Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Coordination of Electric Vehicle Charging Through Multiagent Reinforcement Learning

Full text
Author(s):
Da Silva, Felipe Leno [1] ; Nishida, Cyntia E. H. [1] ; Roijers, Diederik M. [2, 3] ; Costa, Anna H. Reali [1]
Total Authors: 4
Affiliation:
[1] Univ Sao Paulo, Intelligent Tech Lab, Sao Paulo 05508010 - Brazil
[2] HU Univ Appl Sci Utrecht, Inst ICT, Utrecht 3584 - Netherlands
[3] Vrije Univ Brussel, AI Lab, Brussels - Belgium
Total Affiliations: 3
Document type: Journal article
Source: IEEE TRANSACTIONS ON SMART GRID; v. 11, n. 3, p. 2347-2356, MAY 2020.
Web of Science Citations: 0
Abstract

The number of Electric Vehicle (EV) owners is expected to significantly increase in the near future, since EVs are regarded as valuable assets both for transportation and energy storage purposes. However, recharging a large fleet of EVs during peak hours may overload transformers in the distribution grid. Although several methods have been proposed to flatten peak-hour loads and recharge EVs as fairly as possible in the available time, these typically focus either on a single type of tariff or on making strong assumptions regarding the distribution grid. In this article, we propose the MultiAgent Selfish-COllaborative architecture (MASCO), a Multiagent Multiobjective Reinforcement Learning architecture that aims at simultaneously minimizing energy costs and avoiding transformer overloads, while allowing EV recharging. MASCO makes minimal assumptions regarding the distribution grid, works under any type of tariff, and can be configured to follow consumer preferences. We perform experiments with real energy prices, and empirically show that MASCO succeeds in balancing energy costs and transformer load. (AU)

FAPESP's process: 15/16310-4 - Transfer Learning in Reinforcement Learning Multi-Agent Systems
Grantee:Felipe Leno da Silva
Support Opportunities: Scholarships in Brazil - Doctorate
FAPESP's process: 18/00344-5 - Reusing previous task solutions in multiagent reinforcement learning
Grantee:Felipe Leno da Silva
Support Opportunities: Scholarships abroad - Research Internship - Doctorate