基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测

发布时间：2019-02-13 01:49

【摘要】：针对气象变化时负荷曲线预测精度低、预测模型不能完全适应气象变化的情况,提出了一种基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测方法。提出了完全气象因子序列的概念,建立气象粒化集;采用空间多元回归及滞后模型结合多策略灵敏度分析法,建立了针对复杂气象条件下的极值预测模型;基于改进的K-means聚类分析法查找并获取气象特征日,计算初步预测曲线,主动判断预测曲线畸变概率并进行优化修正,得到最佳预测日负荷曲线;利用动态数据流对模型参数进行更新,实现精细化预测。最后采用该方法对我国南方某地区全年负荷曲线进行预测,验证了模型在多种气象条件下的预测准确性,尤其适用于短期内气象存在复杂变化的情形。
[Abstract]:A short-term daily load curve forecasting method based on fuzzy information granulation and multi-strategy sensitivity is proposed in view of the low forecasting accuracy of the load curve and the inability of the forecasting model to adapt to the meteorological change. In this paper, the concept of complete meteorological factor series is put forward, and the meteorological granulation set is established, and the extreme value prediction model for complex meteorological conditions is established by using spatial multivariate regression and lag model combined with multi-strategy sensitivity analysis. Based on the improved K-means clustering analysis method, the meteorological feature days are found and obtained, the preliminary prediction curve is calculated, the distortion probability of the prediction curve is judged and optimized, and the optimal daily load forecasting curve is obtained. The dynamic data stream is used to update the model parameters to realize fine prediction. Finally, this method is used to predict the annual load curve in a certain area of southern China, which verifies the prediction accuracy of the model under various meteorological conditions, especially in the case of complex meteorological changes in the short term.
【作者单位】：广西电力系统最优化与节能技术重点实验室(广西大学);广西电网公司电力调度控制中心;
【基金】：国家自然科学基金(51541707) 国家重点基础研究发展计划(973计划)(2013CB228205)资助项目
【分类号】：TM715

【相似文献】