| 基于相似日原理和CPSO-Elman模型的光伏电站短期功率预测 |
| |
| 引用本文： | 王 超,刘世明.基于相似日原理和CPSO-Elman模型的光伏电站短期功率预测[J].中州煤炭,2022,0(2):208-214. |
| |
| 作者姓名： | 王 超 刘世明 |
| |
| 作者单位： | （1.昌吉学院 物理系，新疆 昌吉 831100； 2.库尔勒新特汇能能源有限责任公司，新疆 库尔勒 841000） |
| |
| 摘 要： | 为了提高光伏电站短期预测功率的精度，提出一种基于相似日原理和改进CPSO-Elman神经网络模型的光伏电站短期功率预测方法。将历史运行数据按照时长划分不同季节，采用欧式距离对天气类型进行处理并建立天气类型系数，通过灰色关联分析法和余弦相似度指标结合选取相似日。由于粒子群算法搜索速度慢且存在易早熟等缺陷，采用改进混沌粒子群（CPSO）来优化Elman神经网络的权值和阈值，对夏季不同天气类型条件下的短期功率分别预测。选用南疆某光伏电站2020年运行数据进行分析，结果表明:CPSO-Elman在非晴天条件下也具有较高的预测精度。
|
| 关 键 词： | 光伏电站 功率预测 相似日原理 粒子群算法 Elman神经网络 |
Short term power prediction of photovoltaic power station based on similar day principle and CPSO-Elman model |
| |
| Wang Chao,Liu Shiming. Short term power prediction of photovoltaic power station based on similar day principle and CPSO-Elman model[J].Zhongzhou Coal,2022,0(2):208-214. |
| |
| Authors: | Wang Chao Liu Shiming |
| |
| Affiliation: | （1.Department of Physics，Changji University，Changji 831100，China； 2.Korla Xinte Huineng Energy Co.，Ltd.，Korla 841000，China） |
| |
| Abstract: | In order to improve the accuracy of short term power prediction of photovoltaic power station,a short term power prediction method of photovoltaic power station based on similar day principle and improved CPSO-Elman neural network model is proposed.The historical operation data are divided into different seasons according to the duration,the European distance is used to process the weather types and establish the weather type coefficient,and the similar days are selected by combining the grey correlation analysis method and cosine similarity index.Due to the slow search speed and premature of particle swarm optimization algorithm,the improved chaotic particle swarm optimization (CPSO) is used to optimize the weight and threshold of Elman neural network to predict the short term power under different weather types in summer.The operation data of a photovoltaic power station in southern Xinjiang in 2020 are selected for analysis.The results show that CPSO Elman also has high prediction accuracy under non sunny conditions. |
| |
| Keywords: | ,photovoltaic station, power forecast, similar day theory, particle swarm optimization（PSO）, Elman neural networ |
|
| 点击此处可从《中州煤炭》浏览原始摘要信息 |
|
点击此处可从《中州煤炭》下载全文 |
