《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 測試測量 > 設(shè)計應(yīng)用 > 基于改進EO-BP神經(jīng)網(wǎng)絡(luò)的高壓線損預(yù)測
基于改進EO-BP神經(jīng)網(wǎng)絡(luò)的高壓線損預(yù)測
電子技術(shù)應(yīng)用 2023年3期
徐利美1,,閆磊1,,李遠1,楊射2,任密蜂3
(1.國網(wǎng)山西省電力公司,, 山西 太原 030021,;2.國網(wǎng)山西超高壓變電公司,, 山西 太原 030021,; 3.太原理工大學(xué) 電氣與動力工程學(xué)院, 山西 太原 030024)
摘要: 針對高壓線損預(yù)測精度不高的問題,,提出一種基于均衡優(yōu)化器(Equilibrium Optimizer,,EO)和BP神經(jīng)網(wǎng)絡(luò)相結(jié)合的線損預(yù)測模型。首先,,為了提高EO算法的尋優(yōu)能力,,利用多種混沌映射關(guān)系初始化種群,使種群多樣性增加,,全局搜索能力得到改善,;同時,采用物競天擇概率跳脫策略改進EO算法,,使模型依概率跳出局部最優(yōu)而收斂于全局最優(yōu)解,。其次,采用改進的EO算法對BP神經(jīng)網(wǎng)絡(luò)的權(quán)值和偏置進行優(yōu)化,進而改善BP神經(jīng)網(wǎng)絡(luò)的預(yù)測效果,。最后,,實驗結(jié)果證明,所提線損預(yù)測模型相對于回歸模型,、BP神經(jīng)網(wǎng)絡(luò)模型,、模擬退火算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型和EO優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型具有更高的預(yù)測精度。
中圖分類號:TP183,;TM73 文獻標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.223399
中文引用格式: 徐利美,閆磊,,李遠,,等. 基于改進EO-BP神經(jīng)網(wǎng)絡(luò)的高壓線損預(yù)測[J]. 電子技術(shù)應(yīng)用,2023,,49(3):82-88.
英文引用格式: Xu Limei,,Yan Lei,Li Yuan,,et al. High-voltage line loss prediction based on improved EO-BP neural network[J]. Application of Electronic Technique,,2023,49(3):82-88.
High-voltage line loss prediction based on improved EO-BP neural network
Xu Limei1,,Yan Lei1,,Li Yuan1,Yang She2,,Ren Mifeng3
(1.State Grid Shanxi Electric Power Company,,Taiyuan 030021, China,; 2.Shanxi Extra High Voltage Substation Company of State Grid,, Taiyuan 030021, China,; 3.College of Electrical and Power Engineering,, Taiyuan University of Technology,Taiyuan 030024,, China)
Abstract: Aiming at the problem of low accuracy of high voltage line loss prediction, a line loss prediction model is proposed based on improved BP neural network and Equalization optimizer (EO) algorithm. Firstly, in order to improve the optimization ability of EO algorithm, a variety of chaotic mapping relations is used to initialize the population to increase the population diversity, then the global search ability could be improved. At the same time, the EO algorithm is improved by using the natural selection probability jump strategy, so that the model could jump out of the local optimization according to the probability and converge to the global optimal solution. Secondly, the improved EO algorithm is used to optimize the weight and bias of BP neural network, and the prediction effect of BP neural network for high voltage line loss is improved. Finally, the experimental results show that the proposed line loss prediction model has the highest prediction accuracy compared with regression model, BP neural network model, simulated annealing optimized BP neural network model and EO optimized BP neural network model.
Key words : line loss prediction,;chaotic mapping;natural selection probability jump strategy,;equilibrium optimizer algorithm,;neural network

0 引言

線路損耗是衡量電能在輸送過程中電能損失的指標(biāo),線損率表征了線路電能損耗占總供電量的比重,。分析電能在電網(wǎng)系統(tǒng)中傳輸和分配過程中的損耗,,提高線路損耗的預(yù)測精度,可以為電力系統(tǒng)節(jié)能降損提供技術(shù)支持,,有利于提高電力相關(guān)企業(yè)的經(jīng)濟效益,。

在線損的治理過程中,,線損計算是其中關(guān)鍵的環(huán)節(jié)。為了更有效地利用線損相關(guān)的特征變量和歷史線損數(shù)據(jù)獲得更準(zhǔn)確的預(yù)測數(shù)據(jù),,近年來相關(guān)研究人員將機器學(xué)習(xí)算法引進線損預(yù)測過程中,。文獻[2]提出一種融合小生境遺傳算法和串級BP神經(jīng)網(wǎng)絡(luò)的線損預(yù)測模型,該方法對模型參數(shù)進行了優(yōu)化,,相對于傳統(tǒng)預(yù)測方法該模型預(yù)測精度有所提高,。文獻[3]考慮特征變量數(shù)據(jù)的量值差異和影響線損的主要影響因素建立改進的BP神經(jīng)網(wǎng)絡(luò)模型,但模型的預(yù)測效果需要進一步提升,。文獻[4]使用粒子群算法改進最小二乘支持向量機的懲罰因子,,該方法提升了模型的預(yù)測精度和收斂速度。文獻[5]通過灰色關(guān)聯(lián)分析法篩選與線損相關(guān)聯(lián)的特征指標(biāo),,并提出自適應(yīng)遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的線損預(yù)測模型,,所建立的模型具有收斂速度快和泛化能力強的特點。上述文獻所建立的模型有利于提高電壓等級較低的線損預(yù)測精度,,對于電壓等級較高的線損預(yù)測需要考慮電暈對線損的影響,。

EO算法是2020年提出的一種新穎的優(yōu)化算法,該算法經(jīng)過多個標(biāo)準(zhǔn)函數(shù)的測試顯現(xiàn)出更強的尋優(yōu)能力和更快的收斂速度,。為了提高高壓線損的預(yù)測精度,,本文提出改進EO-BP神經(jīng)網(wǎng)絡(luò)的線損預(yù)測模型。該模型考慮了BP神經(jīng)網(wǎng)絡(luò)模型參數(shù)的優(yōu)化和電暈對高壓線路損耗的影響,。經(jīng)典BP神經(jīng)網(wǎng)絡(luò)在訓(xùn)練時易陷入局部最優(yōu)而影響預(yù)測精度,,本文引入EO算法對其優(yōu)化,同時采用混沌種群初始化和物競天擇概率跳脫策略提高模型的搜索效率,,擴大搜索范圍的同時使模型收斂于全局最優(yōu),,實驗時將該模型與回歸模型、BP神經(jīng)網(wǎng)絡(luò)模型,、模擬退火算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型和EO優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型進行仿真實驗對比,,證明了本文所提方法的有效性。




本文詳細(xì)內(nèi)容請下載:http://forexkbc.com/resource/share/2000005234




作者信息:

徐利美1,,閆磊1,,李遠1,楊射2,,任密蜂3

(1.國網(wǎng)山西省電力公司,, 山西 太原 030021;2.國網(wǎng)山西超高壓變電公司,, 山西 太原 030021,;

3.太原理工大學(xué) 電氣與動力工程學(xué)院, 山西 太原 030024)


微信圖片_20210517164139.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載,。