基于组合预测技术的高压配电网中期负荷预测研究  

Research on medium term load forecasting of high-voltage distribution network using the combined forecasting technique

作　　者：颜欣藜 李红伟[1] 刘宇陆 张凤珠 YAN Xinli;LI Hongwei;LIU Yulu;ZHANG Fengzhu(School of Electrical Engineering and Information,Southwest Petroleum University,Chengdu 610500,China;Jiangbei Power Supply Branch of State Grid Chongqing Electric Power Company,Chongqing 401147,China)

机构地区：[1]西南石油大学电气信息学院,四川成都610500 [2]国网重庆市电力公司江北供电分公司,重庆401147

出　　处：《电气应用》2019年第10期66-75,共10页Electrotechnical Application

摘　　要：负荷预测是制定发电计划的前提,也是电网安全预警、迎峰负荷调度控制必不可少的环节。针对高压配电网的高峰负荷预测开展研究,预测的基本对象单元为110 kV电站的单台主变压器所接负荷。首先对预测基本对象进行了分析,基于110 kV主变压器负载历史数据分析了其负荷的时间分布特性,并选取地区GDP与温度作为变量元,研究了它们对负荷的相关性影响。在此基础上,采用了组合预测技术,即以二元非线性回归分析法为主,自然增长率法、灰色预测法和季度性趋势比率法为辅进行预测,结合实际算例进行了验证分析,结果显示了算法的有效性,可为高压配电网的高峰负荷转供问题提供数据支持。Load forecasting is the premise of formulating power generation plan, and it is also an indispensable link for power grid security warning and peak load dispatch control. The peak load forecasting of high voltage distribution network is studied. The basic unit of prediction is the load of a single main transformer of 110 kV power station. Firstly, the predicted basic objects are analyzed. The time distribution characteristics of the load are analyzed based on the historical data of 110 kV main transformer load. The regional GDP and temperature are selected as the variable elements, and their correlation effects on the load are studied. On this basis, the combination forecasting technique is adopted, whichmeans the binary nonlinear regression analysis method is mainly used, and the natural growth rate method, the gray prediction method and the quarterly trend ratio method are used as the supplement to predict, and the verification analysis is carried out based on the actual example. The results show the effectiveness of the algorithm and provide data support for the peak load transfer problem of the high voltage distribution network.

关 键 词：城市高压配电网 负荷预测 组合预测技术 二元非线性回归分析 灰色预测法 

分 类 号：TM715[电气工程—电力系统及自动化]