电气工程学报 ›› 2023, Vol. 18 ›› Issue (4): 320-330.doi: 10.11985/2023.04.034

• 新能源发电与电能存储 • 上一篇    下一篇

扫码分享

基于误差补偿LSTM-GRU的综合能源系统多元负荷预测*

耿阳1(), 王海龙2(), 张楠3(), 付明2()   

  1. 1.国网江苏省电力有限公司扬中市供电分公司 扬中 212200
    2.国电南瑞科技股份有限公司 南京 211106
    3.国网江苏省电力有限公司镇江供电分公司 镇江 212000
  • 收稿日期:2022-11-30 修回日期:2023-08-30 出版日期:2023-12-25 发布日期:2024-01-12
  • 通讯作者: 耿阳,男,1990年生,硕士,工程师。主要研究方向为综合能源规划、综合能源服务等。E-mail:gy3742@qq.com
  • 作者简介:王海龙,男,1982年生,硕士,高级工程师。主要研究方向为综合能源服务、电网自动化、新能源接入与运行控制等。E-mail:whllnhc@126.com
    张楠,女,1992年生,工程师。主要研究方向为综合能源服务、电网规划等。E-mail:zhangn6@js.sgcc.com.cn
    付明,男,1986年生,硕士,高级工程师。主要研究方向为新能源接入与运行控制、综合能源服务等。E-mail:fuming@sgepri.sgcc.com.cn
  • 基金资助:
    *国家重点研发计划资助项目(2018YFB0905000)

Multivariate Load Forecasting for Integrated Energy Systems Based on Error-compensated LSTM-GRU

GENG Yang1(), WANG Hailong2(), ZHANG Nan3(), FU Ming2()   

  1. 1. Yangzhong Power Supply Branch, State Grid Jiangsu Electric Power Co., Ltd., Yangzhong 212200
    2. State Grid NARI Technology Co., Ltd., Nanjing 211106
    3. Zhenjiang Power Supply Branch Company, State Grid Jiangsu Electric Power Co., Ltd., Zhenjiang 212000
  • Received:2022-11-30 Revised:2023-08-30 Online:2023-12-25 Published:2024-01-12

摘要:

为实现对综合能源系统的日前调度,需要对综合能源系统的电负荷、热负荷、冷负荷进行联合预测。针对综合能源系统多元负荷的复杂影响因素,首先,通过灰色关联度分析筛选出对多元负荷影响较大的影响因素;随后,采用传统长短期记忆(Long short-term memory,LSTM)神经网络对负荷进行预测;其次,通过门控循环单元(Gated recurrent unit,GRU)对预测误差进行训练,得到误差补偿值;最后,通过负荷预测值与误差预测值的重构,获得更精确的负荷预测值。通过实例对比误差补偿对预测精度的影响,验证了误差补偿模型的可行性,将所提预测方法与其他两种预测模型进行比较,该方法可以提高多元负荷预测的精确度,证明了该方法的优异性。

关键词: 综合能源, 负荷预测, 长短期记忆神经网络, 门控循环单元, 误差补偿

Abstract:

To facilitate the dispatch of energy systems, joint forecasting of electric, thermal, and cooling loads of integrated energy systems is required. Aiming at the complex influencing factors of multi-load in integrated energy systems, firstly, the factors that have a greater impact on the multi-load load are screened out through grey correlation analysis. The load is then predicted using a traditional long short-term memory(LSTM) neural network. Secondly, the prediction error is trained by the gated recurrent unit(GRU) to obtain the error compensation value. Finally, through the reconstruction of the load forecast value and the error forecast value, a more accurate load forecast value is obtained. The feasibility of the error compensation model is verified by comparing the effect of error compensation on prediction accuracy through examples, and the superiority of the proposed prediction method is demonstrated by comparing it with other two prediction models, which can improve the accuracy of multivariate load prediction.

Key words: Integrated energy, load forecasting, long short-term memory neural network, gated recurrent units, error compensation

中图分类号: