Suzhou Electric Appliance Research Institute
期刊號(hào)： CN32-1800/TM| ISSN1007-3175

Article retrieval

文章檢索

首頁(yè) >> 文章檢索 >> 往年索引

基于相似日和CNN-LSTM的短期負(fù)荷預(yù)測(cè)

來(lái)源：電工電氣發(fā)布時(shí)間：2022-08-29 14:29 瀏覽次數(shù)：358

基于相似日和CNN-LSTM的短期負(fù)荷預(yù)測(cè)

童占北1，鐘建偉1，李禎維2，吳建軍2，李家俊2
(1 湖北民族大學(xué) 智能科學(xué)與工程學(xué)院，湖北 恩施 445000；
2 國(guó)網(wǎng)湖北省電力有限公司恩施供電公司，湖北 恩施 445000)
 
    摘 要：為充分發(fā)掘歷史信息，解決氣象數(shù)據(jù)不足影響預(yù)測(cè)精度的問(wèn)題，采用灰色關(guān)聯(lián)分析 (GRA) 選取天氣相似日和 CNN-LSTM 混合神經(jīng)網(wǎng)絡(luò)的方法來(lái)預(yù)測(cè)電力負(fù)荷。利用 GRA 計(jì)算每日各氣象因素與日總負(fù)荷的灰色關(guān)聯(lián)度，再計(jì)算各日與典型日的相同氣象因素之間的歐氏距離，將各氣象因素的歐氏距離分別乘以對(duì)應(yīng)因素的關(guān)聯(lián)度，并將同一天的結(jié)果累加，得到一個(gè)綜合得分。選取待預(yù)測(cè)日之前分?jǐn)?shù)最低的 5 天作為相似日，將相似日各時(shí)刻的負(fù)荷數(shù)據(jù)輸入 CNN-LSTM 網(wǎng)絡(luò)中，預(yù)測(cè)出待預(yù)測(cè)日的負(fù)荷，通過(guò)與其他模型對(duì)比，驗(yàn)證了該方法的有效性。
    關(guān)鍵詞： 灰色關(guān)聯(lián)分析；相似日；CNN-LSTM 混合神經(jīng)網(wǎng)絡(luò)；短期負(fù)荷預(yù)測(cè)
    中圖分類號(hào)：TM715     文獻(xiàn)標(biāo)識(shí)碼：A     文章編號(hào)：1007-3175(2022)08-0017-06
 
Short-Term Load Forecasting Based on Grey Relational
Analysis and CNN-LSTM
 
TONG Zhan-bei1, ZHONG Jian-wei1, LI Zhen-wei2, WU Jian-jun2, LI Jia-jun2
（1 College of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China;
2 Enshi Power Supply Company, State Grid Hubei Electric Power Co., Ltd, Enshi 445000, China）
 
    Abstract: This paper used grey relational analysis(GRA) to select days with similar weather conditions and explore more historical information.In addition, it employed the CNN-LSTM hybrid neural network method to predict power load and solve the problem of insufficient meteorological data affecting prediction accuracy. This research used GRA to calculate the grey relational grade between daily meteorological factors and overall load. In addition, it computed the Euclidean distance of the same meteorological factors between each day and the typical day. The Euclidean distance of each meteorological factor was multiplied by the relevancy of corresponding factors. The accumulation of the calculation results in the same day could obtain an overall score. This study took five days with the lowest score before predicted days as the similar days. It inputted load data into the CNN-LSTM network to forecast the load of prediction days. Compared with other models, the effectiveness of this method is verified.
    Key words: grey relational analysis; similar day; CNN-LSTM hybrid neural network; short-term load forecasting
 
參考文獻(xiàn)
[1] 梁智，孫國(guó)強(qiáng)，李虎成. 基于 VMD 與 PSO 優(yōu)化深度信念網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)[J] . 電網(wǎng)技術(shù)，2018，42(2)：598-606.
[2] KIN J, CHO S, KO K, et al.Short-Term Electric Load Prediction Using Multiple Linear Regression Method[C]//2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids，2018.
[3] LI Hong, ZHAO Yang, ZHANG Zizi, et al.Shortterm load forecasting based on the grid method and the time series fuzzy load forecasting method[C]//International Conference on Renewable Power Generation，2015.
[4] 陳磊，張青云，向曉，等. 改進(jìn)灰色預(yù)測(cè)模型在電力負(fù)荷預(yù)測(cè)中的應(yīng)用[J] . 河北電力技術(shù)，2021，40(6)：27-30.
[5] SHARMA S, MAJUMDAR A, ELVIRA V, et al.Blind Kalman Filtering for Short-Term Load Forecasting[J].IEEE Transactions on Power Systems，2020，35(6)：4916-4919.
[6] 譚風(fēng)雷，張軍，馬宏忠. 基于趨勢(shì)變化分段的電力負(fù)荷組合預(yù)測(cè)方法[J] . 華北電力大學(xué)學(xué)報(bào)，2020，47(2)：17-24.
[7] YANG Wangwang, SHI Jing, LI Shujian, et al.A combined deep learning load forecasting model of single household resident user considering multi-time scale electricity consumption behavior[J].Applied Energy，2022，307(C) ：S0306261921014665.
[8] JALALI S M J, AHMADIAN S, KHOSRAVI A, et al.A Novel Evolutionary-Based Deep Convolutional Neural Network Model for Intelligent Load Forecasting[J].IEEE Transactions on Industrial Informatics，2021，PP(99) ：1.
[9] ZHU Fuyun, WU Guoqing.Load Forecasting of the Power System: An Investigation Based on the Method of Random Forest Regression[J].Energy Engineering，2021，118(6) ：1703-1712.
[10] LI Gen, LI Yunhua, ROOZITALAB Farzad.Midterm Load Forecasting: A Multistep Approach Based on Phase Space Reconstruction and Support Vector Machine[J].IEEE Systems Journal，2020，14(4) ：4967-4977.
[11] 鄧春紅，王蒙. 基于相似日和灰色理論的短期電力負(fù)荷預(yù)測(cè)研究[J] . 重慶工商大學(xué)學(xué)報(bào)( 自然科學(xué)版)，2017，34(3)：93-97.
[12] 王瑞，孫憶楓，逯靜. 基于相似日和 RBF 神經(jīng)網(wǎng)絡(luò)的短期電力負(fù)荷預(yù)測(cè)[J] . 制造業(yè)自動(dòng)化，2021，43(4)：24-29.
[13] JANKOVI Z, SELAKOV A, BEKUT D, et al.Day similarity metric model for short-term load forecasting supported by PSO and artificial neural network[J].Electrical Engineering，2021，103(1) ：2973-2988.
[14] DING Jianmin, YUE Yunli, CHEN Jianhua, et al.Analysis of Factors Affecting Power Load Characteristics Based on Grey Relational Analysis Model [C]//2019 International Conference on Sensing , Diagnostics ,Prognostics, and Control(SDPC)，2020.
[15] 劉亞琿，趙倩. 基于聚類經(jīng)驗(yàn)?zāi)B(tài)分解的 CNN-LSTM 超短期電力負(fù)荷預(yù)測(cè)[J] . 電網(wǎng)技術(shù)，2021，45(11)：4444-4451.
[16] RAFI S H, MASOOD Nahid-Al, DEEBA S R, et al.A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network[J].IEEE Access，2021，9：32436-32448.
[17] 劉可真，阮俊梟，趙現(xiàn)平，等. 基于麻雀搜索優(yōu)化的 Attention-GRU 短期負(fù)荷預(yù)測(cè)方法[J]. 電力系統(tǒng)及其自動(dòng)化學(xué)報(bào)，2022，34(4) ：99-106.