本文關(guān)鍵詞：基于數(shù)據(jù)挖掘的用電數(shù)據(jù)異常的分析與研究　出處：《北京交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 用電信息采集系統(tǒng) 異常數(shù)據(jù) 數(shù)據(jù)挖掘 孤立森林算法 決策樹算法

【摘要】：在大數(shù)據(jù)時代的背景下,我國電力企業(yè)更加重視營銷業(yè)務(wù)的信息化,十三五電力發(fā)展規(guī)劃中指出,利用大數(shù)據(jù)等技術(shù)提升信息平臺承載能力和業(yè)務(wù)應(yīng)用水平。隨著用電信息采集系統(tǒng)的推廣,海量的用電數(shù)據(jù)得以采集,為用電環(huán)節(jié)的大數(shù)據(jù)分析提供了堅實的數(shù)據(jù)基礎(chǔ)。但是面對海量用電數(shù)據(jù)的增加,目前大多數(shù)電力部門僅使用傳統(tǒng)的統(tǒng)計方法進(jìn)行異常分析,異常數(shù)據(jù)背后蘊藏的事件信息無法得到有效提煉。為此,有必要將數(shù)據(jù)挖掘技術(shù)引入到異常分析中,充分挖掘用電數(shù)據(jù)的異常信息。首先,考慮到所有異常都會在電量數(shù)據(jù)上得以體現(xiàn),故采用規(guī)律性強(qiáng)的日負(fù)荷曲線作為異常檢測的特征指標(biāo)。利用具有調(diào)節(jié)參數(shù)少、準(zhǔn)確率高、計算效率快等突出優(yōu)點的孤立森林算法構(gòu)建異常檢測模型,并對模型中的重要參數(shù)進(jìn)行了分析設(shè)置。該模型輸出所有用戶的異常分值及疑似概率排序。研究結(jié)果表明,利用該排序,只需要檢測異常分值靠前的少數(shù)用戶即可查出大部分異常用戶。其次,為了突出基于孤立森林算法在用電異常檢測方面的優(yōu)越性,通過建立基于聚類分析、局部離群因子算法的異常檢測模型并進(jìn)行比較,發(fā)現(xiàn)本文構(gòu)建的用電數(shù)據(jù)異常檢測模型在計算效率方面的優(yōu)勢尤為顯著,并且準(zhǔn)確率保持較高,證明了孤立森林算法用于構(gòu)建用電數(shù)據(jù)異常檢測模型的準(zhǔn)確性和高效性。第三,考慮到日負(fù)荷曲線受用戶用電習(xí)慣的影響較大,因此需要結(jié)合疑似異常用戶的電氣變量作進(jìn)一步分析,建立用電數(shù)據(jù)異常識別模型,減少誤判率。利用決策樹算法易于理解實現(xiàn)和效率高等特點,實現(xiàn)對計量點電壓進(jìn)行自動快速分類,并輔助電流數(shù)據(jù)進(jìn)行判斷,識別出電能計量裝置異常。在現(xiàn)場異常排查中,驗證了用電數(shù)據(jù)異常識別模型的有效性。最后,在實際案例中發(fā)現(xiàn),由于異常的電能計量裝置中存在殘余電壓,導(dǎo)致電量追補(bǔ)出現(xiàn)差錯。為此,有必要對傳統(tǒng)的更正系數(shù)計算方法進(jìn)行改進(jìn),通過用電信息采集系統(tǒng)在故障期間凍結(jié)的96點電壓數(shù)據(jù)進(jìn)行分析,綜合考慮故障相的殘余電壓,并研究電能計量裝置計算電量的原理,調(diào)整更正系數(shù),較現(xiàn)有的方法更全面和更具公正性。
[Abstract]:Under the background of big data era, Chinese electric power enterprises pay more attention to the informationization of marketing business, as pointed out in the 13th Five-Year Plan of Electric Power Development. Using big data and other technologies to enhance the bearing capacity of the information platform and the level of business application. With the promotion of power information acquisition system, massive power consumption data can be collected. It provides a solid data base for big data analysis of power consumption. However, in the face of the increase of massive power consumption data, most power departments only use the traditional statistical method for abnormal analysis. The event information contained behind the abnormal data can not be extracted effectively. Therefore, it is necessary to introduce the data mining technology into the anomaly analysis to fully mine the abnormal information of the electrical data. Considering that all anomalies will be reflected in the data of electric quantity, the daily load curve with strong regularity is used as the characteristic index of abnormal detection. The outlier detection model is constructed by the isolated forest algorithm which has the advantages of fast computing efficiency and so on. The important parameters in the model are analyzed and set. The model outputs outlier scores and suspected probability ranking of all users. The research results show that the ranking is used. In order to highlight the superiority of the isolated forest algorithm in the detection of electrical anomaly, the clustering analysis is established. The anomaly detection model of local outlier factor algorithm is compared and it is found that the outlier detection model constructed in this paper has significant advantages in computing efficiency and high accuracy. It is proved that the isolated forest algorithm is accurate and efficient in building the model of abnormal detection of power consumption data. Thirdly, considering that the daily load curve is greatly affected by users' power consumption habits. Therefore, it is necessary to further analyze the electrical variables of suspected abnormal users, establish a model of abnormal identification of electrical data, reduce the error rate, and use the decision tree algorithm to understand the characteristics of high efficiency and easy to understand. It realizes the automatic and fast classification of the voltage of the measuring point, and adjusts the current data to judge, and identifies the outliers of the electric energy metering device. Finally, it is found that the residual voltage exists in the abnormal electric energy metering device, which leads to the error of power compensation. It is necessary to improve the traditional calculation method of correction coefficient and analyze the 96 points of voltage data frozen by the electrical information acquisition system during the fault, and consider the residual voltage of the fault phase synthetically. The principle of electric energy metering device is studied, and the correction coefficient is adjusted, which is more comprehensive and more just than the existing method.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP311.13;TM76

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 田力;向敏;;基于密度聚類技術(shù)的電力系統(tǒng)用電量異常分析算法[J];電力系統(tǒng)自動化;2017年05期

2 王桂蘭;周國亮;趙洪山;米增強(qiáng);;大規(guī)模用電數(shù)據(jù)流的快速聚類和異常檢測技術(shù)[J];電力系統(tǒng)自動化;2016年24期

3 陳文瑛;陳雁;邱林;趙加奎;王樹龍;張劍;劉洋;朱平飛;歐陽紅;;應(yīng)用大數(shù)據(jù)技術(shù)的反竊電分析[J];電子測量與儀器學(xué)報;2016年10期

4 楊光;;基于神經(jīng)網(wǎng)絡(luò)的異常用電檢測算法模型研究[J];供用電;2016年10期

5 胡偉;李勇;曹一家;張志鵬;趙慶周;段義隆;;基于LOF和SVM的智能配電網(wǎng)故障辨識方法[J];電力自動化設(shè)備;2016年06期

6 彭顯剛;林利祥;劉藝;林幕群;鄭偉欽;;數(shù)據(jù)挖掘技術(shù)在電價執(zhí)行稽查中的應(yīng)用研究[J];電氣應(yīng)用;2016年11期

7 沈海濤;秦靖雅;陳浩;范蓉;莊才杰;;電力用戶用電數(shù)據(jù)的異常數(shù)據(jù)審查和分類[J];電力與能源;2016年01期

8 熊克卿;李彬;祁兵;尹璐;;基于智能電網(wǎng)用戶側(cè)海量數(shù)據(jù)的業(yè)務(wù)系統(tǒng)研究[J];供用電;2016年02期

9 莊池杰;張斌;胡軍;李秋碩;曾嶸;;基于無監(jiān)督學(xué)習(xí)的電力用戶異常用電模式檢測[J];中國電機(jī)工程學(xué)報;2016年02期

10 周文婷;顧楠;王濤;韓雙立;鄧家貴;;基于數(shù)據(jù)挖掘算法的用戶竊電嫌疑分析[J];河南科學(xué);2015年10期

相關(guān)會議論文 前1條

1 涂兵;;數(shù)據(jù)挖掘技術(shù)在電力行業(yè)中的應(yīng)用研究[A];決策論壇——基于公共管理學(xué)視角的決策研討會論文集（上）[C];2015年

相關(guān)碩士學(xué)位論文 前6條

1 周勇;關(guān)聯(lián)規(guī)則決策樹算法在電網(wǎng)故障中的分析及應(yīng)用[D];長沙理工大學(xué);2015年

2 趙新想;基于密度的局部離群點檢測算法的研究與改進(jìn)[D];華中師范大學(xué);2014年

3 簡富俊;基于AMI的入侵檢測技術(shù)研究[D];華北電力大學(xué);2014年

4 秦璇;電力統(tǒng)計數(shù)據(jù)的質(zhì)量評估及其異常檢測方法研究[D];長沙理工大學(xué);2013年

5 宋南;基于電能信息的電表現(xiàn)場校驗狀態(tài)分析研究[D];浙江大學(xué);2011年

6 魯均云;重復(fù)和不完整數(shù)據(jù)的清理方法研究及應(yīng)用[D];江蘇大學(xué);2009年

，

本文編號：1419125