本文選題：負(fù)荷預(yù)測(cè) + 微電網(wǎng)��； 參考：《華北電力大學(xué)》2017年碩士論文

【摘要】：隨著能源問題和環(huán)境污染問題的日益嚴(yán)峻,綜合開發(fā)與合理利用新能源勢(shì)在必行,而微電網(wǎng)的建設(shè)可以充分消納新能源并且優(yōu)化能源結(jié)構(gòu)。準(zhǔn)確地進(jìn)行負(fù)荷預(yù)測(cè)不僅可以為微電網(wǎng)優(yōu)化運(yùn)行和能量管理決策提供重要依據(jù),還可以保證微電網(wǎng)高效率的經(jīng)濟(jì)運(yùn)行。因此,本文針對(duì)微電網(wǎng)的短期負(fù)荷預(yù)測(cè)問題展開研究,對(duì)微電網(wǎng)系統(tǒng)優(yōu)化運(yùn)行具有重要的理論意義和實(shí)用價(jià)值。本文首先對(duì)微電網(wǎng)負(fù)荷預(yù)測(cè)的特點(diǎn)及其影響因素進(jìn)行了分析,采用改進(jìn)的混合蛙跳算法對(duì)核函數(shù)極限學(xué)習(xí)機(jī)的組合參數(shù)進(jìn)行優(yōu)化(ISFLA_KELM),同時(shí)引入Spark on YARN平臺(tái),將算法進(jìn)行并行化改進(jìn),在確保預(yù)測(cè)精度的同時(shí)通過并行計(jì)算來應(yīng)對(duì)大數(shù)據(jù)帶來的挑戰(zhàn),并采用某微電網(wǎng)真實(shí)負(fù)荷數(shù)據(jù)驗(yàn)證預(yù)測(cè)準(zhǔn)確度以及執(zhí)行效率。本文主要進(jìn)行以下幾個(gè)方面的工作。(1)分析了微電網(wǎng)負(fù)荷預(yù)測(cè)面臨的問題,并研究了不同預(yù)測(cè)方法的優(yōu)缺點(diǎn)。針對(duì)微電網(wǎng)負(fù)荷預(yù)測(cè)的影響因素及特點(diǎn),選擇適合的智能優(yōu)化算法——混合蛙跳算法,并對(duì)其存在的缺點(diǎn)進(jìn)行針對(duì)性改進(jìn),給出了改進(jìn)的混合蛙跳算法。(2)研究分析了混合蛙跳優(yōu)化算法的原理其特點(diǎn),確定了其相對(duì)其他優(yōu)化算法的優(yōu)勢(shì)。并將改進(jìn)后的混合蛙跳優(yōu)化算法與核函數(shù)極限學(xué)習(xí)機(jī)結(jié)合,給出一種新型的微電網(wǎng)負(fù)荷預(yù)測(cè)算法(ISFLA_KELM)。將核函數(shù)極限學(xué)習(xí)機(jī)的組合參數(shù)作為蛙群優(yōu)化算法的青蛙個(gè)體進(jìn)行優(yōu)化。(3)給出了基于Spark的ISFLA_KELM微電網(wǎng)負(fù)荷預(yù)測(cè)算法,針對(duì)電力大數(shù)據(jù)下單機(jī)計(jì)算資源不足的問題,分別對(duì)KELM中的耗時(shí)運(yùn)算和ISFLA算法進(jìn)行并行化設(shè)計(jì),并結(jié)合Spark機(jī)器學(xué)習(xí)庫以及分布式文件系統(tǒng),提高算法的執(zhí)行效率。(4)進(jìn)行實(shí)驗(yàn)測(cè)試與算例分析。選用UCI標(biāo)準(zhǔn)數(shù)據(jù)集提供的真實(shí)負(fù)荷數(shù)據(jù)集,在實(shí)驗(yàn)室搭建了8個(gè)節(jié)點(diǎn)的Spark on yarn內(nèi)存計(jì)算平臺(tái),然后對(duì)提出的算法進(jìn)行性能測(cè)試,并將其與現(xiàn)有的負(fù)荷預(yù)測(cè)方法進(jìn)行對(duì)比。實(shí)驗(yàn)結(jié)果表明提出算法的負(fù)荷預(yù)測(cè)精度均優(yōu)于已有算法,且具有較好的并行性能,可為微電網(wǎng)負(fù)荷預(yù)測(cè)提供有效依據(jù)。
[Abstract]:With the increasingly serious problem of energy and environmental pollution, it is imperative to develop and utilize new energy rationally, and the construction of micro-grid can fully absorb new energy and optimize the energy structure. Accurate load forecasting can not only provide an important basis for optimal operation and energy management decision of microgrid, but also ensure the economic operation of micro-grid with high efficiency. Therefore, this paper focuses on the short-term load forecasting of microgrid, which has important theoretical significance and practical value for the optimal operation of micro-grid system. In this paper, the characteristics of load forecasting in microgrid and its influencing factors are analyzed, and the improved hybrid leapfrog algorithm is used to optimize the combined parameters of the kernel function extreme learning machine. At the same time, the Spark on YARN platform is introduced to optimize the combined parameters of the kernel function extreme learning machine. The algorithm is parallelized and improved to meet the challenge brought by big data by parallel computation while ensuring the prediction accuracy. The forecasting accuracy and execution efficiency are verified by the real load data of a microgrid. The main work of this paper is as follows: 1) the problems of load forecasting in microgrid are analyzed, and the advantages and disadvantages of different forecasting methods are studied. According to the influence factors and characteristics of load forecasting in microgrid, a suitable intelligent optimization algorithm, hybrid leapfrog algorithm, is selected, and its shortcomings are improved. This paper presents an improved hybrid leapfrog algorithm. The principle and characteristics of the hybrid leapfrog optimization algorithm are analyzed and its advantages compared with other optimization algorithms are determined. By combining the improved hybrid leapfrog optimization algorithm with the kernel function extreme learning machine, a new micro-grid load forecasting algorithm is presented. This paper presents a load forecasting algorithm of ISFLA_KELM microgrid based on Spark, which takes the combination parameter of kernel function extreme learning machine as the frog individual of frog swarm optimization algorithm. It aims at the problem of insufficient computing resources in single machine under power big data. The time-consuming operation and the ISFLA algorithm in KELM are designed in parallel, and the experimental test and the example analysis are carried out by combining the Spark machine learning library and the distributed file system to improve the execution efficiency of the algorithm. Using the real load data set provided by the UCI standard data set, an 8-node Spark on yarn memory computing platform is built in the laboratory, and then the proposed algorithm is tested and compared with the existing load forecasting methods. The experimental results show that the proposed algorithm has better load forecasting accuracy than the existing algorithms and has better parallel performance, which can provide an effective basis for load forecasting of micro-grid.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 胡俊;胡賢德;程家興;;基于Spark的大數(shù)據(jù)混合計(jì)算模型[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2015年04期

