【摘要】：短期負(fù)荷預(yù)測是電力系統(tǒng)經(jīng)濟運行與系統(tǒng)調(diào)度的重要前提和依據(jù)。智能電網(wǎng)與傳感器技術(shù)的發(fā)展使得電網(wǎng)數(shù)據(jù)劇烈膨脹,形成了用戶側(cè)負(fù)荷大數(shù)據(jù)。電網(wǎng)大數(shù)據(jù)形勢下的短期負(fù)荷預(yù)測要求預(yù)測方法的預(yù)測精度高,計算速度快,傳統(tǒng)的預(yù)測方法已經(jīng)無法滿足。以Hadoop、Spark平臺為代表的大數(shù)據(jù)處理技術(shù)的出現(xiàn),使得海量數(shù)據(jù)的處理方式進(jìn)入一個嶄新的階段。本文分析現(xiàn)階段大數(shù)據(jù)形勢下短期負(fù)荷預(yù)測的需求與面臨的關(guān)鍵問題,從提高短期負(fù)荷預(yù)測精度與提高短期負(fù)荷預(yù)測速度兩個方面為切入點,結(jié)合相關(guān)算法與數(shù)據(jù)處理,展開大數(shù)據(jù)形勢短期負(fù)荷相關(guān)工作。論文首先根據(jù)短期負(fù)荷預(yù)測與實驗需要,利用NREL實驗室公布的負(fù)荷數(shù)據(jù),生成了約2500萬組負(fù)荷實驗數(shù)據(jù)集;分析了商業(yè)用電負(fù)荷與居民用電負(fù)荷的特性,得出了兩種負(fù)荷類型具有周期性與季節(jié)性的結(jié)論。然后根據(jù)負(fù)荷數(shù)據(jù)周期性與季節(jié)性的特點,建立能夠?qū)竟?jié)與周期因素進(jìn)行建模的乘法Holt-Winters的短期負(fù)荷預(yù)測模型,并采用無約束優(yōu)化理論中的L-BFGS內(nèi)存限定擬牛頓算法實現(xiàn)預(yù)測模型的參數(shù)優(yōu)化,以降低預(yù)測模型尋優(yōu)的計算復(fù)雜度,并保證負(fù)荷預(yù)測的精度。接著將文中的短期負(fù)荷預(yù)測算法在Spark集群并行化實現(xiàn),以提高計算效率,實現(xiàn)對海量負(fù)荷數(shù)據(jù)的預(yù)測。提出了包含2個Master節(jié)點,28個Slave節(jié)點的集群構(gòu)建方案,并對集群的配置進(jìn)行優(yōu)化,使得Spark計算性能更好。最后對HDFS分布式文件系統(tǒng)存儲效率、L-BFGS-Holt-Winters短期負(fù)荷預(yù)測算法的預(yù)測誤差和Spark并行計算效率進(jìn)行實驗。結(jié)果表明,論文采用的HDFS負(fù)荷數(shù)據(jù)存儲,效率優(yōu)于傳統(tǒng)的文件存儲方式;論文采用的L-BFGS優(yōu)化方法有良好的計算效率與優(yōu)化精度;與傳統(tǒng)負(fù)荷預(yù)測算法相比,論文采用的Holt-Winters算法有更高的預(yù)測精度;Spark并行化實現(xiàn)后的短期負(fù)荷方法,能夠應(yīng)對海量負(fù)荷數(shù)據(jù)的預(yù)測需求。在論文方法在25個計算節(jié)點的計算集群中,能夠在1.5分鐘內(nèi)實現(xiàn)200萬規(guī)模的負(fù)荷預(yù)測,13分鐘內(nèi)實現(xiàn)2000萬規(guī)模的負(fù)荷預(yù)測,能夠滿足大中型城市乃至省級電力單位的負(fù)荷預(yù)測需求;論文方法能夠減少實際電力系統(tǒng)的費用消耗,節(jié)約更多的時間,為電力系統(tǒng)的調(diào)度調(diào)控等操作提供保障。本文基于Spark與Holt-Winters的短期負(fù)荷預(yù)測方法,是解決大數(shù)據(jù)形勢下海量短期負(fù)荷預(yù)測一種可行的方案。
[Abstract]:Short-term load forecasting is an important premise and basis for power system economic operation and system dispatching. With the development of smart grid and sensor technology, the data of power grid expand rapidly, and the big data of user side load is formed. Short-term load forecasting under the situation of power network big data requires high forecasting accuracy and fast calculation speed, and the traditional forecasting method can not be satisfied. With the emergence of big data processing technology represented by Hadoop Spark platform, the processing of massive data has entered a new stage. This paper analyzes the demand and key problems of short-term load forecasting under the current big data situation. From two aspects of improving the accuracy of short-term load forecasting and improving the speed of short-term load forecasting, the paper combines the relevant algorithms and data processing. Work on short-term load related to big data situation. Firstly, according to the demand of short-term load forecasting and experiment, using the load data published by NREL laboratory, about 25 million sets of load experimental data are generated, and the characteristics of commercial load and residential load are analyzed. It is concluded that the two types of load have periodicity and seasonality. Then, according to the characteristics of periodicity and seasonality of load data, a short-term load forecasting model based on multiplying Holt-Winters, which can model seasonal and periodic factors, is established. In order to reduce the computational complexity and ensure the accuracy of load forecasting, the L-BFGS memory-limited quasi-Newton algorithm in unconstrained optimization theory is used to optimize the parameters of the prediction model. Then the short-term load forecasting algorithm in this paper is implemented in Spark cluster to improve the computational efficiency and realize the prediction of massive load data. A cluster construction scheme with 2 Master nodes and 28 Slave nodes is proposed, and the configuration of the cluster is optimized to make the Spark computing performance better. Finally, experiments are made on the memory efficiency of HDFS distributed file system and the prediction error of L-BFGS-Holt-Winters short-term load forecasting algorithm and the efficiency of Spark parallel computing. The results show that the efficiency of the HDFS load data storage is better than that of the traditional file storage, the L-BFGS optimization method has good calculation efficiency and optimization accuracy, and compared with the traditional load forecasting algorithm, The Holt-Winters algorithm adopted in this paper has a higher prediction accuracy and can meet the demand of massive load data forecasting by using the short-term load method after the parallel implementation of Spark. In this paper, in the computing cluster of 25 computing nodes, 2 million scale load forecasting can be realized in 1.5 minutes and 20 million scale load forecasting can be realized in 13 minutes. It can meet the demand of load forecasting of large and medium-sized cities and even provincial electric power units, and the method of this paper can reduce the cost consumption of actual power system, save more time, and provide guarantee for the operation of power system regulation and control. In this paper, the short-term load forecasting method based on Spark and Holt-Winters is a feasible method to solve the massive short-term load forecasting under the situation of big data.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李坤;劉鵬;呂雅潔;張國鵬;黃宜華;;基于Spark的LIBSVM參數(shù)優(yōu)選并行化算法[J];南京大學(xué)學(xué)報(自然科學(xué));2016年02期

2 孟建良;劉德超;;一種基于Spark和聚類分析的辨識電力系統(tǒng)不良數(shù)據(jù)新方法[J];電力系統(tǒng)保護(hù)與控制;2016年03期

3 陳僑安;李峰;曹越;龍明盛;;基于運行數(shù)據(jù)分析的Spark任務(wù)參數(shù)優(yōu)化[J];計算機工程與科學(xué);2016年01期

4 鮑彤;陳維鋒;盧磊;;基于Hadoop的分布式集群平臺構(gòu)建方法研究[J];信息通信;2013年08期

5 丁澤柳;郭得科;申建偉;羅愛民;羅雪山;;面向云計算的數(shù)據(jù)中心網(wǎng)絡(luò)拓?fù)溲芯縖J];國防科技大學(xué)學(xué)報;2011年06期

6 廖旎煥;胡智宏;馬瑩瑩;盧王允;;電力系統(tǒng)短期負(fù)荷預(yù)測方法綜述[J];電力系統(tǒng)保護(hù)與控制;2011年01期

7 王磊;楊付正;常義林;王蓉;;基于空間復(fù)雜度掩蓋的邊緣檢測算法[J];中國圖象圖形學(xué)報;2008年01期

8 麻凱;陳塑寰;;結(jié)構(gòu)優(yōu)化中的海森矩陣的近似迭代方法[J];吉林大學(xué)學(xué)報(工學(xué)版);2006年S1期

9 徐進(jìn)東,丁曉群,鄧勇;基于相似日的線性外推短期負(fù)荷預(yù)測[J];繼電器;2005年07期

10 葛秀慧 ,田浩 ,王嘉禎 ,孫翠景;Linux中用SSH配置安全遠(yuǎn)程登錄的實踐[J];微型機與應(yīng)用;2004年07期

，

本文編號：2199369