Frontiers of Data and Computing ›› 2021, Vol. 3 ›› Issue (4): 140-148.

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

• Technology and Applicaton • Previous Articles    

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 E-mail:liuxiaoyan@cnic.cn;wangjue@sccas.cn;yaotiechui@cnic.cn;chi@sccas.cn;wangxg@cnic.cn;kai.li@cnic.cn

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