基于运行成本约束的含碳捕集设备电力系统低碳调度模型
A low-carbon dispatch model for power system with carbon capture equipment based on operating cost constraint
陈郑平 1韩晔 1孙蕾 2李文忠 1王芳东 1崔晨 3张兆功4
作者信息
- 1. 国网福建省电力有限公司电力调度控制中心,福州 350003
- 2. 北京科东电力控制系统有限责任公司调度自动化分公司,北京 100085
- 3. 黑龙江大学数据科学与技术学院,哈尔滨 150080
- 4. 黑龙江大学计算机科学与技术学院,哈尔滨 150080
- 折叠
摘要
发展低碳电力系统是应对全球变暖挑战的基础,如何充分发挥碳捕集设备的作用,且有效地解决含碳捕集设备电力系统的调度问题变得至关重要.针对含碳捕集设备场景下的低碳调度问题,首先建立风电、储能、火电机组的联合调度模型,根据此模型以系统运行成本为优化目标,可以得到不含碳捕集设备场景下的系统最优成本.在此基础上,建立风电、储能、碳捕集以及火电机组的低碳优化调度模型,将无碳捕集设备场景下的系统最优成本作为约束条件之一,以二氧化碳排放量减少为调度优化目标.由于该场景下的低碳调度问题可以视为一个马尔可夫决策过程,最后基于深度强化学习模型对问题进行求解.实验结果表明,所提出的含碳捕集设备场景下的低碳调度模型,不但可以有效地控制系统总运行成本,同时可以进一步降低二氧化碳的排放量.
Abstract
The development of low-carbon power system is the basis for coping with the challenge of global warming.It is very important to give full play to the role of carbon capture equipment and effectively solve the low-carbon dispatch problem of the power system containing carbon capture equipment.For the low-carbon dispatch problem in the power system with carbon capture equipment,a joint dispatch model for wind power,energy storage,and thermal power units,which may minimize the operating costs of system,is proposed.Then a low-carbon optimal dispatch model for wind power,energy storage,carbon capture,and thermal power units is established.In this model,the optimal operating costs of the power system withnot carbon capture equipment is considered as one of the constraints,and the optimization goal is to minimize the carbon emissions of the power system.Due to the fact that the low-carbon dispatch problem can be defined as a Markov decision process,deep reinforcement learning model is employed to solve the optimal dispatch problem.The experimental results indicate that the proposed low-carbon scheduling model can effectively reduce operating costs and carbon emissions.
关键词
碳捕集/低碳调度/马尔可夫决策过程/深度强化学习Key words
carbon capture/low-carbon scheduling/Markov decision process/deep reinforcement learning引用本文复制引用
基金项目
国家自然科学基金资助项目(62071151)
黑龙江省自然科学基金资助项目(LH2022F044)
国网福建省电力有限公司科技项目(52130022000P)
出版年
2024
NETL
NSTL
维普
万方数据