[1]陆嘉华,梅 飞,杨 赛,等.基于特征选择和组合预测模型的负荷短期预测方法[J].南京师大学报(自然科学版),2023,46(04):114-124.[doi:10.3969/j.issn.1001-4616.2023.04.015]
　Lu Jiahua,Mei Fei,Yang Sai,et al.Short-term Load Forecasting Method Based on Feature Selection and Combination Forecasting Model[J].Journal of Nanjing Normal University(Natural Science Edition),2023,46(04):114-124.[doi:10.3969/j.issn.1001-4616.2023.04.015]
点击复制

基于特征选择和组合预测模型的负荷短期预测方法()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
第46卷
期数:
2023年04期
页码:
114-124
栏目:
计算机科学与技术
出版日期:
2023-12-15

文章信息/Info

Title:
Short-term Load Forecasting Method Based on Feature Selection and Combination Forecasting Model
文章编号:
1001-4616(2023)04-0114-11
作者:
陆嘉华; 梅 飞; 杨 赛; 唐 瑜; 华昊辰
(河海大学能源与电气学院,江苏 南京 211100)
Author(s):
Lu Jiahua; Mei Fei; Yang Sai; Tang Yu; Hua Haochen
(College of Energy and Electrical Engineering,Hohai University,Nanjing 211100,China)
关键词:
特征选择; 回归模型; 时间序列模型; 组合预测模型
Keywords:
feature selection;  regression model;  time series model;  combination forecasting model
分类号:
TM715; TP183
DOI:
10.3969/j.issn.1001-4616.2023.04.015
文献标志码:
A
摘要:
提高配电网母线负荷短期预测准确性对配电网调度运行具有重要意义,随着配电网中气象敏感负荷数量的不断增加,气象因素带来的负荷波动性对预测精度的影响也随之增大. 针对传统负荷预测建模中的气象特征选择问题,基于特征的最大相关性、最小冗余性和最大协同作用提出了一种最优气象特征选择流程. 在此之上,基于不同特征的不同时间维度提出了回归模型与时间序列模型相结合的短期负荷组合预测模型. 采用回归模型对未来的日期时间特征、气象特征进行拟合,以卷积神经网络-双向门控循环单元构建时间序列模型描述历史负荷、历史气象时间序列中的时序特征和气象因素的累积效应. 算例分析证明了本文特征选择方法比传统特征选择方法有更低的预测误差,且组合预测模型相比于传统回归、时序模型的预测准确性提升显著.
Abstract:
Improving the accuracy of short-term forecasting of bus load in a distribution network is crucial to its dispatch and operation. With the increasing number of weather-sensitive loads in the distribution network,the influence of load fluctuation caused by meteorological factors on forecasting accuracy also increases. Aiming at the problem of meteorological feature selection in traditional load forecasting modeling,an optimal meteorological feature selection process was proposed based on the maximum correlation,minimum redundancy,and maximum synergy of features. On this basis,based on different time dimensions of different characteristics,a short-term load combination forecasting model combining regression model and time series model is proposed. The model uses the regression model to fit the future date-time characteristics and meteorological characteristics and uses the convolutional neural network and bidirectional gated recurrent unit to construct a time series model to describe the time series characteristics of the historical load and meteorological time series and the cumulative effect of meteorological factors. Example analysis proves that the feature selection method has a lower forecast error than the traditional feature selection methods. Compared with the traditional regression and time-series model,the forecasting accuracy of combination forecasting model is improved significantly.

参考文献/References:

