基于智能算法的代理购电业务电量预测与评价体系研究  

Research on Electricity Demand Prediction and Evaluation System of Electricity Purchasing Agency Business Based on Intelligent Algorithms

作　　者：龙玲莉 李昆明[1] 祝永晋[1] 马吉科 雍文 仲智颖 LONG Lingli;LI Kunming;ZHU Yongjin;MA Jike;YONG Wen;ZHONG Zhiying(Jiangsu Frontier Electric Power Technology Co.,Ltd.,Nanjing 210096,Jiangsu Province,China)

机构地区：[1]江苏方天电力技术有限公司,江苏省南京市210096

出　　处：《电力信息与通信技术》2024年第9期70-77,共8页Electric Power Information and Communication Technology

摘　　要：我国电力市场目前仍处于改革中,电力企业代理购电预测的准确与否,在市场资源配置中起着决定性作用。为保证代理购电机制平稳发展,需明确电力企业市场化购电规模。目前代理购电电量主要是根据代理购电工商业用户用电量及典型负荷曲线进行预测,缺乏完整的体系,难以精确预测,导致缺少合理的规划。文章提出一套相似日月度预测算法与混合时序月度预测算法相结合的智能算法,用于代理购电业务电量预测与评价,围绕江苏省2022年用电情况进行预测,从5个维度对预测结果进行评价,帮助电力企业精准预判整体售电量规模,合理规划购电计划。The current power market in our country is still undergoing reform,and the prediction accuracy of electricity purchasing agency of power enterprise plays a critical role in market resource allocation.To ensure the stable development of electricity purchasing agency mechanism,it is necessary to make clear the market-oriented purchase scale of power enterprises.At present,the amount of electricity by purchasing agency is mainly predicted based on the electricity consumption of industrial and commercial users and typical load curves.There is a lack of a complete system,and it is difficult to predict accurately,resulting in a lack of reasonable planning.Therefore,a set of intelligent algorithms combining monthly prediction algorithm for similar days with hybrid time-series monthly prediction algorithm is proposed for electricity demand prediction and evaluation of electricity purchasing agency business.The power consumption in Jiangsu Province in 2022 is predicted and analyzed to support power enterprises accurately predict the overall electricity sales scale and plan power purchase plans reasonably.

关 键 词：智能算法 相似日月度预测算法 混合时序月度预测算法 代理购电 电量预测 

分 类 号：TM73[电气工程—电力系统及自动化] F426.61[经济管理—产业经济]