摘要
针对短期电力负荷预测,在极限学习机的基础上,提出了一种AdaBoost-KELM的方法。本文将KELM作为AdaBoost方法的基学习器,将AdaBoost-KELM方法应用于某地区的单步或者多步的短期电力负荷预测的实例中,在同等条件下,与BP,RBF,ELM,KELM,AdaBoost-BP,AdaBoost-RBF,AdaBoost-ELM几种方法进行比较。实验结果表明,所提出的AdaBoost-KELM方法在预测精度上最有优势。
For short-term power load forecasting,an AdaBoost-KELM method is proposed based on the limit learning machine.In this paper,KELM is used as the basic learner of AdaBoost method,and AdaBoost-KELM method is applied to the example of one-step or multi-step short-term power load forecasting in a region.Under the same conditions,it is compared with BP,RBF,ELM,KELM,AdaBoost BP,AdaBoost RBF,AdaBoost ELM and Ada-Boost ELM.The experimental results show that the proposed AdaBoost-KELM method has the best prediction accuracy.
作者
任瑞琪
Ren Ruiqi(Xi'an Railway Vocational and Technical Institute,Xi'an,Shaanxi 710026,China)
出处
《西安轨道交通职业教育研究》
2023年第1期31-34,共4页
Xi'an Rail Transit Vocational Education Research
关键词
电力负荷预测
极限学习机
Power Load Forecasting
Extreme Learning Machine