基于Kmeans-SSA-LSSVM的光伏短期功率预测

PV Short-Term Power Prediction Based on Kmeans-SSA-SVM

光伏发电受多种气象因素和环境因素的影响,具有明显的间歇性、随机性和波动性。为了提高光伏短期功率预测的准确性,提出了一种基于Kmeans-SSA-LSSVM的预测模型,以提高预测精度。首先使用Kmeans算法对天气进行分类,然后利用SSA优化后的LSSVM对各天气类型分别进行功率预测。结果表明与BP、SVM、PSO-SVM相比,Kmeans-SSA-LSSVM提高了光伏短期功率预测模型的精度,对电力系统并网调度有重要意义。

Photovoltaic power generation is affected by a variety of meteorological and environmental factors,and has obvious intermittent,random and fluctuation.In order to improve the accuracy of short-term photovoltaic power prediction,a prediction model based on Kmeans-SSA-LSSVM is proposed to improve the prediction accuracy of the model.Firstly,the Kmeans algorithm is used to classify the weather.Then,the LSSVM optimized by SSA is used to predict the power of each weather type in decibels.The results show that compared with BP,SVM and PSO-SVM,Kmeans-SSA-LSSVM improves the accuracy of photovoltaic short-term power prediction model,which is of great significance for grid-connected scheduling of power systems.