scholarly journals Sparse Signal Reconstruction on Fixed and Adaptive Supervised Dictionary Learning for Transient Stability Assessment

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7995
Author(s):  
Raoult Teukam Dabou ◽  
Innocent Kamwa ◽  
Jacques Tagoudjeu ◽  
Francis Chuma Mugombozi
Keyword(s):  
Dictionary Learning ◽  
Transient Stability ◽  
Signal Reconstruction ◽  
Test System ◽  
Discrete Wavelet ◽  
Stability Assessment ◽  
Stability Prediction ◽  
Status Assessment ◽  
Supervised Dictionary Learning ◽  
Value Decomposition

Fixed and adaptive supervised dictionary learning (SDL) is proposed in this paper for wide-area stability assessment. Single and hybrid fixed structures are developed based on impulse dictionary (ID), discrete Haar transform (DHT), discrete cosine transform (DCT), discrete sine transform (DST), and discrete wavelet transform (DWT) for sparse features extraction and online transient stability prediction. The fixed structures performance is compared with that obtained from transient K-singular value decomposition (TK-SVD) implemented while adding a stability status term to the optimization problem. Stable and unstable dictionary learning are designed based on datasets recorded by simulating thousands of contingencies with varying faults, load, and generator switching on the IEEE 68-bus test system. This separate supervised learning of stable and unstable scenarios allows determining root mean square error (RMSE), useful for online stability status assessment of new scenarios. With respect to the RMSE performance metric in signal reconstruction-based stability prediction, the present analysis demonstrates that [DWT], [DHT|DWT] and [DST|DHT|DCT] are better stability descriptors compared to K-SVD, [DHT], [DCT], [DCT|DWT], [DHT|DCT], [ID|DCT|DST], and [DWT|DHT|DCT] on test datasets. However, the K-SVD approach is faster to execute in both off-line training and real-time playback while yielding satisfactory accuracy in transient stability prediction (i.e., 7.5-cycles decision window after fault-clearing).

Application of Extreme Learning Machine in Transient Stability Assessment of Power Systems

2013 ◽  
Vol 392 ◽  
pp. 544-547 ◽  
Author(s):  
Yang Li ◽  
Xue Ping Gu
Keyword(s):  
Power Systems ◽  
Extreme Learning Machine ◽  
Rough Sets ◽  
Transient Stability ◽  
Test System ◽  
System Level ◽  
Stability Assessment ◽  
Fuzzy Rough Sets ◽  
Operation Condition ◽  
Learning Machine

This paper presents a new method for transient stability assessment (TSA) of power systems using kernel fuzzy rough sets and extreme learning machine (ELM). Considering the possible real-time information provided by phasor measurement units, a group of system-level classification features were firstly extracted from the power system operation condition to construct the original feature set. Then kernelized fuzzy rough sets were used to reduce the dimension of input space, and ELM was employed to build a TSA model. The effectiveness of the proposed method is validated by the simulation results on the New England 39-bus test system.

Novel Real-Time Stability Assessment Algorithm Based on Synchro-Phasors Measurement and Parallel Algorithms for Multi-Machine Networks.

2012 ◽  
Vol 13 (3) ◽  
Author(s):  
Mohamed Abdelwahhab Ali ◽  
Wagdy Mohamed Mansour ◽  
Wael Refaat Anis ◽  
Fahmy Metwally Bendary
Keyword(s):  
Power Systems ◽  
Parallel Algorithms ◽  
Real Time ◽  
Transient Stability ◽  
Test System ◽  
System Stability ◽  
Stability Assessment ◽  
Varying Coefficients ◽  
Rotor Angle ◽  
Time Varying Coefficients

Abstract The introduction of wide area measurements has brought a need for real time assessment methods of power systems, which are accurate and fast. The time varying coefficients in synchronous machine equations make it difficult to find solutions to obtain machine voltages, currents and flux linkages when expressed in phase quantities under transient conditions. The paper presents an approach to design power system transient stability assessment using direct methods for a multi-machine network based on multiple synchronized phasors, measured from Phasor Measurement Units (PMUs) and generator parameters. The generator rotor angle was derived from phasor measurements of voltage and current, and generator parameters using direct algorithm . The method assumes that a temporary fault is applied to the system therefore the pre-fault and post-fault conditions are similar. The multi-machine system was reduced to groups denoted Single Machine to Equivalent Bus (SMEB) models and another groups denoted Load Equivalent Bus (LEB) using Parallel Algorithms (PAs) [1]. The use of these PAs eliminates the SPMUs at each bus in the system, and it is required number of SPMUs only equals the number of generator buses. So that, the Equal Area Criterion in both rotor angle domain and time domain can be applicable for the SMEBs groups to assess the system stability in real-time through the Synchro-Phasors Measurements Units (SPMUs). A temporary three phase fault was simulated at test system comprises 2-machine, 8-bus network for validating the novel algorithm.

