Transient Stability Assessment Based on Random Forest Algorithm
-
摘要: 利用随机森林算法,通过组合多棵基于随机向量的决策树对电力系统的暂态稳定性分类,提出了一种暂态稳定评估模型.在IEEE 16机和IEEE 50机测试系统进行的仿真验证了该模型对暂态稳定评估的有效性,其评估性能较经典决策树算法、人工神经网络、支持向量机和K最近邻方法均有提高.Abstract: A model for the power system transient stability assessment based on random forest algorithm was presented.This model combines decision trees which depend on the values of a random vector sampled independently and with the same distribution.Simulation results on the IEEE 16-generator and IEEE 50-generator test systems show the validity of the proposed method.Its assessment performance is better than decision tree,artificial neural networks,support vector machine and K nearest neighbor.
-
Key words:
- power system /
- transient stability /
- assessment /
- random forest algorithm /
- decision tree /
- model
-
PAVELLA M.Power system transient stability assessment-traditional vs modern methods[J].Control Engineering Practice,1998,6(10):1233-1246.[2] KUNDUR P,PASERBA J,AJJARAPU V,et al.Definition and classification of power system stability IEEE/CIGRE joint task force on stability terms and definitions[J].IEEE Transactions on Power Systems,2004,19(3):1387-1401.[3] 倪以信,陈寿松,张宝霖.动态电力系统的理论和分析[M].北京:清华大学出版社,2002.[4] DURKIN J,蔡竞峰,蔡自兴.决策树技术及其当前研究方向[J].控制工程,2005,12(1):15-21.DURKIN J,CAI Jingfeng,CAI Zixing.Decision tree technique and its current research[J].Control Engineering of China,2005,12(1):15-21.[5] WEHENKEL L,PAVELLA M,EUXIBIE E,et al.Decision tree based transient stability method a case study[J].IEEE Transactions on Power Systems,1994,9(1):459-469.[6] Rovnyak S,Kretsinger S,Thorp J,et al.Decision trees for real-time transient stability prediction[J].IEEE Transactions on Power Systems,1994,9(3):1417-1426.[7] TAN Pangning.数据挖掘导论[M].范明,范宏建,译.北京:人民邮电出版社,2006.[8] BREIMAN L.Random Forests[J].Machine Learning,2001,45(1):5-32.[9] 张华伟,王明文,甘丽新.基于随机森林的文本分类模型研究[J].山东大学学报(理学版),2006,41(3):139-143.ZHANG Huawei,WANG Mingwen,GAN Lixin.Automatic text classification model based on random forest[J].Journal of Shangdong University (Natural Science),2006,41(3):139-143.[10] HAM J,YANGCHI C,CRAWFORD M M,et al.Investigation of the random forest framework for classification of byperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):492-501.[11] 冯少荣.决策树算法的研究与改进[J].厦门大学学报(自然科学版),2007,46(4):496-500.FENG Shaorong.Research and improvement of decision trees algorithm[J].Journal of Xiamen University (Natural Science),2007,46(4):496-500.[12] QUINLAN J R.CA.5:programs for machine learning[M].San Mateo:Morgan Kaufmann Publishers,1993.[13] BREIMAN L,FRIEDMAN J,OLSHEN R,et al.Classification and regression trees[M].Monterey:Wadsworth,1984.[14] TSO S K,GU X P,ZENG Q Y,et al.An ANN-based multilevel classification approach using decomposed input space for transient stability assessment[J].Electric Power Systems Research,1998,46(3):259-266.[15] MOULIN L S,da SILVA A P A,EL-SHARKAWI M A,et al.Support vector machines for transient stability analysis of large-scale power systems[J].IEEE Transactions on Power Systems,2004,19(2):818-825.[16] WITTEN I H,FRANK E.Data mining:practical machine learning tools and techniques[M].Singapore:Elsevier,2005.[17] HANLEY J A,MCNEIL B J.The meaning and use of the area under a receiver operating characteristic (ROC) curve[J].Radiology,1982,143(1):29-36.[18] VITTAL V.Transient stability test systems for direct stability methods[J].IEEE Transaction on Power Systems,1992,7(1):37-43.
点击查看大图
计量
- 文章访问数: 1796
- HTML全文浏览量: 58
- PDF下载量: 750
- 被引次数: 0