[1]陈宝奇,周再祥,张 强.基于混沌麻雀搜索算法优化BP神经网络的短期风电功率预测[J].工业仪表与自动化装置,2022,(06):13-17.[doi:10.19950/j.cnki.cn61-1121/th.2022.06.003]
　CHEN Baoqi,ZHOU Zaixiang,ZHANG Qiang.Short term wind power prediction based on BP neural network optimized by chaos sparrow search optimization algorithm[J].Industrial Instrumentation & Automation,2022,(06):13-17.[doi:10.19950/j.cnki.cn61-1121/th.2022.06.003]

点击复制

基于混沌麻雀搜索算法优化BP神经网络的短期风电功率预测

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:

期数:

2022年06期

页码:

13-17

栏目:

出版日期:

2022-12-15

文章信息/Info

Title:

Short term wind power prediction based on BP neural network optimized by chaos sparrow search optimization algorithm

文章编号:

1000-0682（2022）06-0000-00

作者:

陈宝奇1; 周再祥2; 张 强1

1. 兰州理工大学 电气工程与信息工程学院，甘肃 兰州 730050；

2. 甘肃送变电工程有限公司，甘肃 兰州 730050

Author(s):

CHEN Baoqi1; ZHOU Zaixiang2; ZHANG Qiang1

1. College of Electrical and Information Engineering, Lanzhou University of Technology,Gansu Lanzhou 730050,China;

2.State Grid Gansu Power Transmission & Distribution Engineering Co., Gansu Lanzhou 730050,China

关键词:

风电功率预测; 混沌麻雀搜索算法( CSSOA); 改进神经网络; 预测精度

Keywords:

wind power prediction;  chaos sparrow search optimization algorithm(CSSOA);  improved neural network;  prediction accuracy

分类号:

TK8

DOI:

10.19950/j.cnki.cn61-1121/th.2022.06.003

文献标志码:

A

摘要:

在构建以新能源为主体的电力系统方面，风电功率的短期预测对提高电力系统的经济效益和风能利用率十分重要。针对传统麻雀搜索算法(SSA)优化BP(SSA-BP)神经网络对风电功率的短期预测存在易陷入局部最优、收敛速度较慢和预测精度不高等问题，提出一种基于混沌麻雀搜索优化算法( CSSOA)优化BP( CSSOA-BP）神经网络的短期风电功率预测方法。该文以西北某风电场作为研究对象，引入皮尔逊(person)相关系数，分析出与风电功率输出相关性较强的风电机组数据集作为模型的输入，避免冗余数据影响风电功率的预测；利用SSA算法和CSSOA算法分别改进BP神经网络；使用该风电场实测历史数据对各预测模型进行仿真测试。仿真结果表明：基于 CSSOA-BP的预测模型相较于SSA-BP拥有更好的预测精度，更符合电力工业生产的需求。

Abstract:

In building a new energy-based power system, short-term prediction of wind power is very important to improve the economic benefits and annual utilization of power system. A short-term wind power prediction method based on chaos sparrow search optimization algorithm(CSSOA) to optimize BP (CSSOA-BP) neural network is proposed to solve the short-term wind power prediction problem of traditional sparrow search algorithm (SSA-BP) neural network, which is prone to fall into local optimization, slow convergence rate and low accuracy. This paper takes a wind farm in Northwest China as the research object. By introducing perason correlation coefficient, a wind power set dataset with strong correlation with wind power output is analyzed as input of the model to avoid redundant data affecting wind power prediction. The BP network is improved by SSA algorithm and CSOA algorithm, respectively. The prediction methods are simulated using the historical data of the wind farm. The simulation results show that the prediction method based on CSSOA-BP has better prediction accuracy than SSA-BP and meets the demand of power industry production better.

参考文献/References:

[1] 丁鹏.基于贝叶斯随机抽样的风电设备可靠性分析与维修决策研究[D].北京：华北电力大学，2019.

相似文献/References:

备注/Memo

备注/Memo:

收稿日期：2022-07-19

作者简介：陈宝奇（1997），男，甘肃兰州人，硕士研究生，研究方向为新能源出力预测。

常用功能