发电技术 ›› 2023, Vol. 44 ›› Issue (6): 790-799.DOI: 10.12096/j.2096-4528.pgt.23094

• 虚拟电厂规划、调度与控制技术 • 上一篇    下一篇

气候变化条件下基于智能预测模型的虚拟电厂不确定性运行优化研究

贾晓强1, 杨永标2, 杜姣2, 甘海庆3, 杨楠4   

  1. 1.电网安全全国重点实验室(中国电力科学研究院有限公司), 北京市 海淀区 100192
    2.东南大学电气工程学院, 江苏省 南京市 210096
    3.国网江苏省电力有限公司, 江苏省 南京市 210000
    4.国网江苏省电力有限公司南京供电分公司, 江苏省 南京市 210000
  • 收稿日期:2023-08-03 出版日期:2023-12-31 发布日期:2023-12-28
  • 作者简介:贾晓强(1995),男,硕士,工程师,主要从事能效分析、综合能源规划运行、运维和平台建设等方面研究工作,xqjia001@163.com
    杨永标(1978),男,硕士,研究员级高级工程师,主要从事综合能源规划运行、电网需求响应、智能配用电及微电网、配电自动化等方面研究工作,103200017@seu.edu.cn
    杜姣(1985),女,硕士,工程师,主要从事综合能源利用、电网需求响应、智能配用电、故障诊断等方面研究工作,278352439@qq.com
    甘海庆(1976),男,硕士,高级工程师,主要从事电力负荷管理、综合能源服务、营销数字化转型等方面研究工作,haiqinggan@139.com
    杨楠(1991),男,硕士,工程师,主要从事电力需求侧管理、能效服务、电动汽车充换电设施等方面研究工作,1592701263@qq.com
  • 基金资助:
    国家电网公司总部科技项目(5100-202118566A-0-5-SF)

Study on Uncertainty Operation Optimization of Virtual Power Plant Based on Intelligent Prediction Model Under Climate Change

Xiaoqiang JIA1, Yongbiao YANG2, Jiao DU2, Haiqing GAN3, Nan YANG4   

  1. 1.State Key Laboratory of Power Grid Safety (China Electric Power Research Institute), Haidian District, Beijing 100192, China
    2.School of Electrical Engineering, Southeast University, Nanjing 210096, Jiangsu Province, China
    3.State Grid Jiagnsu Electric Power Co. , Ltd. , Nanjing 210000, Jiangsu Province, China
    4.State Grid Jiangsu Electric Power Co. , Ltd. , Nanjing Power Supply Branch, Nanjing 210000, Jiangsu Province, China
  • Received:2023-08-03 Published:2023-12-31 Online:2023-12-28
  • Supported by:
    Science and Technology Projects of State Grid Corporation of China(5100-202118566A-0-5-SF)

摘要:

为有效应对气候变化,促进虚拟电厂(virtual power plant,VPP)的健康发展,基于区域气候模型(providing regional climate for impact studies,PRECIS)、BP神经网络预测模型和区间优化算法,提出了适应气候变化的VPP运行优化模型。应用PRECIS模拟2025年不同碳排放情景下气温、风速和辐射量等气象要素的变化规律;基于PRECIS气象要素模拟结果,应用BP神经网络模型预测2025年光伏电站的发电量;将区间优化算法与发电量预测结果相耦合,以此降低光伏发电不确定性对优化模型模拟结果的影响。结果显示,该模型可生成适应气候变化的VPP最优运行策略,降低系统运行成本,提升VPP运行效益。

关键词: 虚拟电厂(VPP), 区域气候模型(PRECIS), BP神经网络, 不确定性优化, 气候变化

Abstract:

In order to effectively cope with climate change and promote the healthy development of virtual power plant, an uncertainty operation optimization model of virtual power plant (VPP) adapted to climate change was proposed based on the providing regional climate for impact studies (PRECIS), BP neural network prediction model and interval optimization algorithm. PRECIS was used to simulate the changes in meteorological factors such as temperature,wind speed and radiation under different carbon emission scenarios in 2025. The BP neural network model was used to predict the power generation of photovoltaic power plants based on the simulation results of PRICES. The interval optimization algorithm was coupled with the power generation prediction results to reduce the impact caused by the influence of photovoltaic power generation uncertainty on the simulation results of the optimization model. The results show that the model can not only generate the optimal operation strategy of VPP under climate change, but also reduce operating costs and improve economic benefits.

Key words: virtual power plant (VPP), providing regional climate for impact studies (PRECIS), BP neural network, uncertainty optimization, climate change

中图分类号: