半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
能源互联环境下考虑需求响应的区域电网短期负荷预测
作者:
作者单位:

1.智能电网教育部重点实验室(天津大学),天津市 300072;2.贵州电网有限责任公司电力科学研究院,贵州省贵阳市 550007;3.中国电力科学研究院有限公司,北京市 100192;4.国网天津市电力公司,天津市 300010

摘要:

在区域能源互联系统中,需求响应改变了电力用户的常规用电习惯,增加了预测环境的不确定因素。针对这种特定的环境,提出一种考虑需求响应的区域电网短期负荷预测方法来满足企业对预测精度的需求,该方法通过依次构建数据处理模型、负荷预测模型和误差预测模型实现了预测精度的提升。更具体地,针对历史数据样本集,采用灰色关联分析法处理气象数据以获取输入预测模型的相似日特征变量;针对电力负荷预测,建立了长短期记忆网络模型,利用其特殊的门结构选择性地控制输入变量对模型参数的影响,从而改善了模型的预测性能;针对误差数据样本集,采用了动态模式分解技术来挖掘误差数据的潜在价值,并利用其数据驱动特性刻画了误差时间序列的趋势变化特征,实现了良好的误差预测。最后,结合实际的电网数据,对比验证了所提方法的有效性和优越性。

关键词:

基金项目:

国家重点研发计划资助项目(2016YFB0901104)。

通信作者:

作者简介:

李闯(1993—),男,硕士研究生,主要研究方向:电力负荷预测及其应用、需求侧管理。E-mail:lchuangsky@tju.edu.cn
孔祥玉(1978—),男,通信作者,博士,副教授,博士生导师,主要研究方向:电力系统分析、智能配用电技术。E-mail:eekongxy@tju.edu.cn
朱石剑(1993—),男,硕士研究生,主要研究方向:家庭能量管理能效评估、智能用电。E-mail:353388947@qq.com


Short-term Load Forecasting of Regional Power Grid Considering Demand Response in Energy Interconnection Environment
Author:
Affiliation:

1.Key Laboratory of the Ministry of Education on Smart Power Grids (Tianjin University), Tianjin 300072, China;2.Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550007, China;3.China Electric Power Research Institute Co., Ltd., Beijing 100192, China;4.State Grid Tianjin Electric Power Company, Tianjin 300010, China

Abstract:

In the regional energy interconnection system, the demand response has changed the conventional power consumption habits of power users, and increased the uncertainties in forecasting environment. In view of this specific environment, this paper proposes a short-term load forecasting method of regional power grids considering demand response to meet the demand of enterprises for forecasting accuracy. This method improves the forecasting accuracy by constructing data processing model, load forecasting model and error forecasting model in turn. More specifically, for the historical data sample set, the gray relation analysis method is used to process the meteorological data to obtain the similar daily characteristic variables of the input forecasting model. For the power load forecasting, a long short-term memory network model is established. Its special gate structure is used to selectively control the influence of input variables on model parameters, and the forecasting performance of the model is improved. For the error data sample set, the dynamic modal decomposition technology is used to mine the potential value of the error data. Its data-driven characteristics are used to characterize the variation trend characteristics of the error series, and a good error prediction is achieved. Finally, combined with the actual power grid data, the effectiveness and superiority of the proposed method are verified.

Keywords:

Foundation:
This work is supported by National Key R&D Program of China (No. 2016YFB0901104).
引用本文
[1]李闯,孔祥玉,朱石剑,等.能源互联环境下考虑需求响应的区域电网短期负荷预测[J].电力系统自动化,2021,45(1):71-78. DOI:10.7500/AEPS20200428001.
LI Chuang, KONG Xiangyu, ZHU Shijian, et al. Short-term Load Forecasting of Regional Power Grid Considering Demand Response in Energy Interconnection Environment[J]. Automation of Electric Power Systems, 2021, 45(1):71-78. DOI:10.7500/AEPS20200428001.
复制
分享
历史
  • 收稿日期:2020-04-28
  • 最后修改日期:2020-08-26
  • 录用日期:
  • 在线发布日期: 2021-01-05
  • 出版日期:
相关附件