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

Article retrieval

文章檢索

首頁 >> 文章檢索 >> 往年索引

基于NBA-SVR的日最大負荷預測

來源:電工電氣發(fā)布時間:2021-01-25 08:25 瀏覽次數(shù):809

基于NBA-SVR的日最大負荷預測

成貴學1,陳昱吉1,趙晉斌2,費敏銳3
(1 上海電力大學 計算機科學與技術(shù)學院,上海 200090;2 上海電力大學 電氣工程學院,上海 200090;
3 上海大學 機電工程與自動化學院,上海 200072)
 
摘 要:為進一步提高日最大負荷預測精度,提出一種基于新型蝙蝠算法和支持向量回歸的日最大負荷預測方法,引入對回波中多普勒效應進行自適應補償和棲息地選擇的新型蝙蝠算法優(yōu)化選取支持向量回歸參數(shù),采用電工杯數(shù)學建模競賽提供的數(shù)據(jù)訓練并建立NBA-SVR模型進行日最大負荷預測,結(jié)果表明NBA-SVR 模型在預測精度上比BPNN、PSO-SVR、WOA-SVR模型有顯著的提升。
    關(guān)鍵詞:日最大負荷預測;新型蝙蝠算法;支持向量回歸;參數(shù)優(yōu)化
    中圖分類號:TM715;TP181     文獻標識碼:A     文章編號:1007-3175(2021)01-0011-06
 
Daily Maximum Load Forecasting Based on NBA-SVR
 
CHENG Gui-xue1, CHEN Yu-ji1, ZHAO Jin-bin2, FEI Min-rui3
(1 School of Computer Science and Technology, Shanghai University of Electric Power,Shanghai 200090, China;
2 School of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China;
3 School of Mechanical Engineering and Automation, Shanghai University, Shanghai 200072, China)
 
   Abstract: In order to further improve the accuracy of daily maximum load forecasting, this paper proposed a new daily maximum load forecasting method based on novel bat algorithm optimization and support vector regression. It introduced the adaptive compensation of Doppler effect in the echo and new bat algorithm for habitat selection to optimize the selection of support vector regression parameters. The data provided by the Electrician Mathematical Contest in Modeling are used to train and establish the NBA-SVR model to perform daily maximum load forecasting. The results showed that the NBA-SVR model has better prediction accuracy than the back propagation neural network, PSO-SVR, and WOA-SVR.
    Key words: daily maximum load forecasting; novel bat algorithm; support vector regression; parameters optimization
 
參考文獻
[1] 康重慶,夏清,劉梅,等. 電力系統(tǒng)負荷預測[M].2版. 北京:中國電力出版社,2017.
[2] 馬立新,李淵. 日最大負荷特性分析及預測方法[J].電力系統(tǒng)及其自動化學報,2014,26(10):31-34.
[3] 劉曉娟,方建安. 基于雙修正因子的模糊時間序列日最大負荷預測[J] . 中國電力,2013,46(10):115-118.
[4] 崔和瑞,彭旭. 基于ARIMA 模型的夏季短期電力負荷預測[J]. 電力系統(tǒng)保護與控制,2015,43(4):108-114.
[5] 任海軍,張曉星,肖波,等. 基于概念格的神經(jīng)網(wǎng)絡日最大負荷預測輸入?yún)?shù)選擇[J] . 吉林大學學報( 理學版),2011,49(1):87-92.
[6] 嵇靈,牛東曉,吳煥苗. 基于貝葉斯框架和回聲狀態(tài)網(wǎng)絡的日最大負荷預測研究[J] . 電網(wǎng)技術(shù),2012,36(11):82-86.
[7] 李筍,王超,張桂林,等. 基于支持向量回歸的短期負荷預測[J] . 山東大學學報( 工學版),2017,47(6):52-56.
[8] 李素,袁志高,王聰,等. 群智能算法優(yōu)化支持向量機參數(shù)綜述[J]. 智能系統(tǒng)學報,2018,13(1):70-84.
[9] JIE Z, SIYUAN W.Thermal load forecasting basedon PSO - SVR [C] / /2018 IEEE 4th International Conference on Computer and Communications(ICCC),2018:2676-2680.
[10] TAO Y, YAN H, GAO H, et al. Application of SVR optimized by modified simulated annealing(MSA-SVR) air conditioning load prediction model[J]. Journal of Industrial Information Integration,2019,15:247-251.
[11] 宮毓斌,滕歡. 基于GOA-SVM 的短期負荷預測[J].電測與儀表,2019,56(14):12-16.
[12] 王建國,張文興. 支持向量機建模及其智能優(yōu)化[M]. 北京:清華大學出版社,2015.
[13] MENG X B, GAO X Z, LIU Yu, et al. A novel bat algorithm with habitat selection and Doppler effect in echoes for optimization[J].Expert Systems with Applications,2015,42(17/18):6350-6364.
[14] 王文錦,戚佳金,王文婷,等. 基于人工蜂群優(yōu)化極限學習機的短期負荷預測[J] . 電測與儀表,2017,54(11):32-35.
[15] SAKURAI D, FUKUYAMA Y, IIZAKA T, et al. Daily peak load forecasting by artificial neural network using differential evolutionary particle swarm optimization considering outliers[J]. IFAC PapersOnLine,2019,52(4):389-394.
[16] 王亞琴,王耀力,王力波,等. 一種改進果蠅算法優(yōu)化神經(jīng)網(wǎng)絡短期負荷預測模型[J] . 電測與儀表,2018,55(22):13-18.