中长期负荷预测研究

Research on medium and long term load forecasting

电力负荷是电力系统的重要组成部分,电力负荷预测对电力系统分析、设计和控制具有重要的影响。随着智能微电网的发展,负荷预测也逐渐成为能量管理系统中的重要模块,是“源、网、荷、储”能量流匹配中的重要环节。采用回归分析与趋势外推相结合的预测方法,基于历史负荷数据的横向比较,识别异常数据,再通过插值法进行异常数据修正,然后通过分析历史时间序列的负荷数据特点,采用合适的函数模型曲线进行拟合,并引入修正因子,最终得到负荷预测数据。结果表明:年度预测的拟合误差较小,月度预测的误差略大,引入修正因子后,平均误差下降了4%。该方法可初步用于年度及月度的负荷预测,为智能微电网的规划奠定了一定的技术基础。

Power load is an important part of power system.Power load forecasting plays an important role in power system analysis,design and control.With the development of smart micro-grid,load forecasting has gradually become an important module in the energy management system(EMS),which is an important link in the energy flow matching of“source,network,load and storage”.Based on the horizontal comparison of historical load data,the abnormal data are identified and corrected by interpolation method,which is based on the combination of regression analysis and trend extrapolation.Then the characteristics of load data of historical time series are analyzed,and the appropriate function model curve is fitted as well as the correction factor is introduced.Finally,the load forecasting data are obtained.The results show that the fitting error of the annual prediction is small and the error of the monthly prediction is relatively large.After introducing the correction factor,the average error decreases by 4%.This method can be applied to the annual and monthly load forecasting,which lays a certain technical foundation for the planning of smart micro-grid.