Short-term Power Load Forecasting Based on Balanced KNN

2017 International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Lv, Xianlong^1 ; Cheng, Xingong^1 ; Shuang, Yan^2 ; Tang, Yan-Mei^3

School of Electrical Engineering, University of Jinan, Jinan, China^1

Zaozhuang Power Supply Company of Shandong Province, Zaozhuang, China^2

China Electric Power Research Institute, Beijing, China^3

关键词: Forecasting algorithm;    High-dimension data;    Household electricity consumption;    Linear regression algorithms;    Load characteristics;    Power load forecasting;    Residential districts;    Short term load forecasting;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/322/7/072058/pdf
DOI  :  10.1088/1757-899X/322/7/072058

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

To improve the accuracy of load forecasting, a short-term load forecasting model based on balanced KNN algorithm is proposed; According to the load characteristics, the historical data of massive power load are divided into scenes by the K-means algorithm; In view of unbalanced load scenes, the balanced KNN algorithm is proposed to classify the scene accurately; The local weighted linear regression algorithm is used to fitting and predict the load; Adopting the Apache Hadoop programming framework of cloud computing, the proposed algorithm model is parallelized and improved to enhance its ability of dealing with massive and high-dimension data. The analysis of the household electricity consumption data for a residential district is done by 23-nodes cloud computing cluster, and experimental results show that the load forecasting accuracy and execution time by the proposed model are the better than those of traditional forecasting algorithm.