Options
A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn
Date Issued
2020-11-17
Date Available
2021-01-19T11:35:54Z
Abstract
Reinforcement learning is a promising model-free and adaptive controller for demand side management, as part of the future smart grid, at the district level. This paper presents the results of the algorithm that was submitted for the CityLearn Challenge, which was hosted in early 2020 with the aim of designing and tuning a reinforcement learning agent to flatten and smooth the aggregated curve of electrical demand of a district of diverse buildings. The proposed solution secured second place in the challenge using a centralised 'Soft Actor Critic' deep reinforcement learning agent that was able to handle continuous action spaces. The controller was able to achieve an averaged score of 0.967 on the challenge dataset comprising of different buildings and climates. This highlights the potential application of deep reinforcement learning as a plug-and-play style controller, that is capable of handling different climates and a heterogenous building stock, for district demand side management of buildings.
Sponsorship
Science Foundation Ireland
Other Sponsorship
ESIPP UCD
Type of Material
Conference Publication
Publisher
ACM
Copyright (Published Version)
2020 the Authors
Language
English
Status of Item
Peer reviewed
Conference Details
The 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities (RLEM 2020), New York, United States of America, 17 November 2020
This item is made available under a Creative Commons License
File(s)
Owning collection
Scopus© citations
12
Acquisition Date
Apr 16, 2024
Apr 16, 2024
Views
619
Last Month
2
2
Acquisition Date
Apr 16, 2024
Apr 16, 2024
Downloads
270
Last Week
2
2
Last Month
5
5
Acquisition Date
Apr 16, 2024
Apr 16, 2024