2 陳紹煒;柳光峰;冶帥;;基于核極限學(xué)習(xí)機(jī)的模擬電路故障診斷研究[J];西北工業(yè)大學(xué)學(xué)報(bào);2015年02期

3 陳虹君;;基于Hadoop平臺(tái)的Spark框架研究[J];電腦知識(shí)與技術(shù);2014年35期

4 湯慶峰;劉念;張建華;于壯壯;張清鑫;雷金勇;;基于EMD-KELM-EKF與參數(shù)優(yōu)選的用戶側(cè)微電網(wǎng)短期負(fù)荷預(yù)測(cè)方法[J];電網(wǎng)技術(shù);2014年10期

5 王保義;趙碩;張少敏;;基于云計(jì)算和極限學(xué)習(xí)機(jī)的分布式電力負(fù)荷預(yù)測(cè)算法[J];電網(wǎng)技術(shù);2014年02期

6 張健美;周步祥;林楠;張勤;陳杰;;灰色Elman神經(jīng)網(wǎng)絡(luò)的電網(wǎng)中長期負(fù)荷預(yù)測(cè)[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2013年04期

7 鄭婷婷;王海霞;李衛(wèi)東;;風(fēng)電預(yù)測(cè)技術(shù)及其性能評(píng)價(jià)綜述[J];南方電網(wǎng)技術(shù);2013年02期

8 王大鵬;汪秉文;;基于變權(quán)緩沖灰色模型的中長期負(fù)荷預(yù)測(cè)[J];電網(wǎng)技術(shù);2013年01期

9 張平;潘學(xué)萍;薛文超;;基于小波分解模糊灰色聚類和BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)[J];電力自動(dòng)化設(shè)備;2012年11期

10 崔杰;李陶深;蘭紅星;;基于Hadoop的海量數(shù)據(jù)存儲(chǔ)平臺(tái)設(shè)計(jì)與開發(fā)[J];計(jì)算機(jī)研究與發(fā)展;2012年S1期

相關(guān)碩士學(xué)位論文 前6條

1 潘超;微電網(wǎng)超短期負(fù)荷預(yù)測(cè)方法及策略研究[D];遼寧工業(yè)大學(xué);2015年

2 馬平莉;混合蛙跳算法研究[D];西安電子科技大學(xué);2013年

3 尹昊;新能源微電網(wǎng)短期負(fù)荷預(yù)測(cè)[D];湖南大學(xué);2012年

4 黃超輝;微電網(wǎng)的發(fā)電和負(fù)荷預(yù)測(cè)及其模糊控制研究[D];湖南大學(xué);2012年

5 陳艷金;MapReduce模型在Hadoop平臺(tái)下實(shí)現(xiàn)作業(yè)調(diào)度算法的研究和改進(jìn)[D];華南理工大學(xué);2011年

6 夏yN;Hadoop平臺(tái)下的作業(yè)調(diào)度算法研究與改進(jìn)[D];華南理工大學(xué);2010年

，

本文編號(hào)：1851773