【摘要】：隨著社會(huì)經(jīng)濟(jì)的發(fā)展和環(huán)境因素的制約,電力系統(tǒng)運(yùn)行越來(lái)越接近穩(wěn)定極限,高滲透率可再生能源的大規(guī)模接入,增加了電力系統(tǒng)運(yùn)行的復(fù)雜性和不確定性,也對(duì)電力系統(tǒng)電壓穩(wěn)定評(píng)估提出了新的要求。傳統(tǒng)的靜態(tài)電壓穩(wěn)定評(píng)估方法因計(jì)算耗時(shí)、建模困難,難以滿足在線評(píng)估的應(yīng)用要求。隨著向量測(cè)量單元(phasor measurement unit,PMU)的廣泛使用,海量的電網(wǎng)實(shí)時(shí)數(shù)據(jù)為電壓穩(wěn)定的在線分析提供了可能性。本文提出一種基于數(shù)據(jù)挖掘的靜態(tài)電壓穩(wěn)定在線監(jiān)測(cè)算法,核心思想是通過(guò)離線仿真分析產(chǎn)生大量的原始數(shù)據(jù),并應(yīng)用機(jī)器學(xué)習(xí)的方式,從大量數(shù)據(jù)中提取出有價(jià)值的信息,再通過(guò)PMU實(shí)現(xiàn)在線監(jiān)控的目的。首先利用電力系統(tǒng)靜態(tài)電壓穩(wěn)定的分析方法,通過(guò)PV曲線計(jì)算不同網(wǎng)架下基于電壓穩(wěn)定約束的最大傳輸功率和電壓穩(wěn)定儲(chǔ)備系數(shù)。并在PV曲線極限點(diǎn)處求出各母線節(jié)點(diǎn)對(duì)主導(dǎo)電壓失穩(wěn)模式的參與因子,以及各母線的電壓-無(wú)功靈敏度�；诖�,引入模糊聚類分析的方法對(duì)電壓穩(wěn)定指標(biāo)進(jìn)行綜合判斷,從而更準(zhǔn)確地識(shí)別電壓薄弱區(qū)域,并應(yīng)用中國(guó)某地區(qū)電網(wǎng)數(shù)據(jù)進(jìn)行算例分析及驗(yàn)證。在對(duì)整個(gè)電網(wǎng)的靜態(tài)電壓穩(wěn)定評(píng)估的基礎(chǔ)之上,展開(kāi)數(shù)據(jù)挖掘。針對(duì)較多的輸入特征變量使得模型訓(xùn)練時(shí)間長(zhǎng)以及分類準(zhǔn)確率低的問(wèn)題,本文從電壓失穩(wěn)的實(shí)質(zhì)出發(fā),在充分考慮導(dǎo)致電壓失穩(wěn)原因的基礎(chǔ)上來(lái)選擇輸入變量。首先依靠模態(tài)分析確定電力系統(tǒng)電壓穩(wěn)定問(wèn)題的主要影響因素,完成初步篩選,其次根據(jù)Relief特征選擇算法進(jìn)一步優(yōu)化,最終得到最佳的特征變量集合,從而降低電力系統(tǒng)的特征維度。最后選擇決策樹(shù)模型作為靜態(tài)電壓穩(wěn)定評(píng)估的分類器,并引入代價(jià)敏感機(jī)制,提出了基于代價(jià)敏感決策樹(shù)的靜態(tài)電壓穩(wěn)定在線評(píng)估算法。該算法以誤分代價(jià)最小為目標(biāo),可在一定程度上避免電壓失穩(wěn)漏診為電壓穩(wěn)定的情形,有效降低了漏警率。電網(wǎng)調(diào)度人員可利用PMU實(shí)時(shí)采集需要監(jiān)測(cè)的變量數(shù)據(jù),依據(jù)決策樹(shù)中提取的判定規(guī)則,對(duì)電力系統(tǒng)的靜態(tài)電壓穩(wěn)定性進(jìn)行快速評(píng)估,實(shí)現(xiàn)在線監(jiān)測(cè)的目的,并應(yīng)用某地區(qū)電網(wǎng)數(shù)據(jù)進(jìn)行算例分析及驗(yàn)證。
[Abstract]:With the development of social economy and the restriction of environmental factors, the operation of power system is more and more close to the limit of stability. The large-scale access of renewable energy with high permeability increases the complexity and uncertainty of power system operation. New requirements for voltage stability evaluation of power system are also put forward. The traditional static voltage stability evaluation method is difficult to meet the requirements of online evaluation because of its time-consuming calculation and difficult modeling. With the wide use of vector measurement unit (phasor measurement unit,PMU), massive real-time data of power grid provide the possibility of on-line analysis of voltage stability. In this paper, a static voltage stability on-line monitoring algorithm based on data mining is proposed. The core idea is to generate a large amount of raw data by off-line simulation analysis, and to extract valuable information from a large number of data by means of machine learning. Then the purpose of online monitoring is realized by PMU. Firstly, using the static voltage stability analysis method of power system, the maximum transmission power and voltage stability reserve coefficient based on voltage stability constraints under different grid structures are calculated by PV curve. At the limit point of the PV curve, the participation factors of each bus node to the dominant voltage instability mode and the voltage-reactive power sensitivity of each bus are obtained. Based on this, the fuzzy cluster analysis method is introduced to judge the voltage stability index synthetically, so as to identify the weak voltage area more accurately, and to use the data of a certain area in China to analyze and verify the example. Based on the static voltage stability evaluation of the whole power network, data mining is carried out. In view of the problem that more input characteristic variables make the training time of the model long and the classification accuracy low, this paper selects input variables based on the essence of voltage instability and considering the causes of voltage instability. Firstly, the main influencing factors of voltage stability in power system are determined by modal analysis, and the primary screening is completed. Secondly, the optimal set of characteristic variables is obtained by further optimization according to the Relief feature selection algorithm. Thus, the characteristic dimension of power system is reduced. Finally, the decision tree model is selected as the classifier of static voltage stability evaluation, and the cost sensitive mechanism is introduced, and an on-line static voltage stability evaluation algorithm based on the cost sensitive decision tree is proposed. The algorithm aims at minimizing the cost of misdivision, which can avoid the situation that voltage instability is diagnosed as voltage stability to a certain extent, and effectively reduce the leakage alarm rate. The power grid dispatcher can use PMU to collect the variable data that needs to be monitored in real time, according to the decision rules extracted from the decision tree, the static voltage stability of power system can be evaluated quickly, and the purpose of on-line monitoring can be realized. An example is used to analyze and verify the data of a regional power network.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM712;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳成業(yè);劉光曄;羅經(jīng)緯;;基于泰勒級(jí)數(shù)的PV曲線求取及參變量選擇分析[J];電網(wǎng)技術(shù);2017年04期

2 李培強(qiáng);王繼飛;唐捷;黎文黛;李欣然;李文英;;基于模態(tài)分析的雙饋機(jī)組對(duì)電壓穩(wěn)定性的影響[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2016年04期

3 張瑋靈;胡偉;閔勇;陳磊;劉顯壯;;穩(wěn)定域概念下考慮保守性的電力系統(tǒng)在線暫態(tài)穩(wěn)定評(píng)估方法[J];電網(wǎng)技術(shù);2016年04期

4 楊杰明;閆欣;曲朝陽(yáng);宋晨晨;喬媛媛;;基于數(shù)據(jù)密度分布的欠采樣方法研究[J];計(jì)算機(jī)應(yīng)用研究;2016年10期

5 董雷;張昭;蒲天驕;于汀;韓巍;;基于PMU量測(cè)信息的電壓穩(wěn)定在線評(píng)估指標(biāo)[J];電力系統(tǒng)保護(hù)與控制;2015年11期

6 李海英;劉中銀;宋建成;;電力系統(tǒng)靜態(tài)安全狀態(tài)實(shí)時(shí)感知的相關(guān)向量機(jī)法[J];中國(guó)電機(jī)工程學(xué)報(bào);2015年02期

7 傅旭;付覽，

本文編號(hào)：2315596