基于均衡KNN算法的电力负荷短期并行预测

为提高电力负荷预测精度，应对海量、高维数据带来的单机计算资源不足的问题，提出一种基于均衡KNN算法的短期电力负荷并行预测方法。针对电力负荷数据特征，采用K均值聚类算法进行电力负荷场景划分；为提高场景划分精度，采用反熵权法量化负荷特征的权重系数；针对不均衡的负荷场景，提出均衡KNN算法对待预测负荷进行精确的场景归类；采用BP神经网络算法对海量历史数据进行负荷预测模型的分场景训练与预测；采用ApacheSpark架构对提出的模型进行并行化编程，提高其处理海量、高维数据的能力。选取某小区居民用电数据进行算例分析，在30节点云计算集群上进行测试验证，结果表明基于该模型的负荷预测精度与执行时间均优于传统预测算法，且提出的算法具有优异的并行性能。

Short-term Parallel Power Load Forecasting Based on Balanced KNN

To improve the accuracy of load forecasting and cope with the challenge of single computer's insufficient computing resource under massive and high-dimension data, a short-term load forecasting model based on balanced KNN algorithm is proposed. In order to improve the accuracy of scene division, the weight of load characteristics is quantified by using the anti-entropy weight method; 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 BP neural network algorithm is used to train and predict the load; Adopting the Apache Spark 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 30-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, besides, the proposed forecasting algorithm possesses excellent parallel performance.