基于PSO优化BP神经网络的能源需求预测  

Energy demand forecasting based on PSO optimized BP neural network

作　　者：吴伟杰 吴杰康[2] 雷振 郑敏嘉 张伊宁 李猛 黄欣 李逸欣 WU Weijie;WU Jiekang;LEI Zhen;ZHENG Minjia;ZHANG Yining;LI Meng;HUANG Xin;LI Yixin(Grid Planning&Research Center,Guangdong Power Grid Corporation,Guangzhou 510000,China;School of Automation,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东电网规划研究中心,广东广州510000 [2]广东工业大学自动化学院,广东广州510006

出　　处：《电气应用》2021年第6期49-58,共10页Electrotechnical Application

基　　金：广东省基础与应用基础研究基金区域联合基金项目—粤港澳研究团队项目(2020B1515130001);广东省科技计划项目(2020A050515003);广东电网有限责任公司科技计划项目(037700KK52190004)。

摘　　要：针对经济发展与能源消费存在复杂的耦合关系,从能源耦合角度出发提出了一种改进灰色关联分析和粒子群算法优化BP神经网络的能源需求预测方法。首先为量化能源耦合,粗略选取了与能源耦合密切相关的输入要素;其次,基于传统灰色关联分析的不足,建立了距离相似度和趋势相似度的综合相似度的输入要素选取方法,选取常用能源对应的输入要素;囿于BP神经网络的初始权重过于随机化,采用改进粒子群优化BP神经网络实现能源需求预测。以广东地区为实例,分析能源耦合对能源需求预测的影响,所提预测方法有效地提高了预测准确度,成功预测了"十四五""十五五"广东地区能源需求量。In view of the complex coupling relationship between economic development and energy consumption,an energy demand forecasting method based on Improved Grey Correlation Analysis and particle swarm optimization BP neural network is proposed from the perspective of energy coupling.Firstly,in order to quantify the energy coupling,the input elements closely related to the energy coupling are roughly selected;secondly,based on the shortcomings of the traditional grey correlation analysis,the input elements selection method of comprehensive similarity of distance similarity and trend similarity is established,and the corresponding input elements of each primary energy are selected;due to the randomization of the initial weight of BP neural network,the improved particle swarm optimization BP neural network is used to achieve energy demand forecasting.Taking Guangdong Province as an example,this paper analyzes the impact of energy coupling on energy demand forecasting,and verifies that the proposed forecasting method effectively improves the forecasting accuracy,and successfully forecasts the energy demand of Guangdong Province in the 14 th and 15 th five year plan.

关 键 词：能源需求预测 能源耦合关系 改进灰色关联分析 改进粒子群算法 BP神经网络 

分 类 号：F426.2[经济管理—产业经济] TP18[自动化与计算机技术—控制理论与控制工程]