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

SUBSCRIPTION MANAGEMENT

發(fā)行征訂

首頁 >> 發(fā)行征訂 >> 征訂方式

基于改進的SSA優(yōu)化SVR的某工業(yè)園區(qū)短期負荷預(yù)測

來源:電工電氣發(fā)布時間:2024-12-02 11:02瀏覽次數(shù):32

基于改進的SSA優(yōu)化SVR的某工業(yè)園區(qū)短期負荷預(yù)測

譚學(xué)彪1,龍邦燎1,黃干1,李江娥1,田驥1,王海文2,鐘建偉2
(1 國網(wǎng)湖北省電力有限公司恩施供電公司,湖北 恩施 445000;
  2 湖北民族大學(xué) 智能科學(xué)與工程學(xué)院,湖北 恩施 445000)
 
    摘 要:為實現(xiàn)不規(guī)律、波動性大、不確定性的電力負荷數(shù)據(jù)高精度預(yù)測,提出了一種使用小波包分解(WPD)與麻雀搜索算法(SSA)來優(yōu)化支持向量回歸(SVR)的短期負荷預(yù)測方案。該方案使用 WPD 將原始負荷序列分解成多個各異的小波動分量,將分解后的各組數(shù)據(jù)分別輸入 SSA 優(yōu)化后的 SVM 模型,并將得到的多個各異的小波動分量分別經(jīng)模型預(yù)測出的結(jié)果進行相加得到最后取得的預(yù)測結(jié)果。結(jié)果表明:該方案能較好擬合整個測試集上的實際預(yù)測點位,適合于電力系統(tǒng)短期負荷的準確預(yù)測,證實了該模型的有效性和優(yōu)越性。
    關(guān)鍵詞: 短期電力負荷預(yù)測;小波包分解;麻雀搜索算法;支持向量機
    中圖分類號:TM714     文獻標識碼:A     文章編號:1007-3175(2024)11-0015-09
 
Short-Term Power Load Forecasting for an Industrial Park Based on
Improved SSA and Optimized SVR
 
TAN Xue-biao1, LONG Bang-liao1, HUANG Gan1, LI Jiang-e1, TIAN Ji1, WANG Hai-wen2, ZHONG Jian-wei2
(1 Enshi Powr Supply Company of State Grid Hubei Electric Power Co., Ltd, Enshi 445000, China;
2 College of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China)
 
    Abstract: To achieve high-precision prediction of irregular, highly volatile, and uncertain power load data, a short-term load forecasting scheme with using wavelet packet decomposition (WPD) and sparrow search algorithm (SSA) is proposed to optimize support vector regression(SVR). Firstly, WPD is used to decompose the original load into multiple distinct small fluctuation components. Then, each group of decomposed data is inputted into the SSA optimized SVM model. Finally, the obtained multiple distinct small fluctuation components are added up to the predicted results of the model to obtain the final prediction result. The results show that this scheme can well fit the actual predicted points on the entire test set, and is suitable for accurate short-term load prediction of the power system, confirming the effectiveness and superiority of the model.
    Key words: short-term power load forecasting; wavelet packet decomposition; sparrow search algorithm; support vector machine
 
參考文獻
[1] 陶娟,鄒紅波,周冬. 基于提升人工神經(jīng)網(wǎng)絡(luò)的短期負荷預(yù)測模型[J]. 電工材料,2021(2) :53-56.
[2] ZHANG N, NIU M, WAN F, et al.Hazard prediction of water inrush in water-rich tunnels based on random forest algorithm[J].Applied Sciences,2024,14(2) :867.
[3] DONG J, WANG Z, WU J, et al.A novel runoff prediction model based on support vector machine and gate recurrent unit with secondary mode decomposition[J].Water Resources Management,2024,38(5) :1655-1674.
[4] 張曉燕,林鴻才,黃波,等. 基于最優(yōu)交集相似日的 EMD-SVR 短期負荷預(yù)測[J]. 海峽科學(xué),2023(7) :30-35.
[5] 邵必林,莊雪莉,曾卉玢. 基于 LSTM-XGBoost 和多模型算法的短期負荷預(yù)測[J] . 計算機時代,2023(12) :49-54.
[6] 孟德乾,袁建平,吳月超. 基于 VMD-IWOA-KELM 的短期電力負荷預(yù)測研究[J] . 科技創(chuàng)新與應(yīng)用,2023,13(33) :136-139.
[7] 余志成,孫皓月,張碧寧. 基于 ARIMA 和 SVR 的短期電力負荷預(yù)測[J] . 河北建筑工程學(xué)院學(xué)報,2023,41(3) :189-196.
[8] 周思明,段金長,李穎杰,等. 一種改進的 SVM 短期電力系統(tǒng)負荷預(yù)測方法[J] . 沈陽工業(yè)大學(xué)學(xué)報,2023,45(6) :661-665.
[9] SINA A, KAUR D.Short Term Load Forecasting Model Based on Kernel-Support Vector Regression with Social Spider Optimization Algorithm[J].Journal of Electrical Engineering and Technology,2020,15(1) :393-402.
[10] FIGUEIRO C I, ABAIDE R A, NETO K N, et al.Bottom-Up Short-Term Load Forecasting Considering Macro-Region and Weighting by Meteorological Region [J] . Energies,2023,16(19) :6857.
[11] VRABLECOVA P, EZZEDDINE A B, ROZINAJOVA V, et al.Smart grid load forecasting using online support vector regression[J].Computers and Electrical Engineering,2018,65 :102-117.
[12] 樊浩研,劉楊,李璟. 基于 PCA-WPD 優(yōu)化的電流互感器故障檢測方法研究[J]. 粘接,2024,51(5) :193-196.
[13] 冷騰飛,蘇圣超. 基于子區(qū)域切分與 SSA-XGBoost 的室內(nèi)定位方法[J] . 傳感技術(shù)學(xué)報,2024,37(5) :833-840.