Shah, Margi  ORCID: https://orcid.org/0000-0003-2222-8412, Zhou, Yue ORCID: https://orcid.org/0000-0002-6698-4714, Wu, Jianzhong ORCID: https://orcid.org/0000-0001-7928-3602 and Mowbray, Max
2025.
Deep reinforcement learning for demand response of a steel plant in energy and spinning reserve markets.
Presented at: 2025 IEEE Power & Energy Society General Meeting (PESGM),
Austin, TX, USA,
27-31 July 2025.
2025 IEEE Power & Energy Society General Meeting (PESGM).
IEEE,
10.1109/pesgm52009.2025.11225478
|
Preview |
PDF
- Accepted Post-Print Version
Download (763kB) | Preview |
Abstract
Industrial demand response has potential to enhance power systems’ operational flexibility amid the operational challenges posed by massive proliferation of distributed energy resources. As an energy intensive industry, steel manufacturing has the potential to participate in demand response via responding to time-varying electricity price and providing spinning reserve service at the same time, leading to reduced electricity costs while supporting the power systems. However, this potential is hindered due to the complex and intertwined processes involved in steelmaking and the uncertainties of electricity prices and onsite renewable power generation. In this paper, we present a novel deep reinforcement learning based demand response scheme to address these challenges, which optimizes the schedules of steelmaking processes for maximizing the benefits in both the energy and spinning reserve markets.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Engineering |
| Publisher: | IEEE |
| ISSN: | 1944-9933 |
| Date of First Compliant Deposit: | 22 December 2025 |
| Date of Acceptance: | 13 February 2025 |
| Last Modified: | 22 Dec 2025 11:30 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/182622 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions