The Experts below are selected from a list of 52911 Experts worldwide ranked by ideXlab platform
Yanzhen Zhou - One of the best experts on this subject based on the ideXlab platform.
-
Data driven method for transient Stability Prediction of power systems considering incomplete measurements
2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), 2017Co-Authors: Yanzhen Zhou, Hongbin Sun, Qinglai Guo, Liangliang HaoAbstract:This paper presents a novel data pre-processing for data-based method of transient Stability Prediction considering incomplete measurements. Firstly, the statistical features are utilized as the input features, of which number is independent from the power system's scale. Secondly, the dataset is expanded considering the situations when some generator measurements are unavailable randomly. Next, a k-difference-neighbor method is used to reduce the number of instances. After that, a new dataset is generated as the training set to train a more robustness classifier. Case studies are conducted on the New England 10-machine 39-bus system and Northeast Power Coordinated Council 48-machine 140-bus system respectively to verify the effectiveness of the proposed method.
-
Using Trajectory Clusters to Define the Most Relevant Features for Transient Stability Prediction Based on Machine Learning Method
Energies, 2016Co-Authors: Yanzhen Zhou, Liangliang HaoAbstract:To achieve rapid real-time transient Stability Prediction, a power system transient Stability Prediction method based on the extraction of the post-fault trajectory cluster features of generators is proposed. This approach is conducted using data-mining techniques and support vector machine (SVM) models. First, the post-fault rotor angles and generator terminal voltage magnitudes are considered as the input vectors. Second, we construct a high-confidence dataset by extracting the 27 trajectory cluster features obtained from the chosen databases. Then, by applying a filter–wrapper algorithm for feature selection, we obtain the final feature set composed of the eight most relevant features for transient Stability Prediction, called the global trajectory clusters feature subset (GTCFS), which are validated by receiver operating characteristic (ROC) analysis. Comprehensive simulations are conducted on a New England 39-bus system under various operating conditions, load levels and topologies, and the transient Stability predicting capability of the SVM model based on the GTCFS is extensively tested. The experimental results show that the selected GTCFS features improve the Prediction accuracy with high computational efficiency. The proposed method has distinct advantages for transient Stability Prediction when faced with incomplete Wide Area Measurement System (WAMS) information, unknown operating conditions and unknown topologies and significantly improves the robustness of the transient Stability Prediction system.
-
A Hierarchical Method for Transient Stability Prediction of Power Systems Using the Confidence of a SVM-Based Ensemble Classifier
Energies, 2016Co-Authors: Yanzhen Zhou, Junyong Wu, Zhihong Yu, Luyu JiAbstract:Machine learning techniques have been widely used in transient Stability Prediction of power systems. When using the post-fault dynamic responses, it is difficult to draw a definite conclusion about how long the duration of response data used should be in order to balance the accuracy and speed. Besides, previous studies have the problem of lacking consideration for the confidence level. To solve these problems, a hierarchical method for transient Stability Prediction based on the confidence of ensemble classifier using multiple support vector machines (SVMs) is proposed. Firstly, multiple datasets are generated by bootstrap sampling, then features are randomly picked up to compress the datasets. Secondly, the confidence indices are defined and multiple SVMs are built based on these generated datasets. By synthesizing the probabilistic outputs of multiple SVMs, the Prediction results and confidence of the ensemble classifier will be obtained. Finally, different ensemble classifiers with different response times are built to construct different layers of the proposed hierarchical scheme. The simulation results show that the proposed hierarchical method can balance the accuracy and rapidity of the transient Stability Prediction. Moreover, the hierarchical method can reduce the misjudgments of unstable instances and cooperate with the time domain simulation to insure the security and Stability of power systems.
Liangliang Hao - One of the best experts on this subject based on the ideXlab platform.
-
Data driven method for transient Stability Prediction of power systems considering incomplete measurements
2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), 2017Co-Authors: Yanzhen Zhou, Hongbin Sun, Qinglai Guo, Liangliang HaoAbstract:This paper presents a novel data pre-processing for data-based method of transient Stability Prediction considering incomplete measurements. Firstly, the statistical features are utilized as the input features, of which number is independent from the power system's scale. Secondly, the dataset is expanded considering the situations when some generator measurements are unavailable randomly. Next, a k-difference-neighbor method is used to reduce the number of instances. After that, a new dataset is generated as the training set to train a more robustness classifier. Case studies are conducted on the New England 10-machine 39-bus system and Northeast Power Coordinated Council 48-machine 140-bus system respectively to verify the effectiveness of the proposed method.
