基于糊聚类的用电客户交费渠道偏好研究

发布时间：2018-05-29 17:38

  本文选题：电费回收 + 交费渠道　； 参考：《计算机工程与应用》2016年19期

【摘要】：电费回收直接关系到电力公司的有序运行,而交费渠道的建设和用电客户交费渠道的偏好,直接影响电力公司的电费回收;因此做好用电客户交费渠道偏好的研究至关重要。基于黑洞熵理论和贝叶斯模型,提出了适合电力数据的黑洞熵模糊聚类模型。该模型的显著特点是能通过最大后验概率推理和迭代抽样算法求解聚类最优参数,且适用于大规模用户数据。基于黑洞熵模糊聚类对某省用电客户的实际抽样数据进行模式发现表明,电力公司自营自助交费渠道尤为值得推广,预付费交费渠道最具有潜力。
[Abstract]:Electricity recovery is directly related to the orderly operation of power companies, and the construction of payment channels and the preference of customer payment channels directly affect the electricity recovery of power companies; therefore, it is very important to do a good job in the research of the preference of customer payment channels. Based on black hole entropy theory and Bayesian model, a black hole entropy fuzzy clustering model suitable for power data is proposed. The remarkable feature of this model is that it can solve the clustering optimal parameters by maximum posterior probability reasoning and iterative sampling algorithm, and it is suitable for large-scale user data. Based on black hole entropy fuzzy clustering, the actual sampling data of power customers in a certain province are found. The results show that self-service payment channels of power companies are particularly worthy of promotion, and prepaid payment channels have the most potential.
【作者单位】： 国网江苏省电力公司;江南大学数字媒体学院;国网江苏省电力公司南京供电公司;
【基金】：国家电网公司科技项目
【分类号】：F426.61;TP311.13
，

本文编号：1951809