基于支持向量机的电网负荷预测  

Load Forecasting of Power Grid Based on Support Vector Machine

作　　者：王诗涵 周法国[1] WANG Shihan;ZHOU Faguo(School of Mechanical Electronic&Information Engineering,China University of Mining and Technology-Beijing,Beijing 100083,China)

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《现代信息科技》2020年第24期120-122,共3页Modern Information Technology

摘　　要：基于现有的电力负荷预测方法提高电力负荷预测的准确性,提出了一种基于支持向量机(SVM)的电力负荷预测模型。首先分析支持向量机的理论基础,通过建立支持向量机预测模型,将经过预处理的真实电力数据输入该模型进行学习预测,借助均方根误差(RMSE)、平均绝对百分比误差(MAPE)以及预测图表对模型预测性能进行验证分析。实验结果表明,SVM预测模型能够较为准确地对电力负荷预测进行刻画。Based on the existing power load forecasting methods to improve the accuracy of power load forecasting,a power load forecasting model based on support vector machine(SVM)is proposed.First,analyze the theoretical basis of support vector machines,and by establishing a support vector machine prediction model,input the pre-processed real power data into the model for learning prediction.The prediction performance of the model is verified and analyzed with the help of root mean square error(RMSE),mean absolute percentage error(MAPE)and prediction chart.The experimental results show that the SVM prediction model can describe the power load forecast more accurately.

关 键 词：机器学习 电力负荷 支持向量机 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置]