A Low-Carbon Economic Dispatch Method for Power Systems With Carbon Capture Plants Based on Safe Reinforcement Learning
- 13 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (8) , 10542-10553
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (51977046)
This publication has 31 references indexed in Scilit:
- A phenazine-based high-capacity and high-stability electrochemical CO2 capture cell with coupled electricity storageNature Energy, 2023
- Action decoupled SAC reinforcement learning with discrete-continuous hybrid action spacesNeurocomputing, 2023
- Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments From Temporal Logic SpecificationsIEEE Robotics and Automation Letters, 2023
- A novel two-stage energy management of hybrid AC/DC microgrid considering frequency security constraintsInternational Journal of Electrical Power & Energy Systems, 2022
- A Tri-dimensional Equilibrium-based stochastic optimal dispatching model for a novel virtual power plant incorporating carbon Capture, Power-to-Gas and electric vehicle aggregatorApplied Energy, 2022
- Economic-Emission Dispatch Problem in Power Systems With Carbon Capture Power PlantsIEEE Transactions on Industry Applications, 2021
- Life-cycle assessment of an industrial direct air capture process based on temperature–vacuum swing adsorptionNature Energy, 2021
- A two-stage stochastic p-robust optimal energy trading management in microgrid operation considering uncertainty with hybrid demand responseInternational Journal of Electrical Power & Energy Systems, 2021
- Distributed Deep Reinforcement Learning for Intelligent Load Scheduling in Residential Smart GridsIEEE Transactions on Industrial Informatics, 2020
- Low-carbon economic dispatch for electricity and natural gas systems considering carbon capture systems and power-to-gasApplied Energy, 2018