引用本文: | 卿竹雨,安锐,高红均,高艺文,王程,杨景茜,刘俊勇.考虑分散式资源互动响应的虚拟电厂智能化调峰定价[J].电力自动化设备,2023,43(5): |
| QING Zhuyu,AN Rui,GAO Hongjun,GAO Yiwen,WANG Cheng,YANG Jingxi,LIU Junyong.Intelligent peak regulation pricing for virtual power plant considering interactive response of distributed resources[J].Electric Power Automation Equipment,2023,43(5): |
|
摘要: |
随着新型电力系统的提出,电网灵活性需求不断提高,传统电力调峰压力增大,而目前调峰服务逐渐市场化,虚拟电厂等概念的发展使各类分散式资源参与电网调峰成为研究热点。基于此,提出考虑分散式资源互动响应的虚拟电厂智能化调峰定价策略。基于虚拟电厂技术特性与调峰市场要求构建虚拟电厂与内部资源互动的框架,分析响应补偿机制;利用大量历史用电信息建立基于循环神经网络的资源响应行为预测模型,并以虚拟电厂运营收益最大化和调峰偏差量最小化为目标制定响应价格;采用强化学习智能化方法对调峰环境进行学习感知,并针对价格策略改进更新此方法;利用MATLAB进行仿真分析和方法对比,仿真结果验证了所提模型的有效性。 |
关键词: 虚拟电厂 调峰 互动响应 价格制定 强化学习 |
DOI:10.16081/j.epae.202301007 |
分类号:TM73;F123.9 |
基金项目:国家自然科学基金资助项目(52077146);新能源电力系统国家重点实验室开放课题资助项目(LAPS210005) |
|
Intelligent peak regulation pricing for virtual power plant considering interactive response of distributed resources |
QING Zhuyu1, AN Rui1, GAO Hongjun1, GAO Yiwen2, WANG Cheng3, YANG Jingxi1, LIU Junyong1
|
1.College of Electrical Engineering, Sichuan University, Chengdu 610065, China;2.Electric Power Research Institute, State Grid Sichuan Electric Power Company, Chengdu 610041, China;3.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
|
Abstract: |
With the proposal of new power system, the demand for flexibility of power grid keeps improving and the pressure on traditional power peak regulation increases. Meanwhile, the gradual marketization of peak regulation service and the development of concepts such as virtual power plant etc. make a research focus for the participation of various distributed resources in peak regulation. In this context, the intelligent peak regulation pricing strategy for virtual power plant considering the interactive response of distributed resources is proposed. The interaction framework between virtual power plant and internal resources is constructed based on the technical characteristics of virtual power plant and the requirements of peak regulation market, and the response compensation mechanism is analyzed. The prediction model of resource response behavior is established based on recurrent neural network utilizing a large amount of historical electricity consumption information, and the response price is set with the objectives of maximizing the operating revenue of virtual power plant and minimizing the deviation of peak regulation. Then, the reinforcement learning intelligent method is used to learn and sense the peak regulation environment, and the method is improved and updated according to the price strategy. Finally, MATLAB is applied for simulation analysis and method comparison, and the effectiveness of the proposed model is verified by the simulative results. |
Key words: virtual power plants peak regulation interactive response price setting reinforcement learning |