决策函数应用下电力需求信息个性化推荐  

Personalized recommendation of power demand information based on decision function

作　　者：刘振华 覃浩 苏立伟 方霆 LIU Zhen-hua;QIN Hao;SU Li-wei;FANG Ting(Guangdong Power Grid Co.,Ltd.,Customer Service Center,Guangzhou 510000,China)

机构地区：[1]广东电网有限责任公司客户服务中心,广州510000

出　　处：《信息技术》2022年第12期177-182,共6页Information Technology

摘　　要：为了解决电力市场用户量庞大,交易过程中电力需求信息选择困难的问题,研究决策函数应用下电力需求信息个性化推荐方法。提出基于FTP效用函数和关联分析的区间二型模糊决策方法,在计算区间二型模糊关联度的基础上,结合FTP效用函数产生区间二型模糊信息集成算子,排序推荐策略,实现电力需求信息个性化推荐。实验结果表明,使用该方法后MAE和RMSE始终低于使用前的结果,NDCG结果上升趋势先迅速后缓慢,贴近度与实际贴近度基本一致,推荐性能极具优势。In order to solve the problem of the difficulty of selection of power demand information in the transaction process among large number of users in the power market,the personalized recommendation method of power demand information under the application of decision function is studied.An interval type-2 fuzzy decision-making method based on FTP utility function and correlation analysis is proposed.On the basis of calculating the interval type-2 fuzzy correlation degree,combined with FTP utility function,the interval type-2 fuzzy information integration operator is generated,and the ranking recommendation strategy is used to realize the personalized recommendation of power demand information.The experiment results show that the MAE and RMSE results after using this method are always lower than those before using.The rising trend of NDCG results shows rapid first and slow afterwards.The closeness is basically consistent with the actual closeness,and the recommended performance is very advantageous.

关 键 词：排序 决策函数 电力需求信息 推荐方法 二型模糊集 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]