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

遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的電能質(zhì)量預(yù)測(cè)預(yù)警研究

來(lái)源:電工電氣發(fā)布時(shí)間:2021-09-18 12:18 瀏覽次數(shù):500

遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的電能質(zhì)量預(yù)測(cè)預(yù)警研究

武晨晨1,苗霽1,祝佳楠1,張文惠2
(1 國(guó)網(wǎng)江蘇省電力有限公司宿遷供電分公司,江蘇 宿遷 223800;
2 南京理工大學(xué) 自動(dòng)化學(xué)院,江蘇 南京 210094)
 
    摘 要:電能質(zhì)量穩(wěn)態(tài)指標(biāo)的預(yù)測(cè)和預(yù)警對(duì)于優(yōu)化電網(wǎng)運(yùn)行方式具有重要意義。以某監(jiān)測(cè)點(diǎn)為研究對(duì)象,根據(jù)該監(jiān)測(cè)點(diǎn)的歷史天氣信息、有功功率、無(wú)功功率和電能質(zhì)量數(shù)據(jù),使用遺傳算法改進(jìn) BP 神經(jīng)網(wǎng)絡(luò),構(gòu)建復(fù)合型神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)系統(tǒng)。給出了電能質(zhì)量分等級(jí)預(yù)警方式,通過(guò)模糊聚類合理靈活地設(shè)置閾值并給出電能質(zhì)量預(yù)警信息,以適應(yīng)不同場(chǎng)合的預(yù)警。算例驗(yàn)證證明了該方法的有效性與實(shí)用性。
    關(guān)鍵詞:電能質(zhì)量;遺傳算法;BP 神經(jīng)網(wǎng)絡(luò);預(yù)測(cè);預(yù)警;模糊聚類
    中圖分類號(hào):TM933.4     文獻(xiàn)標(biāo)識(shí)碼:A     文章編號(hào):1007-3175(2021)09-0018-05
 
Power Quality Prediction and Warning Based on BP
Neural Network Optimized by Genetic Algorithm
 
WU Chen-chen1, MIAO Ji1, ZHU Jia-nan1, ZHANG Wen-hui2
(1 State Grid Jiangsu Electric Power Co., Ltd Suqian Power Supply Branch, Suqian 223800, China;
2 School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China)
 
    Abstract: The prediction and warning of power quality steady state indices is of great significance to optimize the operation of power grid.In this paper, a certain monitoring point is taken as the research object and the data about its historical weather information, active power, reactive power and power quality are performed., The genetic algorithm is utilized to improve the BP neural network and a complex neural network prediction system is constructed accordingly. This prediction system could warn by the grades of power quality and could set threshold value reasonably and flexibly by the use of fuzzy clustering aiming at giving warning information which is available for various situations. In the end ,this method is verified effective and practical by an example.
    Key words: power quality; genetic algorithm; BP neural network; prediction; warning; fuzzy clustering
 
參考文獻(xiàn)
[1] SONG J, XIE Z, ZHOU J, et al.Power quality indexes prediction based on cluster analysis and support vector machine[J].CIRED-Open Access Proceedings Journal,2017(1) :814-817.
[2] 李君衛(wèi), 湯亞芳, 郝正航, 等. 聚類分析及其在電力系統(tǒng)中的應(yīng)用綜述[J] . 現(xiàn)代電力,2019,36(3) :1-10.
[3] 林順富,湯繼開(kāi),湯波,等. 典型電能質(zhì)量 z 穩(wěn)態(tài)指標(biāo)預(yù)測(cè)模型研究[J] . 電網(wǎng)技術(shù),2018,42(2) :614-620.
[4] 趙秀平. 基于多種預(yù)測(cè)方法的電能質(zhì)量預(yù)警機(jī)制研究與實(shí)現(xiàn)[D]. 北京:華北電力大學(xué),2016.
[5] 劉建華,劉艷梅,馮純純,等. 基于 k 中心點(diǎn)聚類的穩(wěn)態(tài)電能質(zhì)量預(yù)警閾值研究[J] . 電測(cè)與儀表,2018,55(23) :41-45.
[6] ZEJUN D, PING L, SEN O, et al.Mechanism of Power Quality Forecast and Early Warning and Their Application[J].Proceedings of the CSUEPSA,2015,27(10) :87-92.
[7] 丁澤俊,劉平,歐陽(yáng)森,等. 電能質(zhì)量預(yù)測(cè)與預(yù)警機(jī)制及其應(yīng)用[J] . 電力系統(tǒng)及其自動(dòng)化學(xué)報(bào),2015,27(10) :87-92.
[8] 盧玨,孫云蓮,謝信霖,等. 基于改進(jìn)組合預(yù)測(cè)的電能質(zhì)量預(yù)警研究[J] . 電工電能新技術(shù),2020,39(9) :65-73.
[9] 蘇衛(wèi)衛(wèi),馬素霞,齊林海. 基于 ARIMA 和神經(jīng)網(wǎng)絡(luò)的電能質(zhì)量穩(wěn)態(tài)指標(biāo)預(yù)測(cè)[J] . 計(jì)算機(jī)技術(shù)與發(fā)展,2014,24(3) :163-167.
[10] 王芳,顧偉,袁曉冬,等. 面向智能電網(wǎng)的新一代電能質(zhì)量管理平臺(tái)[J] . 電力自動(dòng)化設(shè)備,2012,32(7) :134-139.
[11] 王同勛,楊岑玉,彭傊,等. 一種電能質(zhì)量預(yù)警系統(tǒng)及其方法:CN103647276A[P].2014-03-19.
[12] 歐陽(yáng)森,李奇,石怡理,等. 考慮模糊聚類特性的電能質(zhì)量預(yù)警方法及其應(yīng)用[J] . 電網(wǎng)技術(shù),2014,38(6) :1712-1716.