A Low-Carbon Economic Dispatch Method for Power Systems With Carbon Capture Plants Based on Safe Reinforcement Learning

To address the high-dimensional and complex scheduling issues in the low-carbon economic dispatch (LCED) with carbon capture plants, in this article, we propose a novel safe reinforcement learning (SRL) based on heterogeneous action space representation, which can make fast decisions for both optima...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2024-08, Vol.20 (8), p.10542-10553
Main Authors: Wang, Qian, Zhang, Xueguang, Xu, Ying, Yi, Zhongkai, Xu, Dianguo
Format: Article
Language:English
Subjects:
Biological system modeling
Carbon
Carbon capture and storage
Carbon capture plant (CCP)
Carbon content
Carbon sequestration
Cloning
Continuity (mathematics)
discrete–continuous actions
Dispatching
low-carbon economic dispatch (LCED)
Markov processes
Optimization
Power dispatch
Power flow
Power systems
Regularization
Renewable energy sources
safe reinforcement learning (SRL)
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address the high-dimensional and complex scheduling issues in the low-carbon economic dispatch (LCED) with carbon capture plants, in this article, we propose a novel safe reinforcement learning (SRL) based on heterogeneous action space representation, which can make fast decisions for both optimal power flow and carbon capture operation. First, SRL is designed based on the feasible set to ensure that the dispatch results continuously remain within the preset range. Then, to tackle the problem of having a large number of discrete and continuous variables in the LCED, this article employs a parameterized Markov process to represent these discrete-continuous actions and uses a conditional variational autoencoder to depict heterogeneous space. To learn the correlation between discrete and continuous action spaces, a mechanism for approximating action space based on small-sample behavior cloning is proposed, and a method based on dynamic time warping for calculating environment similarity is designed for determining the value of the regularization term. Finally, numerical simulations validate the superiority and scalability of the proposed method in enhancing decision-making efficiency and promoting the low-carbon economic operation of the power system.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2024.3396355