發(fā)布時間：2018-04-02 20:00

  本文選題：居民用電行為　切入點：負荷預測　出處：《華北電力大學》2017年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)、物聯(lián)網(wǎng)、無線傳感器等新一代技術的發(fā)展,加快了智能電網(wǎng)建設的速度。在智能電網(wǎng)的建設過程中,先進的計量設備、智能終端設備被大量安裝與使用,居民的用電方式也趨于多元化。深入感知居民的實際功耗模式對提高負荷預測的精度、保障電力系統(tǒng)的正常運行、能量管理和規(guī)劃至關重要。本文首先分析居民用電大數(shù)據(jù)的來源,針對居民用電大數(shù)據(jù)體量大、類型復雜、速度快與交互性強等特點,指出居民用電大數(shù)據(jù)在存儲、處理等操作所面臨的挑戰(zhàn)。然后提出了一種基于大數(shù)據(jù)的居民用電行為分析與負荷預測模型,該模型將智能電表、氣象、節(jié)假日等數(shù)據(jù)作為輸入,并使用基于內(nèi)存計算的大數(shù)據(jù)處理框架Spark對居民用電大數(shù)據(jù)進行挖掘與分析。最后設計并開發(fā)基于大數(shù)據(jù)的居民用電行為分析與負荷預測原型系統(tǒng),系統(tǒng)包括Spark集群管理、負荷數(shù)據(jù)管理、算法分析、預測結果展示等模塊。將基于Spark的K-Means聚類算法應用于居民用戶的用電模式聚類實驗,實驗結果表明對居民用戶分類具有較高的正確率。并將其運行效果與傳統(tǒng)K-Means算法運行效果進行對比,實驗結果表明隨著數(shù)據(jù)集規(guī)模的不斷擴大,基于Spark的K-Means算法表現(xiàn)出良好的性能,減少了聚類執(zhí)行的時間和提高了聚類的準確性。并針對不同類別的居民用戶進行用電行為的分析�；谏鲜鰧嶒�,針對每類居民用戶建立負荷預測模型,分別使用基于Spark的多層感知器神經(jīng)網(wǎng)絡算法(MLP-NN)與基于Spark的SVM算法實現(xiàn)每類居民用戶的負荷預測,實驗結果表明MLP-NN具有較高的預測精度。使用兩個不同的數(shù)據(jù)集驗證該模型的可行性,并擴大兩種數(shù)據(jù)集的規(guī)模,從每類用戶的智能電表數(shù)據(jù)、氣象數(shù)據(jù)和節(jié)假日數(shù)據(jù)中抽取20個特征向量作為算法的輸入層數(shù)據(jù),實驗結果表明該預測方法在一定程度上提高了負荷預測的精度,大數(shù)據(jù)環(huán)境下表現(xiàn)出更好的預測效果。
[Abstract]:With the Internet, the Internet of things, the development of a new generation of wireless sensor technology, accelerate the construction of smart grid speed. In the process of construction of smart grid, advanced metering equipment, intelligent terminal equipment by a large number of installation and use, residents of the electricity also tends to be diversified. The actual power consumption mode of residents' perception of depth to improve the accuracy of load forecasting, guarantee the normal operation of the power system, vital energy management and planning. This paper first analyzes the source of large data by residents, for residents with large data volume, complex types, characteristics of high speed and strong interaction, pointed out that the residential electricity data in the storage, processing and other operations of the challenges faced by the and then an electrical behavior analysis and load forecasting model for large data based on the model of residents, smart meters, weather, holidays and other data as input, and use the base Big data in memory computing processing framework using Spark data mining and analysis of large residents. Finally the design and analysis of behavior and electric load forecasting prototype system with large data systems including Spark residents based on development, cluster management, load data management, algorithm analysis, the prediction results display module. The application based on K-Means clustering algorithm Spark to the residents' electricity pattern clustering experiments, experimental results show that the correct rate is higher for residential users classification. And compared its effect with the traditional K-Means algorithm running effect, the experimental results show that with the continuous expansion of the scale of data set, the K-Means Spark algorithm shows good performance on reducing clustering of execution time and improves the accuracy of clustering. And analyze the consumption behavior of the residents according to different categories of users. Based on the above experiments, for each Resident users to establish the forecasting model, using multilayer perceptron neural network algorithm based on Spark (MLP-NN) and SVM Spark algorithm for each type of load forecasting based on residential users, the experimental results show that MLP-NN has higher prediction accuracy. Using two different data sets to verify the feasibility of the model, and expand the two kinds of data from the data set size, the smart meter of each user, extraction of meteorological data and data in the 20 holiday feature vector as the input data of the algorithm, the experimental results show that the prediction method can improve the accuracy of load forecasting in a certain extent, performance under the big data environment a better prediction effect.

【學位授予單位】：華北電力大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP311.13;TM715

【參考文獻】

相關期刊論文 前10條

1 王德文;楊力平;;智能電網(wǎng)大數(shù)據(jù)流式處理方法與狀態(tài)監(jiān)測異常檢測[J];電力系統(tǒng)自動化;2016年14期

2 王德文;周青;;一種電力設備狀態(tài)監(jiān)測大數(shù)據(jù)的分布式聯(lián)機分析處理方法[J];中國電機工程學報;2016年19期

3 張魁;王亞明;劉明;伏祥運;李紅;;基于大數(shù)據(jù)及智能算法的連云港電量負荷預測研究[J];江蘇電機工程;2016年03期

4 蔡洪山;;基于Spark的Kmeans并行算法研究[J];電腦知識與技術;2016年04期

5 王桂蘭;周國亮;薩初日拉;朱永利;;Spark環(huán)境下的并行模糊C均值聚類算法[J];計算機應用;2016年02期

6 何琬;劉進;朱肖晶;;基于深層神經(jīng)網(wǎng)絡的電力負荷預測[J];環(huán)境與可持續(xù)發(fā)展;2016年01期

7 郭洪月;關微;趙波;張津銘;張玉良;陳明非;;基于無線傳感器網(wǎng)絡的智能電網(wǎng)信息管理平臺[J];科技與創(chuàng)新;2016年02期

8 常鮮戎;孫景文;;粒子群優(yōu)化的模糊聚類在負荷預處理的應用[J];電力系統(tǒng)及其自動化學報;2015年07期

9 王德文;孫志偉;;電力用戶側大數(shù)據(jù)分析與并行負荷預測[J];中國電機工程學報;2015年03期

10 瞿海妮;張鵬飛;凌平;黃興德;賀向南;甘信軍;盛文博;;基于海量數(shù)據(jù)的電網(wǎng)需求側用戶行為分析研究[J];華東電力;2014年12期

相關碩士學位論文 前4條

1 杜明建;大數(shù)據(jù)技術在負荷預測與負荷特性分析中的應用[D];東南大學;2015年

2 黃山山;南京電信網(wǎng)廳用戶行為分析系統(tǒng)的設計實現(xiàn)與應用[D];南京理工大學;2011年

3 殷利杰;混沌理論的研究及其在短期電力負荷預測中的應用[D];華北電力大學（河北）;2009年

4 曾夢妤;分類用戶峰谷電價研究[D];華北電力大學（北京）;2006年

，

本文編號：1701886