基于神经网络的日峰荷预测方法中日期类型系数的确定.pdfVIP

第35 卷 第22 期 中 国 电 机 工 程 学 报 Vol.35 No.22 Nov. 20, 2015 2015 年11 月20 日 Proceedings of the CSEE ©2015 Chin.Soc.for Elec.Eng. 5715 DOI ：10.13334/j.0258-8013.pcsee.2015.22.005 文章编号：0258-8013 (2015) 22-5715-08 中图分类号：TM 715 基于神经网络的日峰荷预测方法中 日期类型系数的确定 1 1 2 2 2 包宇庆 ，李扬 ，杨斌 ，陈楚 ，阮文骏 (1．东南大学电气工程学院，江苏省 南京市 210096 ；2．江苏省电力公司，江苏省 南京市 210024) Weekday Index Determination for ANN-Based Daily Peak Load Forecasting Method 1 1 2 2 2 BAO Yuqing , LI Yang , YANG Bin , CHEN Chu , RUAN Wenjun (1. School of Electrical Engineering, Southeast University, Nanjing 210096, Jiangsu Province, China; 2. State Grid Jiangsu Electric Power Company, Nanjing 210024, Jiangsu Province, China) ABSTRACT: For the ANN-based short-term load forecasting, 该文采用一种基于遗传算法的气温修正方法，对气温变量进 the weekday index (day of week) is a very important 行修正。最后通过对苏州的实际负荷数据预测验证了方法的 influencing factor that needs to be considered. Usually, the 有效性。 weekday index is coded as 7 binary inputs. This paper 关键词：负荷预测；神经网络；日期类型系数；气温累积效应 proposed a method that codes the weekday index as only one input variable. Due to the simplicity, the precision of the 0 INTRODUCTION forecasting was improved. The proposed weekday index is determined by estimating the load’s difference of different day Short-term load forecasting is of great types.