Proceedings ArticleDOI
A random forest-based approach for voltage security monitoring in a power system
Michael Negnevitsky,Nikita Tomin,Victor Kurbatsky,Daniil Panasetsky,Alexey E. Zhukov,Christian Rehtanz +5 more
- pp 1-6
TLDR
This paper presents an on-line voltage security assessment scheme using periodically updated random forest-based decision trees and demonstrated the proposed method on the modified 53-bus IEEE power system.Abstract:
Voltage collapse is a critical problem that impacts power system operational security. Timely and accurate assessment of voltage security is necessary to detect alarm states in order to prevent a large-scale blackout. This paper presents an on-line voltage security assessment scheme using periodically updated random forest-based decision trees. We demonstrated the proposed method on the modified 53-bus IEEE power system. Results are presented and discussed.read more
Citations
More filters
Journal ArticleDOI
Construction of decision tree based on C4.5 algorithm for online voltage stability assessment
TL;DR: A case study on a practical power system demonstrates that DT can extract operating guidelines from offline voltage stability analysis results, and helps system operators assess voltage stability status in real-time.
Journal ArticleDOI
Improvement in the computational efficiency of a technique for assessing the reliability of electric power systems based on the Monte Carlo method
TL;DR: This paper demonstrates the effectiveness of two methods: a support vector machine and a random forest, and shows their performance when the Monte Carlo and quasi-Monte Carlo methods are used.
Journal ArticleDOI
Adaptive Online Monitoring of Voltage Stability Margin via Local Regression
TL;DR: The results show that the proposed VSM monitoring approach can be successfully employed in online voltage stability monitoring for real size systems, and the adaptivity of model and data endows the proposed approach with the advantage in the circumstances where large and unforeseen changes of system condition are inevitable.
Journal ArticleDOI
A review of machine learning for new generation smart dispatch in power systems
TL;DR: The characteristics and challenges of the new generation smart dispatch systems are analyzed, the framework of smart dispatch is proposed, and the development of machine learning algorithms is represented.
Journal ArticleDOI
A machine learning based optimized energy dispatching scheme for restoring a hybrid microgrid
TL;DR: In this paper, a system based on machine learning algorithm is implemented to forecast the security of a standalone microgrid and based on the forecasting, schedule multiple backup diesel generators under the contingency of loss of a major generating unit.
References
More filters
Journal ArticleDOI
Random Forests
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Proceedings ArticleDOI
Initial review of methods for cascading failure analysis in electric power transmission systems IEEE PES CAMS task force on understanding, prediction, mitigation and restoration of cascading failures
Ross Baldick,Badrul H. Chowdhury,Ian Dobson,Zhao Yang Dong,Bei Gou,David Hawkins,H. Huang,Manho Joung,Daniel S. Kirschen,Fangxing Li,Juan Li,Zuyi Li,Chen-Ching Liu,Lamine Mili,Stephen S. Miller,Robin Podmore,Kevin P. Schneider,Kai Sun,David Wang,Zhigang Wu,Pei Zhang,Wenjie Zhang,Xiao-Ping Zhang +22 more
TL;DR: In this article, the authors define cascading failure for blackouts and give an initial review of the current understanding, industrial tools, and the challenges and emerging methods of analysis and simulation.
Journal ArticleDOI
Decision Tree-Based Online Voltage Security Assessment Using PMU Measurements
Ruisheng Diao,Kai Sun,Vijay Vittal,R.J. O'Keefe,M.R. Richardson,Navin Bhatt,D. Stradford,S. Sarawgi +7 more
TL;DR: In this article, an online voltage security assessment scheme using synchronized phasor measurements and periodically updated decision trees (DTs) is presented. But the DTs are first trained offline using detailed voltage security analysis conducted using the past representative and forecasted 24-h ahead operating conditions.
Journal ArticleDOI
Machine learning approaches to power-system security assessment
TL;DR: A framework that uses machine learning and other automatic-learning methods to assess power-system security and exploits simulation models in parallel to screen diverse simulation scenarios of a system, yielding a large database.
Journal ArticleDOI
Catastrophe Predictors From Ensemble Decision-Tree Learning of Wide-Area Severity Indices
TL;DR: Wide-area-severity indices (WASI) derived from PMU measurements serve as the basis for building fast catastrophe predictors using random-forest (RF) learning and unexpectedly showed that the ensemble of trees in the RF is very robust in the presence of small changes in the training data and generalize across widely different network dynamics.