Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (10): 90-95.DOI: 10.3778/j.issn.1002-8331.1801-0479

Previous Articles     Next Articles

Recommendation Method of Power Selling Packages Considering Spark and Attribute Weights

QU Zhaoyang1,2, FENG Rongqiang1,2, QU Nan3, XIE Shuya1,2, LIU Yaowei4, YAN Jia4   

  1. 1.College of Information Engineering, Northeast Electric Power University, Jilin 132012, China
    2.Jilin Engineering Technology Research Center of Intelligent Electric Power Big Data Processing, Jilin 132012, China
    3.Maintenance Company of Jiangsu Power Company, Nanjing 210000, China
    4.State Grid Jilin Electric Power Supply Company, Changchun 130000, China
  • Online:2019-05-15 Published:2019-05-13

计及Spark和属性权重的售电套餐推荐方法

曲朝阳1,2,冯荣强1,2,曲  楠3,谢树雅1,2,刘耀伟4,颜  佳4   

  1. 1.东北电力大学 信息工程学院,吉林 132012
    2.吉林省电力大数据智能处理工程技术研究中心,吉林 132012
    3.国网江苏省电力公司 检修分公司,南京 210000
    4.国网吉林省电力有限公司,长春 130000

Abstract: Aiming at the huge user groups in the power market and the difficult selection of power selling packages in the trading process, a recommendation method of power selling packages based on Spark is proposed. At the same time, the scalability and real-time issues of the packages in the big data environment is also solved. First, the weight values of each package attribute are calculated, and the comprehensive similarity is calculated. Then, taking into account both the user and packages, a recommended method of packages is proposed to achieve the accurate recommendation of power selling packages. Experiments show that the proposed method can significantly improve the accuracy of recommendation and has good recommendation efficiency and scalability in distributed environment.

Key words: power market, Spark, recommendation of power selling packages, attribute weights

摘要: 针对电力市场用户群庞大,交易过程中售电套餐选择困难的问题,在Spark环境下设计了一种售电套餐推荐方法,同时也解决了售电套餐推荐过程中在大数据环境下的可扩展性及实时性问题。首先,计算出每个套餐属性的权重值,从而计算得到售电套餐综合相似度。然后,计及用户和套餐两方面提出一种售电套餐推荐方法,实现售电套餐的精准推荐。实验表明,提出的推荐方法能够明显提高推荐的准确度,并且在分布式环境下具有良好的推荐效率和可扩展性。

关键词: 电力市场, Spark, 售电套餐推荐, 属性权重