ELM算法在用户用电行为分析中的应用①.PDF

2016 年 第 25 卷 第 8 期 计 算 机 系 统 应 用 ELM 算法在用户用电行为分析中的应用① 胡殿刚 1, 李韶瑜 1, 楼 俏 2, 王 琼 2, 程淼海 2, 王国军 2, 李国辉 3,4 1(国网甘肃省电力公司, 兰州 730030) 2(国网甘肃省电力公司兰州供电公司, 兰州 730050) 3(福州大学 数学与计算机科学学院, 福州 350116) 4(福建省网络计算与智能信息处理重点实验室, 福州 350116) 摘 要: 对于非法用电行为的检测, 电力企业通常采用传统的人工检查方式, 而这种方式的准确率和效率往往都 比较低. 提出一种将极限学习机(ELM)应用于预测存在非法用电行为用户的方法. 首先, 在收集到的用户历史用 电数据, 对原始数据进行预处理. 然后, 应用 ELM 算法建立异常用电行为的神经网络模型. 最后, 在真实用电数 据上进行实证分析, 通过与随机森林算法建立的预测模型及预测结果的对比, 证明提出的方法具有较高的准确 率和较好的性能. 关键词: 极限学习机; 特征选择; 用户用电行为 Application of ELM Algorithm in the Analysis of Customer Electrical Behavior HU Dian-Gang1, LI Shao-Yu1, LOU Qiao2, WANG Qiong2, CHENG Miao-Hai2, WANG Guo-Jun2, LI Guo-Hui3,4 1(State Grid Gansu Electic Power Company, Lanzhou 730030, China) 2(State Grid Lanzhou Branch Electic Power Company of Gansu, Lanzhou 730050, China) 3(College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350108, China) 4(Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou 350116, China) Abstract: In order to detect the illegal use of electricity, electrical enterprises generally adopt traditional manual examination ways. However, both of the accuracy and efficiency of the approaches are far from satisfaction. In this paper, an analysis method based on the Extreme Learning Machine (ELM) algorithm is proposed, which is used to predict the behavior of customers’ illegal electric use. Firstly, it collects the historical electric usage data and preprocesses the data to make it suitable for analysis by the algorithms. Then, it applys an algorithm based on neural network model, which is called ELM, to build the model to describe the abnormal power utilization behavior of the customers. Finally, experiments on the real electrical c