计及Spark和属性权重的售电套餐推荐方法

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。

Recommendation Method of Power Selling Packages Considering Spark and Attribute Weights

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.