scholarly journals An Improved Power System Transient Stability Prediction Model Based on mRMR Feature Selection and WTA Ensemble Learning

2020 ◽  
Vol 10 (7) ◽  
pp. 2255
Author(s):  
Jun Liu ◽  
Huiwen Sun ◽  
Yitong Li ◽  
Wanliang Fang ◽  
Shuanbao Niu
Keyword(s):  
Feature Selection ◽  
Power Systems ◽  
Power System ◽  
Prediction Model ◽  
Ensemble Learning ◽  
Prediction Accuracy ◽  
Transient Stability ◽  
Stability Assessment ◽  
Stability Prediction ◽  
Electromagnetic Power

Fast online transient stability assessment (TSA) is very important to maintain the stable operation of power systems. However, the existing transient stability assessment methods suffer the drawbacks of unsatisfactory prediction accuracy, difficult applicability, or a heavy computational burden. In light of this, an improved high accuracy power system transient stability prediction model is proposed, based on min-redundancy and max-relevance (mRMR) feature selection and winner take all (WTA) ensemble learning. Firstly, the contributions of four different series of raw sampled data from all of the three-time stages, namely the pre-fault, during-fault and post-fault, to transient stability are compared. The new feature of generator electromagnetic power is introduced and compared with three conventional types of input features, through a support vector machine (SVM) classifier. Furthermore, the two types of most contributive input features are obtained by the mRMR feature selection method. Finally, the prediction results of the electromagnetic power of generators and the voltage amplitude of buses are combined using the WTA ensemble learning method, and an improved transient stability prediction model with higher accuracy for unstable samples is obtained, whose overall prediction accuracy would not decrease either. The real-time data collected by wide area monitoring systems (WAMS) can be fed into this model for fast online transient stability prediction; the results can also provide a basis for the future emergency control decision-making of power systems.

A Sensitivity Analysis Method for Transient Stability Assessment Feature Selection

2013 ◽  
Vol 448-453 ◽  
pp. 2447-2454
Author(s):  
De Quan Yao ◽  
Shuai Zhao ◽  
Hong Jie Jia ◽  
Hao Liang
Keyword(s):  
Sensitivity Analysis ◽  
New England ◽  
Transient Stability ◽  
Test System ◽  
Impact Factors ◽  
Features Selection ◽  
Stability Assessment ◽  
Analysis Method ◽  
Sensitivity Matrix ◽  
Sensitivity Analysis Method

Input features selection is the premise of transient stability assessment base on neural network method. This paper adopts sensitivity analysis method to calculate the sensitivity-matrix of input features. And on this basis it defines important indexes and impact factors. Based on the gap information of impact factors, it selects the optimal subset of input features, which helps to decrease the redundant information and reduce the dimension of input features. This approach can improve the efficiency and accuracy of transient stability assessment effectively. The results of New England test system demonstrate the validity of the approach.

Transient Stability Assessment of Power System Using Support Vector Machine with Generator Phase Plane Trajectory Inputs

2013 ◽  
Vol 732-733 ◽  
pp. 1038-1042
Author(s):  
Ke Wang ◽  
Da Hai You ◽  
Cheng Long ◽  
Wei Hua Chen ◽  
Gang Wang
Keyword(s):  
Support Vector Machine ◽  
Power System ◽  
Transient Stability ◽  
Phase Plane ◽  
Test System ◽  
Support Vector ◽  
Svm Classifier ◽  
Stability Assessment ◽  
Plane Trajectory ◽  
Electromagnetic Power

Transient stability assessment (TSA) is part of dynamic stability assessment of power systems, which involves the assessment of the systems ability to remain synchronism under credible disturbances. Recent research shows that transient stability status of a power system following a large disturbance such as a fault can be early predicted based on phase plane trajectories of generator variables. Based on this, a binary support vector machine (SVM) classifier with generator phase plane trajectory inputs was trained to predict the transient stability status. In order to find the best trajectory inputs, three different types of phase plane trajectories were designed. By investigating effectiveness of the three trajectories with New England 39-bus test system, classifiers with phase plane trajectories of electromagnetic power as inputs achieved better predictions than other two types of trajectories. The highest accuracy achieved by the classifier with inputs of electromagnetic power phase plane trajectories is 99.336% which can meet requirements of practical application.

Sign in / Sign up

Export Citation Format

Share Document