-
Using Trajectory Clusters to Define the Most Relevant Features for Transient Stability Prediction Based on Machine Learning Method
Energies, 2016Co-Authors: Yanzhen Zhou, Liangliang HaoAbstract:To achieve rapid real-time transient Stability Prediction, a power system transient Stability Prediction method based on the extraction of the post-fault trajectory cluster features of generators is proposed. This approach is conducted using data-mining techniques and support vector machine (SVM) models. First, the post-fault rotor angles and generator terminal voltage magnitudes are considered as the input vectors. Second, we construct a high-confidence dataset by extracting the 27 trajectory cluster features obtained from the chosen databases. Then, by applying a filter–wrapper algorithm for feature selection, we obtain the final feature set composed of the eight most relevant features for transient Stability Prediction, called the global trajectory clusters feature subset (GTCFS), which are validated by receiver operating characteristic (ROC) analysis. Comprehensive simulations are conducted on a New England 39-bus system under various operating conditions, load levels and topologies, and the transient Stability predicting capability of the SVM model based on the GTCFS is extensively tested. The experimental results show that the selected GTCFS features improve the Prediction accuracy with high computational efficiency. The proposed method has distinct advantages for transient Stability Prediction when faced with incomplete Wide Area Measurement System (WAMS) information, unknown operating conditions and unknown topologies and significantly improves the robustness of the transient Stability Prediction system.
Yutian Liu - One of the best experts on this subject based on the ideXlab platform.
-
Real-time transient Stability Prediction using incremental learning algorithm
IEEE Power Engineering Society General Meeting 2004., 1Co-Authors: Xiaodong Chu, Yutian LiuAbstract:Real-time transient Stability Prediction is an essential and challenging step of response-based transient Stability emergency controls. Machine learning methods including decision trees and artificial neural networks have the potential to be applied to the problem. To counter the inefficiency of common machine learning methods in learning new information, an incremental learning algorithm is employed to train an artificial neural network for real-time transient Stability Prediction. The resulted learning framework can readily be integrated into on-line dynamic security assessment. The effectiveness of such Prediction model is demonstrated by the simulation results of a practical power system.
-
ISCAS (4) - On-line learning applied to power system transient Stability Prediction
2005 IEEE International Symposium on Circuits and Systems, 1Co-Authors: Xiaodong Chu, Yutian LiuAbstract:A neural network-based system is proposed for power system transient Stability Prediction. A power system is a nonstationary environment, where operating conditions change from time to time. To make accurate Predictions of the transient Stability status of a power system, training examples are added continuously to reflect the most current operating condition. An on-line learning algorithm is employed to accommodate new training examples while avoiding negative interference. A real-world power system in China is used to demonstrate the effectiveness of the proposed transient Stability Prediction system. Simulation results show that the system performs well in different working modes and is able to make accurate Predictions.
Luyu Ji - One of the best experts on this subject based on the ideXlab platform.
-
A Hierarchical Method for Transient Stability Prediction of Power Systems Using the Confidence of a SVM-Based Ensemble Classifier
Energies, 2016Co-Authors: Yanzhen Zhou, Junyong Wu, Zhihong Yu, Luyu JiAbstract:Machine learning techniques have been widely used in transient Stability Prediction of power systems. When using the post-fault dynamic responses, it is difficult to draw a definite conclusion about how long the duration of response data used should be in order to balance the accuracy and speed. Besides, previous studies have the problem of lacking consideration for the confidence level. To solve these problems, a hierarchical method for transient Stability Prediction based on the confidence of ensemble classifier using multiple support vector machines (SVMs) is proposed. Firstly, multiple datasets are generated by bootstrap sampling, then features are randomly picked up to compress the datasets. Secondly, the confidence indices are defined and multiple SVMs are built based on these generated datasets. By synthesizing the probabilistic outputs of multiple SVMs, the Prediction results and confidence of the ensemble classifier will be obtained. Finally, different ensemble classifiers with different response times are built to construct different layers of the proposed hierarchical scheme. The simulation results show that the proposed hierarchical method can balance the accuracy and rapidity of the transient Stability Prediction. Moreover, the hierarchical method can reduce the misjudgments of unstable instances and cooperate with the time domain simulation to insure the security and Stability of power systems.
James S. Thorp - One of the best experts on this subject based on the ideXlab platform.
-
Transient Stability Prediction based on apparent impedance trajectory recorded by PMUs
International Journal of Electrical Power & Energy Systems, 2014Co-Authors: Anamitra Pal, Arun G. Phadke, James S. ThorpAbstract:Abstract Traditional methods for predicting transient Stability of power systems such as the direct method, the time domain approach, and the energy function methods, do not work well for real-time Stability Predictions. The use of Phasor Measurement Units (PMUs) appears to alleviate this problem by providing information in real-time for transient Stability assessment and enhancement. Techniques such as the rotor oscillation Prediction method based on time series have made the Prediction of system Stability possible for real-time applications. However, such methods often require more than 300 ms after the start of a transient event to make reliable Predictions. This paper proposes using the trajectory of the apparent impedance recorded by PMUs placed at strategic locations in the power system to rapidly predict transient Stability. From the simulations performed, it is realized that system Stability can be predicted in approximately 200 ms (12 cycles). The main advantage of this method is its simplicity as the PMUs can record the apparent impedance trajectories in real-time without any previous calculation. Moreover, using decision trees built in CART®, transient Stability Prediction becomes straightforward and computationally very fast. The optimum locations for PMU placement can also be determined using this technique.
