本文選題：短期負(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】：隨著能源和環(huán)境問題的日趨嚴(yán)重,新能源的開發(fā)和利用受到越來越多的關(guān)注,隨之帶來了微電網(wǎng)的興起和發(fā)展。為了保證微電網(wǎng)高效率的經(jīng)濟(jì)運(yùn)行,準(zhǔn)確地負(fù)荷預(yù)測(cè)就變得尤為重要。關(guān)于微電網(wǎng)短期負(fù)荷預(yù)測(cè)的研究還相對(duì)較少,因此,本文對(duì)微電網(wǎng)的負(fù)荷預(yù)測(cè)展開研究,對(duì)微電網(wǎng)安全、節(jié)能、高效運(yùn)行具有重要的理論意義和實(shí)用價(jià)值。首先針對(duì)人工蜂群算法易陷入局部最優(yōu)及收斂速度慢的缺點(diǎn),引入當(dāng)前最優(yōu)蜜源和慣性權(quán)重函數(shù),對(duì)該算法的食物源更新方式進(jìn)行改進(jìn);然后針對(duì)支持向量回歸機(jī)的參數(shù)選擇和優(yōu)化問題,轉(zhuǎn)化成組合優(yōu)化的問題,并使用改進(jìn)的人工蜂群算法進(jìn)行優(yōu)化求解,進(jìn)而得到人工蜂群算法優(yōu)化SVR的預(yù)測(cè)模型。以微電網(wǎng)短期負(fù)荷預(yù)測(cè)數(shù)據(jù)為例,將該模型的預(yù)測(cè)結(jié)果與蟻群算法優(yōu)化的支持向量回歸機(jī)(ACO-SVR)、粒子群算法優(yōu)化的支持向量回歸機(jī)(PSO-SVR)和未改進(jìn)的蜂群算法優(yōu)化的支持向量回歸機(jī)(ABC-SVR)進(jìn)行對(duì)比分析,實(shí)驗(yàn)結(jié)果表明該模型具有最優(yōu)的預(yù)測(cè)效果并且運(yùn)行時(shí)間最短,相比其他模型具有更好的學(xué)習(xí)和推廣能力。近年來電力系統(tǒng)智能化的發(fā)展導(dǎo)致了負(fù)荷數(shù)據(jù)的海量化和高維化,負(fù)荷預(yù)測(cè)面臨著單機(jī)計(jì)算資源不足、預(yù)測(cè)實(shí)時(shí)性差的挑戰(zhàn)。針對(duì)電力系統(tǒng)的海量歷史負(fù)荷數(shù)據(jù),對(duì)上面模型在Spark平臺(tái)下進(jìn)行了并行化設(shè)計(jì)。利用實(shí)驗(yàn)室設(shè)備搭建了含一個(gè)主節(jié)點(diǎn)、七個(gè)數(shù)據(jù)節(jié)點(diǎn)的Spark計(jì)算集群,在Spark云平臺(tái)實(shí)現(xiàn)了分布式支持向量回歸預(yù)測(cè)算法。測(cè)試了本文設(shè)計(jì)的并行化算法的并行性能,實(shí)驗(yàn)分析表明本文設(shè)計(jì)的并行算法在進(jìn)行海量數(shù)據(jù)處理時(shí)相對(duì)于常用的方法具有更快的處理速度。
[Abstract]:With the increasingly serious problems of energy and environment, more and more attention has been paid to the development and utilization of new energy, which has brought about the rise and development of microgrid. In order to ensure high efficiency of economic operation of microgrid, accurate load forecasting becomes more and more important. The research on short-term load forecasting of micro-grid is relatively few. Therefore, the research on micro-grid load forecasting in this paper has important theoretical significance and practical value for micro-grid safety, energy saving and efficient operation. Firstly, aiming at the shortcomings of artificial bee colony algorithm, which is easy to fall into local optimization and slow convergence speed, the current optimal honey source and inertial weight function are introduced to improve the food source updating method of the algorithm. Then, the problem of parameter selection and optimization of support vector regression machine is transformed into a combinatorial optimization problem, and the improved artificial bee colony algorithm is used to solve the optimization problem, and then the prediction model of artificial bee colony algorithm to optimize SVR is obtained. Taking the short-term load forecasting data of microgrid as an example, The prediction results of the model are compared with the support vector regression machine (ACO-SVRV) optimized by ant colony algorithm, the support vector regression machine (PvR) optimized by particle swarm optimization (PSO) and the support vector regression machine (ABC-SVR) optimized by the unimproved bee colony algorithm. The experimental results show that the model has the best prediction effect and the shortest running time, and it has better learning and generalization ability than other models. In recent years, the development of intelligent power system has led to the sea quantization and high dimensional load data. Load forecasting is faced with the challenge of insufficient computing resources and poor real-time forecasting. Aiming at the massive historical load data of power system, parallel design of the above model is carried out on Spark platform. A Spark computing cluster with one master node and seven data nodes is constructed by using laboratory equipment. The distributed support vector regression prediction algorithm is implemented on the Spark cloud platform. The parallel performance of the parallel algorithm designed in this paper is tested. The experimental analysis shows that the parallel algorithm designed in this paper has a faster processing speed than the common methods in mass data processing.
【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)】：TP18;TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李曼;于青利;;Spark生態(tài)系統(tǒng)走向成熟和應(yīng)用[J];世界電信;2015年07期

2 劉念;張清鑫;劉海濤;;基于核函數(shù)極限學(xué)習(xí)機(jī)的微電網(wǎng)短期負(fù)荷預(yù)測(cè)方法[J];電工技術(shù)學(xué)報(bào);2015年08期

3 李彥廣;;基于Spark+MLlib分布式學(xué)習(xí)算法的研究[J];商洛學(xué)院學(xué)報(bào);2015年02期

4 高雷阜;高晶;趙世杰;;人工魚群算法優(yōu)化SVR的預(yù)測(cè)模型[J];統(tǒng)計(jì)與決策;2015年07期

5 張玲玲;楊明玉;梁武;;基于相似日和LS-SVM的微網(wǎng)短期負(fù)荷預(yù)測(cè)[J];電力建設(shè);2014年11期

6 楊再鶴;向鐵元;鄭丹;;基于小波變換和SVM算法的微電網(wǎng)短期負(fù)荷預(yù)測(cè)研究[J];現(xiàn)代電力;2014年03期

7 張賁;史沛然;蔣超;;氣象因素對(duì)京津唐電網(wǎng)夏季負(fù)荷特性影響分析[J];電力自動(dòng)化設(shè)備;2013年12期

8 于舒娟;張昀;楊磊;;基于改進(jìn)蟻群優(yōu)化的盲檢測(cè)算法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2013年11期

9 陳明;劉衍民;;基于自適應(yīng)排斥因子的改進(jìn)粒子群算法[J];計(jì)算機(jī)應(yīng)用;2013年08期

10 陳超;黃國勇;邵宗凱;王曉東;范玉剛;;基于日特征量相似日的PSO-SVM短期負(fù)荷預(yù)測(cè)[J];中國電力;2013年07期

相關(guān)博士學(xué)位論文 前1條

1 鄭凌蔚;光伏微電網(wǎng)控制與優(yōu)化的若干問題研究[D];華東理工大學(xué);2014年

相關(guān)碩士學(xué)位論文 前7條

1 沈紹輝;基于人工蜂群算法優(yōu)化支持向量機(jī)的柴油機(jī)故障診斷研究[D];中北大學(xué);2016年

2 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

3 龔根平;微電網(wǎng)下垂控制及新型微網(wǎng)的研究[D];華東交通大學(xué);2014年

4 徐俊;基于預(yù)測(cè)控制的微電網(wǎng)能量管理研究[D];華東理工大學(xué);2014年

5 趙碩;云計(jì)算和機(jī)器學(xué)習(xí)算法在電力負(fù)荷預(yù)測(cè)中的研究與應(yīng)用[D];華北電力大學(xué);2014年

6 劉榮;基于Elman神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)[D];浙江大學(xué);2013年

7 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

，

本文編號(hào)：1793264