摘要
针对短期水电功率影响分析,为提高水电功率预测的准确性,通过粒子群优化算法优化支持向量机参数,建立较优的预测模型并对水电功率进行预测。利用SVM模型对水电功率特征信息进行分类与识别,引入PSO对SVM的优化算法模型对其参数进行优化,提高模型的分类识别准确率。实验结果表明,PSO-SVM模型能够显著提高水电功率预测的精度和效率,具有一定的实用价值。
For short-term hydropower power impact analysis,in order to improve the accuracy of hydropower power prediction,Particle Swarm Optimization was used to optimize the parameters of support vector machines(SVM).The optimal prediction model is established and the hydropower power is forecasted.Firstly,SVM model is used to classify and identify hydropower power characteristics.Secondly,PSO was introduced to the SVM optimization algorithm model to optimize its parameters and improve the classification recognition accuracy of the model.The experimental results show that the PSO-SVM model can significantly improve the accuracy and efficiency of hydropower power prediction,and has certain practical value.
作者
王鹤炅
赵家伟
Wang Hejiong;Zhao Jiawei(School of Electrical and Control Engineering,Liaoning Technical University,Huludao Liaoning 125105,China)
出处
《现代工业经济和信息化》
2024年第6期287-288,293,共3页
Modern Industrial Economy and Informationization
关键词
水电功率预测
粒子群优化算法
支持向量机
hydropower power forecast
particle swarm optimization algorithm
support vector machine
