Multi-Armed Bandits Learning for Optimal Decentralized Control of Electric Vehicle Charging

被引：0

作者：

Zafar, Sharyal ^{[1
]}

Feraud, Raphael ^{[2
]}

Blavette, Anne ^{[3
]}

Camilleri, Guy ^{[4
]}

Ben Ahmed, Hamid ^{[1
]}

机构：

[1] Ecole Normale Super Rennes, SATIE Lab, Bruz, France

[2] Orange Labs, Orange, Lannion, France

[3] Ecole Normale Super Rennes, CNRS, SATIE Lab, Bruz, France

[4] Paul Sabatier Univ, IRIT Lab, Toulouse, France

来源：

2023 IEEE BELGRADE POWERTECH | 2023年

关键词：

Electric vehicles; Active distribution networks; Smart charging; Multi-agent reinforcement learning; Combinatorial multi-armed bandits;

D O I：

10.1109/POWERTECH55446.2023.10202971

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Optimal control of new grid elements, such as electric vehicles, can ensure an efficient, and stable operation of distribution networks. Decentralization can result in scalability, higher reliability, and privacy (which may not be present in centralized or hierarchical control solutions). A decentralized multi-agent multi-armed combinatorial bandits system using Thompson Sampling is presented for smart charging of electric vehicles. The proposed system utilizes the concepts of bandits reinforcement learning to manage the uncertainties in the choice of other players' actions, and in the intermittent photovoltaic energy production. This proposed solution is fully decentralized, real-time, scalable, model-free, and fair. Its performance is evaluated through comparison with other charging strategies i.e., basic charging, and centralized optimization.

引用

页数：6

共 50 条

[41] MULTI-ARMED BANDITS AND THE GITTINS INDEX
WHITTLE, P
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1980, 42 (02): : 143 - 149
[42] Multi-armed bandits with episode context
Christopher D. Rosin
[J]. Annals of Mathematics and Artificial Intelligence, 2011, 61 : 203 - 230
[43] Multi-armed bandits with switching penalties
Asawa, M
Teneketzis, D
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1996, 41 (03) : 328 - 348
[44] Secure Outsourcing of Multi-Armed Bandits
Ciucanu, Radu
Lafourcade, Pascal
Lombard-Platet, Marius
Soare, Marta
[J]. 2020 IEEE 19TH INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS (TRUSTCOM 2020), 2020, : 202 - 209
[45] Are Multi-Armed Bandits Susceptible to Peeking?
Loecher, Markus
[J]. ZAGREB INTERNATIONAL REVIEW OF ECONOMICS & BUSINESS, 2018, 21 (01): : 95 - 104
[46] PAC-Bayesian lifelong learning for multi-armed bandits
Flynn, Hamish
Reeb, David
Kandemir, Melih
Peters, Jan
[J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2022, 36 (02) : 841 - 876
[47] Multi-Armed Bandits with Cost Subsidy
Sinha, Deeksha
Sankararama, Karthik Abinav
Kazerouni, Abbas
Avadhanula, Vashist
[J]. 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
[48] Batched Multi-armed Bandits Problem
Gao, Zijun
Han, Yanjun
Ren, Zhimei
Zhou, Zhengqing
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[49] Multi-Armed Bandits With Correlated Arms
Gupta, Samarth
Chaudhari, Shreyas
Joshi, Gauri
Yagan, Osman
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (10) : 6711 - 6732
[50] Learning Variable Ordering Heuristics with Multi-Armed Bandits and Restarts
Wattez, Hugues
Koriche, Frederic
Lecoutre, Christophe
Paparrizou, Anastasia
Tabary, Sebastien
[J]. ECAI 2020: 24TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, 325 : 371 - 378

← 1 2 3 4 5 →