[1]郭创新,刘祝平,冯斌,等. 新型电力系统风险评估研究现状及展望[J]. 高电压技术,2022,48(9):3394-3404.
[2]徐潇源,王晗,严正,等. 能源转型背景下电力系统不确定性及应对方法综述[J]. 电力系统自动化,2021,45(16):2-13.
[3]张东霞,苗新,刘丽平,等. 智能电网大数据技术发展研究[J]. 中国电机工程学报,2015,35(1):2-12.
[4]李鹏,何帅,韩鹏飞,等. 基于长短期记忆的实时电价条件下智能电网短期负荷预测[J]. 电网技术,2018,42(12):4045-4052.
[5]陆继翔,张琪培,杨志宏,等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化,2019,43(8):131-137.
[6]庞昊,高金峰,杜耀恒. 基于时间卷积网络分位数回归的短期负荷概率密度预测方法[J]. 电网技术,2020,44(4):1343-1350.
[7]蔡舒平,闫静,刘国海,等. 基于Fisher信息和在线SVR的智能电网气象敏感负荷预测动态建模技术[J]. 中国电机工程学报,2020,40(11):3441-3451.
[8]王继东,杜冲. 基于Attention-BiLSTM神经网络和气象数据修正的短期负荷预测模型[J]. 电力自动化设备,2022,42(4):172-177,224.
[9]ZHANG G Q,GUO J F. A novel method for hourly electricity demand forecasting[J]. IEEE transactions on power systems,2020,35(2):1351-1363.
[10]孙辉,杨帆,高正男,等. 考虑特征重要性值波动的MI-BILSTM短期负荷预测[J]. 电力系统自动化,2022,46(8):95-103.
[11]LI C,LI G J,WANG K Y,et al. A multi-energy load forecasting method based on parallel architecture CNN-GRU and transfer learning for data deficient integrated energy systems[J]. Energy,2022,259:124967.
[12]HU Z Y,BAO Y K,XIONG T,et al. Hybrid filter-wrapper feature selection for short-term load forecasting[J]. Engineering applications of artificial intelligence,2014,40:17-27.
[13]WANG Y,GAN D,ZHANG N,et al. Feature selection for probabilistic load forecasting via sparse penalized quantile regression[J]. Modern power system and clean energy,2019,7:1200-1209.
[14]郭玲,徐青山,郑乐. 基于TCN-GRU模型的短期负荷预测方法[J]. 电力工程技术,2021,40(3):66-71.
[15]任建吉,位慧慧,走卓霖,等. 基于CNN-BiLSTM-Attention的超短期电力负荷预测[J]. 电力系统保护与控制,2022,50(8):108-116.
[16]JIANG L J,WANG X L,LI W,et al. Hybrid multitask multi-information fusion deep learning for household short-term load forecasting[J]. IEEE transactions on smart grid,2021,12(6):5362-5372.
[17]AFRASIABI M,MOHAMMADI M,RASTEGAR M,et al,Deep-based conditional probability density function forecasting of residential loads[J]. IEEE transactions on smart grid,2020,11(4):3646-3657.
[18]杨海柱,田馥铭,张鹏,等. 基于CEEMD-FE和AOA-LSSVM的短期电力负荷预测[J]. 电力系统保护与控制,2022,50(13):126-133.
[19]ZHANG C,LI R. A novel closed-loop clustering algorithm for hierarchical load forecasting[J]. IEEE transactions on smart grid,2021,12(1):432-441.
[20]刘亚珲,赵倩. 基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测[J]. 电网技术,2021,45(11):4444-4451.
[21]董新伟,卜智龙,陈鸣慧,等. 基于VMD-LSTMQR的滚动母线负荷区间预测[J]. 电力工程技术,2021,40(6):9-17.
[22]ABEDINIA O,AMJADY N,ZAREIPOUR H. A new feature selection technique for load and price forecast of electrical power systems[J]. IEEE transactions on power systems,2017,32(1):62-74.
[23]李滨,陆明珍. 考虑实时气象耦合作用的地区电网短期负荷预测建模[J]. 电力系统自动化,2020,44(17):60-68.
[24]KO M S,KO L,HUR K. Feedforward error learning deep neural networks for multivariate deterministic power forecasting[J]. IEEE transactions on industrial informatics,2022,18(9):6214-6223.

相似文献/References:

[1]徐海峰,张 雁,刘 江,等.基于变异系数和最大特征树的特征选择方法[J].南京师大学报(自然科学版),2021,44(01):111.[doi:10.3969/j.issn.1001-4616.2021.01.016]
　Xu Haifeng,Zhang Yan,Liu Jiang,et al.Feature Selection Method Based on Coefficient ofVariation and Maximum Feature Tree[J].Journal of Nanjing Normal University(Natural Science Edition),2021,44(04):111.[doi:10.3969/j.issn.1001-4616.2021.01.016]
[2]吉珊珊.基于神经网络树和人工蜂群优化的数据聚类[J].南京师大学报(自然科学版),2021,44(01):119.[doi:10.3969/j.issn.1001-4616.2021.01.017]
　Ji Shanshan.Neuron Network Tree and Artificial Bee Colony OptimizationBased Data Clustering Algorithm[J].Journal of Nanjing Normal University(Natural Science Edition),2021,44(04):119.[doi:10.3969/j.issn.1001-4616.2021.01.017]
[3]孙 林,施恩惠,司珊珊,等.基于AP聚类和互信息的弱标记特征选择方法[J].南京师大学报(自然科学版),2022,45(03):108.[doi:10.3969/j.issn.1001-4616.2022.03.014]
　Sun Lin,Shi Enhui,Si Shanshan,et al.Weak Label Feature Selection Method Based on AP Clustering and Mutual Information[J].Journal of Nanjing Normal University(Natural Science Edition),2022,45(04):108.[doi:10.3969/j.issn.1001-4616.2022.03.014]
[4]穆晓霞,郑李婧.基于F-score和二进制灰狼优化的肿瘤基因选择方法[J].南京师大学报(自然科学版),2024,(01):111.[doi:10.3969/j.issn.1001-4616.2024.01.013]
　Mu Xiaoxia,Zheng Lijing.Tumor Gene Selection Based on F-score and Binary Grey Wolf Optimization[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(04):111.[doi:10.3969/j.issn.1001-4616.2024.01.013]

备注/Memo

备注/Memo:
收稿日期:2023-02-03.
基金项目:国家重点研发计划项目(2022YFE0140600)、江苏省重点研发计划项目(BE2020027).
通讯作者:梅飞,博士,讲师,研究方向:电气设备在线监测与故障诊断、配电网故障定位. E-mail:meifei@hhu.edu.cn
更新日期/Last Update: 2023-12-15