###
DOI:
电力大数据:2019,22(12):-
←前一篇   |   后一篇→
本文二维码信息
应对海量数据的超短期负荷预测在实时电力市场的应用研究
李家璐, 何剑军, 张坤, 刘敬诚, 吕勃翰, 张勇, 辛阔
(中国南方电网有限责任公司)
Feasibility Analysis of Ultra-Short Term Load Forecasting Adapting To Actual-Time Electricity Market considering the Mass Data
LI Jialu, HE Jianjun, ZHANG Kun, LIU Jingcheng, LV Bohan, ZHANG Yong, XIN Kuo
(China Southern Power Grid,Guangzhou,Guangdong)
摘要
图/表
参考文献
相似文献
本文已被:浏览 419次   下载 7
投稿时间:2019-07-09    修订日期:2019-09-04
中文摘要: 在开展实时现货市场和辅助服务市场的过程中,负荷预测的精度和速度成为影响各主体报价结果的瓶颈,负荷预测越准确,越有利于保障各市场主体报价的公平性和经济性。本文为解决该问题,选择南方电网某区域的历史负荷作为研究对象,通过对其日负荷曲线进行分析,考虑将工作日和非工作日的海量负荷数据进行了筛选和预处理,并针对各自的负荷特性进行了分析,确定了分别预测建模的预测路线,同时本文将当前常用的几种预测算法进行了比较,通过对比优缺点,针对超短期负荷预测的预测时间短、预测速度高的要求,最终选择负荷求导法作为超短期负荷预测的数学模型。最后通过对南网某省的实际负荷进行了算例验证,结果表明该方法具有预测速度快,预测精度高,适应度高,技术系统占用率低的特点。
Abstract:During the progress of Electricity Market and Ancillary Services Market, the precision and speed of load forecastingthe are the bottleneck of the quotation scheme,which is the more accurate ,the better.In order to solve this problem,the history load data is introduced as the sample ,with the analysis of daily load curve and processing scheme of working and non-working days, a new kind method of Ultra-Short Term Load Forecasting is introduced to improve the progress of the Spot Market and Ancillary Services Market. Based on the load characteristics of CSG, and the method of the current ultra-short term fast load forecasting, the load derivation method is introduced to improve the current model. The example shows that the method has the advantages of fast prediction , high prediction accuracy and low resource usage.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本: