发电技术 ›› 2024, Vol. 45 ›› Issue (2): 299-311.DOI: 10.12096/j.2096-4528.pgt.23017

• 新能源 • 上一篇    下一篇

一种二模态天气分型方法及其在光伏功率概率预测的应用

付小标1, 侯嘉琪2, 李宝聚1, 温亚坤2, 赖晓文3, 郭雷1, 王志伟1, 王尧1, 张海锋4, 李德鑫4   

  1. 1.国网吉林省电力有限公司电力调度控制中心, 吉林省 长春市 130021
    2.北京清能互联科技有限公司创新中心, 北京市 海淀区 100084
    3.清华四川能源互联网研究院交易与运筹研究所, 四川省 成都市 610299
    4.国网吉林省电力有限公司电力科学研究院, 吉林省 长春市 130021
  • 收稿日期:2023-02-20 出版日期:2024-04-30 发布日期:2024-04-29
  • 通讯作者: 侯嘉琪
  • 作者简介:付小标(1979),男,硕士,高级工程师,研究方向为电力系统调度运行与管理,syfuxb@jl.sgcc.com.cn
    侯嘉琪(1998),女,硕士,研究方向为新能源功率预测,本文通信作者,houjq@tsintergy.com
    李宝聚(1986),男,博士,高级工程师,研究方向为电力系统调度运行与管理,libaoju1986@163.com
    温亚坤(1993),男,硕士,工程师,研究方向为人工智能、负荷预测,wenyk@tsintergy.com
    赖晓文(1988),男,博士,高级工程师,研究方向为电力系统调度优化、电力市场,laixwthu@163.com
    李德鑫(1985),男,硕士,高级工程师,研究方向为新能源技术研究与应用,lidexin0323@163.com
  • 基金资助:
    国网吉林省电力有限公司揭榜挂帅项目(2021JBGS-09)

A Two-Modal Weather Classification Method and Its Application in Photovoltaic Power Probability Prediction

Xiaobiao FU1, Jiaqi HOU2, Baoju LI1, Yakun WEN2, Xiaowen LAI3, Lei GUO1, Zhiwei WANG1, Yao WANG1, Haifeng ZHANG4, Dexin LI4   

  1. 1.Power Dispatch Control Center of State Grid Jilinsheng Electric Power Supply Company, Changchun 130021, Jilin Province, China
    2.Innovation Center of Beijing TsIntergy Technology Co. , Ltd. , Haidian District, Beijing 100084, China
    3.Transaction and Operations Research Division of Tsinghua Sichuan Energy Internet Research Institute, Chengdu 610299, Sichuan Province, China
    4.Electric Power Research Institute of State Grid Jilinsheng Electric Power Supply Company, Changchun 130021, Jilin Province, China
  • Received:2023-02-20 Published:2024-04-30 Online:2024-04-29
  • Contact: Jiaqi HOU
  • Supported by:
    Science and Technology Project Selected by the Open Competition Mechanism of State Grid Jilinsheng Electric Power Supply Company(2021JBGS-09)

摘要:

天气分型是光伏功率预测中不可或缺的预处理步骤,为精细刻画光伏出力的不确定性,提出一种新的基于光伏功率聚类的二模态天气分类方法。该方法结合气象信息和功率信息进行天气分型,为天气分型在光伏功率预测的应用提供了一条有效的新路径。此外,该方法使用数据融合技术,依据融合数值天气预报(numeric weather prediction,NWP)气象和实际气象二者间的相关信息进行天气分型,以减少模型对NWP准确度的依赖并提高模型的鲁棒性。以吉林某光伏电站数据为例,验证了该天气分型方法的合理性,同时,将天气分型方法与功率概率预测相结合,其测算结果表明,使用所提方法进行天气分型概率预测的区间覆盖率更接近预设的置信水平,且平均带宽更窄。

关键词: 光伏发电, 天气分型, 光伏功率概率预测, 时间序列K均值聚类, 多模态学习, 不确定性, 数值天气预报

Abstract:

Weather classification is an indispensable preprocessing step in photovoltaic (PV) power prediction. A new two-modal weather classification methods based on PV power clustering was proposed to finely depict the uncertainty of PV power output. Both PV power data and meteorological data were considered for weather classification, providing a novel and effective path for PV power prediction. In addition, data fusion technology was used to extract relevant information from both numeric weather prediction (NWP) data and measured meteorological data to help for weather classification. This approach reduces the model’s reliance on the accuracy of forecasted meteorological indicators and improve the robustness of the model. Experiments based on data from a PV power station in Jilin demonstrated the rationality of the proposed weather classification method. Combining the PV power probability prediction with the proposed weather classifier resulted in prediction interval coverage probabilities closer to the preassigned confidence level and narrower mean prediction interval width.

Key words: photovoltaic power generation, weather classification, photovoltaic power probability prediction, time series K-means clustering, multi-modal learning, uncertainty, numeric weather prediction

中图分类号: