异常电力负荷数据的辨识方法研究

为了满足实际对负荷预测精度的要求,提高中期负荷预测的准确性,针对目前异常数据辨识方法工作量大,人工干预较多,易误判、漏判的现状,以及电力系统年负荷曲线所具有的纵向相似性和横向相似性,提出了基于数理统计及三点平滑原理的异常数据辨识和修正算法.通过对甘肃省电网实际历史数据的辨识和修正研究,验证了此方法具有简单实用、工作量小、人工干预大大减少等优点,提高了负荷预测精度,具有一定的有效性和适用性.

Study on Identification Method of Anomalous Electric Load Data

In order to meet the need of load forecasting precision and improve the accuracy of medium-term load forecasting, according to the characteristics of longitudinal and cross similarity of the load forecasting curve of the year, and aim at the present status of identification and correction of anomalous data, the algorithm based on mathematical statistics and three-point fiat principle is presented to solve the problems of large workload, too much man-made interference, misidentifying and failing to identify the anomalous data. At last, an application case of Gansu power grid is given to prove that this method has the advantage of simpleness, practicality, small workload and little man-made interference and shows that the method is effective and practical and the precision of load forecasting is improved.