电力系统自动化
電力繫統自動化
전력계통자동화
AUTOMATION OF ELECTRIC POWER SYSTEMS
2014年
18期
72-78
,共7页
微电网(微网)%分布式电源%孤岛检测%数据挖掘%RELIEF 算法%功率不平衡度%元学习方法
微電網(微網)%分佈式電源%孤島檢測%數據挖掘%RELIEF 算法%功率不平衡度%元學習方法
미전망(미망)%분포식전원%고도검측%수거알굴%RELIEF 산법%공솔불평형도%원학습방법
microgrid%distributed generation%islanding detection%data mining%recursive elimimation of features (RELIEF) algorithm%power imbalance%meta-learning method
数据挖掘技术能有效解决孤岛检测中检测阈值的整定问题，已成为重要的孤岛检测方法。文中提出由关键特征识别、基学习器和元学习器等3个环节构成的孤岛检测数据挖掘系统。首先，分析了孤岛检测样本中的弱相关特征对分类的不利影响，提出利用 RELIEF(recursive elimination of features)算法首先识别孤岛检测的关键特征。然后，分析了单一分类器的归纳偏置现象，提出利用多个分类器的互补性提高孤岛检测的精度；最后，提出了基于元学习的新的孤岛检测方法。为验证上述方法的有效性，仿真算例中充分考虑了功率不平衡度、电压扰动等因素。仿真结果表明，上述3个环节对提高孤岛检测的精度和泛化能力具有重要作用。
數據挖掘技術能有效解決孤島檢測中檢測閾值的整定問題，已成為重要的孤島檢測方法。文中提齣由關鍵特徵識彆、基學習器和元學習器等3箇環節構成的孤島檢測數據挖掘繫統。首先，分析瞭孤島檢測樣本中的弱相關特徵對分類的不利影響，提齣利用 RELIEF(recursive elimination of features)算法首先識彆孤島檢測的關鍵特徵。然後，分析瞭單一分類器的歸納偏置現象，提齣利用多箇分類器的互補性提高孤島檢測的精度；最後，提齣瞭基于元學習的新的孤島檢測方法。為驗證上述方法的有效性，倣真算例中充分攷慮瞭功率不平衡度、電壓擾動等因素。倣真結果錶明，上述3箇環節對提高孤島檢測的精度和汎化能力具有重要作用。
수거알굴기술능유효해결고도검측중검측역치적정정문제，이성위중요적고도검측방법。문중제출유관건특정식별、기학습기화원학습기등3개배절구성적고도검측수거알굴계통。수선，분석료고도검측양본중적약상관특정대분류적불리영향，제출이용 RELIEF(recursive elimination of features)산법수선식별고도검측적관건특정。연후，분석료단일분류기적귀납편치현상，제출이용다개분류기적호보성제고고도검측적정도；최후，제출료기우원학습적신적고도검측방법。위험증상술방법적유효성，방진산례중충분고필료공솔불평형도、전압우동등인소。방진결과표명，상술3개배절대제고고도검측적정도화범화능력구유중요작용。
Data mining technique can effectively determine the threshold settings of islanding detection,which has become an important islanding detection approach.This paper proposes a comprehensive islanding detection data mining system consisting of three parts:critical feature identification,base learner and meta learner.First,the negative effect of inferior features of islanding detection samples on classification is analyzed.Correspondingly,the recursive elimimation of features(RELIEF) algorithm is provided to identify those critical features.Then,since a single classifier causes inductive bias phenomenon, multiple classifiers are combined to enhance islanding detection accuracy.Finally,a new approach based on meta-learning is proposed.In order to verify the effectiveness of the above method,power imbalance and voltage disturbance are taken into consideration in simulation examples.Results show that the three parts of the system perform remarkably well in improving the islanding detection accuracy and generalization ability.
