数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (4): 140-148.

doi: 10.11871/jfdc.issn.2096-742X.2021.04.012

• 技术与应用 • 上一篇    

基于时序数据处理的分布式光伏功率预测系统

刘晓艳1,2(),王珏1,*(),姚铁锤1,2(),迟学斌1,2(),王晓光1(),李凯1()   

  1. 1.中国科学院计算机网络信息中心,北京 100190
    2.中国科学院大学,北京 100049
  • 收稿日期:2021-03-04 出版日期:2021-08-20 发布日期:2021-08-30
  • 通讯作者: 王珏
  • 作者简介:刘晓艳,中国科学院计算机网络信息中心,硕士研究生,主要研究方向为人工智能算法、时序数据预测。
    本文承担工作为:时序数据处理算法设计、算法实现、系统实现。
    LIU Xiaoyan is a master student at Com-puter Network Information Center of the Chinese Academy of Sciences..Her main research interests are artificial intelligence algorithms and time series data prediction.
    In this paper she undertakes the following tasks: time series data processing algorithm design, algorithm realization, and system realization
    E-mail: liuxiaoyan@cnic.cn|王珏,中国科学院计算机网络信息中心,副研究员,博士,主要研究方向为人工智能算法与应用软件。
    本文承担工作为:分布式光伏功率预测系统设计。
    WANG Jue, Ph.D., is an associate research fellow of Computer Network Information Center of the Chinese Academy of Sciences. His main research interests are artificial intelligence algorithms and application software.
    In this paper he undertakes the following tasks: the design of distributed photovoltaic power prediction system.
    E-mail: wangjue@sccas.cn|姚铁锤,中国科学院计算机网络信息中心,博士研究生,主要研究方向为人工智能。
    本文承担工作为:系统实现。
    YAO Tiechui is a Ph.D. student at Com-puter Network Information Center of the Chinese Academy of Sciences. His main research interest is arti-ficial intelligence.
    In this paper he undertakes the following tasks: system imple-mentation.
    E-mail: yaotiechui@cnic.cn|迟学斌,中国科学院计算机网络信息中心,研究员,博士生导师,主要研究方向为高性能计算、并行计算。
    本文承担工作为:系统的整体结构设计、研究指导。
    CHI Xuebin is a research fellow and Ph.D. supervisor of Computer Network Information Center of the Chinese Academy of Sciences. His main research interests are high performance computing and parallel computing.
    In this paper he undertakes the following tasks: the design of overall paper structure and research guidance of the system.
    E-mail: chi@sccas.cn|王晓光,中国科学院计算机网络信息中心,工程师,硕士,主要研究方向为人工智能算法与应用软件。
    本文承担工作为:系统实现。
    WANG Xiaoguang, master, is an engineer at Computer Network Information Center of the Chinese Academy of Sciences. His main research interests are artificial intelligence algorithms and application software.
    In this paper he undertakes the following tasks: system imple-mentation.
    E-mail: wangxg@cnic.cn|李凯,中国科学院计算机网络信息中心,工程师,硕士,主要研究方向为人工智能平台与应用软件。
    本文承担工作为:系统优化。
    LI Kai, master, is an engineer at Com-puter Network Information Center of the Chinese Academy of Sciences. His main research interests are artificial intelligence platforms and application software.
    In this paper he undertakes the following tasks: system optimi-zation.
    E-mail: kai.li@cnic.cn
  • 基金资助:
    科技部重大科技项目(2020AAA0105202);中国科学院战略性先导科技专项(A类)(XDA27000000)

A Distributed Photovoltaic Power Prediction System Based on Time Series Data Processing

LIU Xiaoyan1,2(),WANG Jue1,*(),YAO Tiechui1,2(),CHI Xuebin1,2(),WANG Xiaoguang1(),LI Kai1()   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2021-03-04 Online:2021-08-20 Published:2021-08-30
  • Contact: WANG Jue

摘要:

【目的】使用高质量的历史数据预测未来光伏发电功率,对高效利用太阳能可再生能源、补充电网供电能力和推进节能减碳具有重要意义。【方法】由于光伏时序数据质量参差不齐,本文提出了面向光伏时序数据的缺失值与异常值处理算法,并基于此搭建了分布式光伏功率预测系统。【结果】该系统可以有效处理多种光伏时序数据,并集成了不同时间尺度及不同时长的功率预测模型,可以对多个电站展开光伏功率预测。【结论】该系统能够满足智能电网对辖区内光伏电站功率预测的需求。

关键词: 时序数据处理, 光伏功率预测, 分布式光伏系统, 系统设计

Abstract:

[Objective] Using high-quality historical data to predict future photovoltaic (PV) power generation is of great significance for the efficient use of renewable solar energy, supplementing the power supply capacity of the Power Grid, and promoting energy conservation and carbon reduction. [Methods] Due to the uneven quality of PV time series data, this paper proposes an algorithm for processing missing values and outliers of PV time series data, based on which a distributed PV power prediction system is built. [Results] The system can effectively process a variety of PV time series data, integrate power prediction models of different durations and time scales, and predict PV power for multiple power stations. [Conclusions] This system can meet the demands of a smart Power Grid for power forecasting of PV power stations within its jurisdiction.

Key words: time series data processing, photovoltaic power prediction, distributed photovoltaic system, system design