cost functions when the communication graphs are time-changing connected and unbalanced. Based on dual decomposition, we propose a distributed online dual push-sum learning algorithm by incorporating the push-sum protocol into dual gradient method. We then show that the regret bound has a sublinear growth of O(Tp) and the constraint violation is also sublinear with order of O(T1−p/2), where T is the time horizon and 0 < p ≤ 1/2. Finally, simulation experiments on a plug-in electric vehicle charging problem are utilized to verify the performance of the proposed algorithm. The proposed algorithm is adaptive without knowing the total number of iterations T in advance. The convergence results are established on more general unbalanced graphs without the boundedness assumption on dual variables. In addition, more privacy concerns are guaranteed since only dual variables related with coupled constraints are exchanged among agents.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0016-0032
1879-2693
0016-0032
DOI:10.1016/j.jfranklin.2019.06.026