A weighted random forest approach to improve predictive performance for power system transient stability assessment

Transient stability assessment (TSA) based on machine learning techniques is a classical problem of classification. In this paper, a new transient stability assessment model using the weighted random forest (WRF) is proposed. Random forest, which runs fast and can scale to very high dimensional datasets, is one of the most popular methods applied to TSA after faults occurred. However, in the actual operation of modern power system, unstable samples constitute only a very small minority of the cases. Besides, the traditional random forest algorithm does not work very well on imbalanced data. To tackle the problem, weighted random forest is adopted to lean the interest towards to the correct classification of rare class, and improve the prediction performance. Case study on the New England 39-bus test power system exhibits that WRF has better performance than the original random forest.

[1]  Qian Qing-quan.  Transient Stability Assessment Based on Random Forest Algorithm , 2008 .

[2]  Miao He,et al.  Online dynamic security assessment with missing pmu measurements: A data mining approach , 2013, IEEE Transactions on Power Systems.

[3]  I. Kamwa,et al.  Causes of the 2003 major grid blackouts in North America and Europe, and recommended means to improve system dynamic performance , 2005, IEEE Transactions on Power Systems.

[4]  Rui Zhang,et al.  Real-time transient stability assessment model using extreme learning machine , 2011 .

[5]  Xin Li,et al.  Power System Transient Stability Assessment Based on Adaboost and Support Vector Machines , 2012, 2012 Asia-Pacific Power and Energy Engineering Conference.

[6]  R. Grondin,et al.  Time-varying contingency screening for dynamic security assessment using intelligent-systems techniques , 2001, PICA 2001. Innovative Computing for Power - Electric Energy Meets the Market. 22nd IEEE Power Engineering Society. International Conference on Power Industry Computer Applications (Cat. No.01CH37195).

[7]  Janath Geeganage,et al.  Application of energy-based power system features for dynamic security assessment , 2015, 2015 IEEE Power & Energy Society General Meeting.

[8]  Constantin F. Aliferis,et al.  Are Random Forests Better than Support Vector Machines for Microarray-Based Cancer Classification? , 2007, AMIA.

[9]  N. Peng,et al.  A SVM-kNN method for quasar-star classification , 2013, Science China Physics Mechanics and Astronomy.

[10]  Francisco Silva-Mata,et al.  An Approach to Automatic Target Recognition in Radar Images Using SVM , 2006, CIARP.

[11]  Bo Wang,et al.  Power System Transient Stability Assessment Based on Big Data and the Core Vector Machine , 2016, IEEE Transactions on Smart Grid.

[12]  Deng Gui-ping.  Preliminary Analysis of Large Scale Blackout in Western Europe Power Grid on November 4 and Measures to Prevent Large Scale Blackout in China , 2006 .

[13]  Canicious Abeynayake,et al.  Automatic target detection and discrimination algorithm applicable to ground penetrating radar data , 2015, Defense + Security Symposium.

[14]  Zhihua Cai,et al.  Evaluation Measures of the Classification Performance of Imbalanced Data Sets , 2009 .

[15]  Wei Hu,et al.  A novel stability classifier based on reformed support vector machines for online stability assessment , 2015, 2015 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC).