基于误差修正的短期负荷预测方法  

Short-term load forecasting based on deviation correction

作　　者：张贲[1] 邵常宁 赵燃 

机构地区：[1]国家电网公司华北分部,北京100053 [2]北京清软创新科技有限公司,北京100085

出　　处：《电力自动化设备》2015年第11期152-157,共6页Electric Power Automation Equipment

摘　　要：目前常用的负荷预测方法主要是通过负荷自身和相关关系的研究建立模型,提出一种新的负荷预测思路,即从传统频域预测方法的误差入手,通过研究虚拟预测误差的历史分布规律进行误差预测,然后对传统方法得到的预测结果进行修正。建立负荷预测的误差修正模型,并通过算例验证了误差修正的短期负荷预测方法的可行性和实用性,达到了提高短期负荷预测精度的目的。The current load forecasting methods mainly build models by rules of load itself and related factors. A new concept is proposed for the short-term load forecasting to ensure the reliable and economical operation of power system,which studies the deviation of traditional frequency-domain forecasting method to obtain the historic distribution rule of virtual forecasting deviation and modifies the forecasting results of traditional frequency-domain forecasting method by the forecasted deviation. A deviation correction model of load forecasting is built and a case study verifies the feasibility and practicability of the proposed method and shows the improved accuracy of short-term load forecasting.

关 键 词：负荷预测 短期预测 频域分解 虚拟预测 误差分析 误差修正 模型 

分 类 号：TM715[电气工程—电力系统及自动化]