基于WT和黏菌算法的LSSVM短期风功率预测
Short-Term Wind Power Prediction Using LSSVM Based on WT and Slime Mould Algorithm
赵卿 1高文华 1石慧 1董增寿1
作者信息
- 1. 太原科技大学电子学院,山西 太原 030024
- 折叠
摘要
针对风电出力存在随机性、波动性等问题,建立基于小波变换(WT)与黏菌算法(Slime mould algorithm,SMA)优化最小二乘支持向量机(LSSVM)关键参数的风功率预测模型.首先利用小波变换将风功率信号以及风速信号分解为多个不同频率的平稳的子序列,并提出采用一种黏菌优化算法优化LSSVM的参数,同时引入气象因素,包括风速、风向、温度、气压、湿度作为输入,分别建立模型来预测风电功率.通过将各个模型预测结果加和得到完整的风功率预测值.使用某风电厂数据进行仿真验证,实验结果表明,所提出的WT-SMA-LSSVM预测模型在短期风功率预测中具有更高的预测精度.
Abstract
The wind power prediction model based on the wavelet transform(WT)and the Slime mould algorithm(SMA)is developed to optimise the key parameters of the least squares support vector machine(LSSVM).A wavelet transform was used to decompose the wind power signal and the wind speed signal into several smooth subseries with different frequencies,and a slime mould algorithm was proposed to optimise the parameters of the LSSVM,while mete-orological factors,including wind speed,wind direction,temperature,air pressure and humidity,were introduced as in-puts to build separate models to predict wind power.The complete wind power prediction was obtained by summing the individual model predictions.The simulations were carried out using data from a wind power plant and the experi-mental results show that the WT-SMA-LSSVM prediction model proposed in this paper has higher prediction accuracy in short-term wind power prediction.
关键词
风功率预测/最小二乘支持向量机/小波变换/黏菌算法Key words
Wind power forecasting/Least squares support vector machine/Wavelet transform/Slime mould algo-rithm引用本文复制引用
基金项目
国家青年科学基金项目(61703297)
国家青年科学基金项目(72071183)
山西省重点研发计划项目(202202100401002)
山西省重点研发计划项目(202202090301011)
山西省重点研发计划项目(202202150401005)
山西省基础研究计划(自由探索类)面上项目(20210302123206)
山西省基础研究计划(自由探索类)面上项目(202203021211205)
山西省回国留学人员科研资助项目(2021-135)
山西省回国留学人员科研资助项目(2021-134)
山西省留学人员科技活动择优资助项目(20220029)
出版年
2024
NETL
NSTL
万方数据