基于Hadoop架構(gòu)的多重分布式BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)方法
發(fā)布時(shí)間：2018-10-05 11:22
【摘要】：隨著智能電網(wǎng)、通信網(wǎng)絡(luò)技術(shù)和傳感器技術(shù)的發(fā)展,電力負(fù)荷數(shù)據(jù)規(guī)模呈現(xiàn)指數(shù)形式增長(zhǎng)、且復(fù)雜程度增大,逐步構(gòu)成了電力負(fù)荷大數(shù)據(jù),傳統(tǒng)負(fù)荷預(yù)測(cè)方法已無法滿足海量負(fù)荷大數(shù)據(jù)分析的要求。提出一種基于Hadoop架構(gòu)的多重分布式BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)方法。該方法首先在從BP神經(jīng)網(wǎng)絡(luò)原理層對(duì)其輸入信號(hào)的正向傳遞、誤差信號(hào)的反向傳播過程予以剖析的基礎(chǔ)上,研究并建立基于Hadoop架構(gòu)中Map Reduce框架的BP神經(jīng)網(wǎng)絡(luò)負(fù)荷分布式預(yù)測(cè)模型;其次,為弱化其"過擬合"問題,在引入"多重"概念的基礎(chǔ)上,提出基于灰色關(guān)聯(lián)度和最短距離法聚類的方式擇取多重分布式BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型初始重?cái)?shù)和成員集的方法,并定義衡量聚類優(yōu)劣的有效指標(biāo),以確定合理重?cái)?shù)。實(shí)驗(yàn)結(jié)果表明,多重分布式BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)方法相比傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò),預(yù)測(cè)精度更高。
[Abstract]:With the development of smart grid, communication network technology and sensor technology, the scale of power load data increases exponentially and the complexity increases. Traditional load forecasting method can not meet the requirements of mass load big data analysis. This paper presents a short term load forecasting method for multiple distributed BP neural networks based on Hadoop architecture. The method is based on the analysis of the forward transmission of the input signal and the backward propagation of the error signal from the principle layer of the BP neural network. The distributed load forecasting model of BP neural network based on Map Reduce framework in Hadoop architecture is studied and established. Secondly, in order to weaken the problem of "overfitting", the concept of "multiple" is introduced. This paper presents a method of selecting the initial multiplicity and membership set of multiple distributed BP neural network prediction model based on grey correlation degree and shortest distance clustering method, and defines the effective index to evaluate the clustering quality in order to determine the reasonable multiplicity. Experimental results show that the multiple distributed BP neural network prediction method is more accurate than the traditional BP neural network.
【作者單位】： 四川大學(xué)電氣信息學(xué)院;國(guó)網(wǎng)信通產(chǎn)業(yè)集團(tuán)北京中電普華信息技術(shù)有限公司;
【分類號(hào)】：TM715;TP183
[Abstract]:With the development of smart grid, communication network technology and sensor technology, the scale of power load data increases exponentially and the complexity increases. Traditional load forecasting method can not meet the requirements of mass load big data analysis. This paper presents a short term load forecasting method for multiple distributed BP neural networks based on Hadoop architecture. The method is based on the analysis of the forward transmission of the input signal and the backward propagation of the error signal from the principle layer of the BP neural network. The distributed load forecasting model of BP neural network based on Map Reduce framework in Hadoop architecture is studied and established. Secondly, in order to weaken the problem of "overfitting", the concept of "multiple" is introduced. This paper presents a method of selecting the initial multiplicity and membership set of multiple distributed BP neural network prediction model based on grey correlation degree and shortest distance clustering method, and defines the effective index to evaluate the clustering quality in order to determine the reasonable multiplicity. Experimental results show that the multiple distributed BP neural network prediction method is more accurate than the traditional BP neural network.
【作者單位】： 四川大學(xué)電氣信息學(xué)院;國(guó)網(wǎng)信通產(chǎn)業(yè)集團(tuán)北京中電普華信息技術(shù)有限公司;
【分類號(hào)】：TM715;TP183
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 王雪峰,鄔建華,馮英浚,王建元;運(yùn)用樣本更新的實(shí)時(shí)神經(jīng)網(wǎng)絡(luò)進(jìn)行短期電力負(fù)荷預(yù)測(cè)[J];系統(tǒng)工程理論與實(shí)踐;2003年04期
2 文漢云;;硫化氫燃燒的神經(jīng)網(wǎng)絡(luò)PID控制及其仿真[J];自動(dòng)化與儀器儀表;2006年01期
3 張U，
本文編號(hào)：2253190
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2253190.html
最近更新
教材專著
