基于EMD-RVM模型的短期负荷预测方法  

Short-term Load Prediction Method Based on EMD-RVM Model

作　　者：吕尚 孙悦桐 Lü Shang;SUN Yuetong(School of Electrical and New Energy,China Three Gorges University,Yichang 443000,China)

机构地区：[1]三峡大学,电气与新能源学院,湖北宜昌443000

出　　处：《微型电脑应用》2022年第10期22-24,31,共4页Microcomputer Applications

基　　金：湖北省科技计划项目技术创新专项重大项目(2016AAA040)。

摘　　要：负荷可能受到各种外部影响因子的影响,因而准确的负荷预测是一个具有挑战的问题。针对这个问题,提出基于经验模态分解(EMD)和相关向量机(RVM)的短期负荷预测方法。通过EMD对负荷序列进行分解,通过RVM预测每一个本征模函数分量,通过信号重构得到最终的负荷预测值。应用浙江省某地区的负荷数据和气象数据进行仿真,并与WD-RVM模型、RVM模型和CNN-GRU模型的预测结果进行比较,验证了所提出的方法具有相对较高的预测精度。The load may be affected by various external influence factors,and achieving accurate load forecasting is a challenging problem.To solve the problem,a short-term load forecast method based on empirical mode decomposition(EMD)and correlation vector machine(RVM)is proposed.The load sequence is decomposed by EMD,each eigenmode function component is predicted by RVM,and the final load forecast value is obtained by signal reconstruction.The simulation of load data and weather data in a certain area of Zhejiang Province and comparison with the prediction results of WD-RVM model,RVM model and CNN-GRU model verify that the proposed method has relatively high prediction accuracy.

关 键 词：经验模态分解 相关向量机 短期负荷预测 

分 类 号：TM743[电气工程—电力系统及自动化]