【摘要】：隨著大規(guī)�？稍偕茉床粩嗖⒕W(wǎng),對(duì)電網(wǎng)的實(shí)時(shí)調(diào)控能力提出了更高的要求。傳統(tǒng)的基于在線關(guān)鍵斷面自動(dòng)發(fā)現(xiàn)以及基于連續(xù)潮流的在線極限傳輸容量計(jì)算方法,模型復(fù)雜、計(jì)算周期長(zhǎng),難以做到在線運(yùn)行。從數(shù)據(jù)驅(qū)動(dòng)的角度出發(fā),首先將電網(wǎng)實(shí)時(shí)運(yùn)行狀態(tài)的潮流量抽象為該時(shí)刻電網(wǎng)的運(yùn)行特征;然后對(duì)所有特征進(jìn)行聚類和分布式特征選擇;最后運(yùn)用人工神經(jīng)網(wǎng)絡(luò)建立所選特征與關(guān)鍵斷面極限傳輸容量之間的對(duì)應(yīng)關(guān)系。算例分析表明,所提基于人工神經(jīng)網(wǎng)絡(luò)的電力系統(tǒng)精細(xì)化安全運(yùn)行規(guī)則,在保證時(shí)間效率的前提下,能夠在一定程度上提高關(guān)鍵斷面極限傳輸容量的預(yù)測(cè)準(zhǔn)確度。
[Abstract]:With the continuous grid connection of large-scale renewable energy, the real-time regulation and control ability of power grid is put forward higher requirements. The traditional calculation method of online limit transmission capacity based on online key section automatic discovery and continuous power flow is complex and the calculation period is long, so it is difficult to run online. From the point of view of data-driven, the tidal flow of the real-time operation state of the power grid is abstracted as the operation characteristics of the power grid at that time, and then all the features are clustering and distributed feature selection. Finally, the artificial neural network is used to establish the corresponding relationship between the selected features and the ultimate transmission capacity of the key section. The example analysis shows that the proposed fine and safe operation rules of power system based on artificial neural network can improve the prediction accuracy of critical section limit transmission capacity to a certain extent on the premise of ensuring time efficiency.
【作者單位】： 廣東電網(wǎng)有限責(zé)任公司電力調(diào)度控制中心;北京清大高科系統(tǒng)控制有限公司;
【基金】：南方電網(wǎng)科技項(xiàng)目(GDKJ00000058)“面向大數(shù)據(jù)的復(fù)雜大電網(wǎng)安全特征選擇和知識(shí)發(fā)現(xiàn)的關(guān)鍵技術(shù)與示范應(yīng)用”~~
【分類號(hào)】：TM732;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 楊新華;王關(guān)平;侯z，

本文編號(hào)：2487394