A comparative analysis of artificial neural network and support vector machine for online transient stability prediction considering uncertainties

Shahzad, Umair

doi:10.1080/1448837x.2021.2022999

Cited by 9 publications

(5 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where w is an m-dimensional weighted column vector; b is a constant representing the offset term; ξ i is the relaxation variable corresponding to x i , which represents the tolerance of sample classification errors; C is the margin parameter, also known as the penalty factor, which represents the degree of punishment for sample classification errors; φ(x) is a high-dimensional function that maps the vector x from the original space to the characteristic space, and is usually called "kernel function". There are many different types of kernel functions, among which the radial basis function can approximate any function with any error, and there is only one undetermined parameter, which applies to both large and small samples [8]. Therefore, the radial basis kernel function is adopted in this paper, and its expression is…”

Section: Support Vector Machinementioning

confidence: 99%

“…On the contrary, the data-driven methods employ a series of data tricks (including data preprocessing, data transformation, spatial mapping, etc. ), and various modern advanced machine learning algorithms (including support vector machine [7][8][9], Bayesian method [10], decision tree method [11,12], random forest method [13,14], deep learning method [15][16][17][18][19][20][21], active learning method [22], etc.) to seek the valuable information from the data, and obtain the assessment results of the transient stability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parallel Integrated Model-Driven and Data-Driven Online Transient Stability Assessment Method for Power System

Zhang,

Han,

Zhang

et al. 2023

Energy Engineering

View full text Add to dashboard Cite

More and more uncertain factors in power systems and more and more complex operation modes of power systems put forward higher requirements for online transient stability assessment methods. The traditional modeldriven methods have clear physical mechanisms and reliable evaluation results but the calculation process is time-consuming, while the data-driven methods have the strong fitting ability and fast calculation speed but the evaluation results lack interpretation. Therefore, it is a future development trend of transient stability assessment methods to combine these two kinds of methods. In this paper, the rate of change of the kinetic energy method is used to calculate the transient stability in the model-driven stage, and the support vector machine and extreme learning machine with different internal principles are respectively used to predict the transient stability in the data-driven stage. In order to quantify the credibility level of the data-driven methods, the credibility index of the output results is proposed. Then the switching function controlling whether the rate of change of the kinetic energy method is activated or not is established based on this index. Thus, a new parallel integrated model-driven and datadriven online transient stability assessment method is proposed. The accuracy, efficiency, and adaptability of the proposed method are verified by numerical examples.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Parallel Integrated Model-Driven and Data-Driven Online Transient Stability Assessment Method for Power System

Zhang,

Han,

Zhang

et al. 2023

Energy Engineering

View full text Add to dashboard Cite

show abstract

“…The results showed that ANN training precision was higher than SVM, and the training time was less than SVM. Therefore, the classification and computing performance of ANN were superior [7]. Fard compared multiple artificial neural network (ANN) methods to better predict the number of COVID-19 cases at N steps ahead of the current time.…”

Section: Related Workmentioning

confidence: 99%

“…In equation ( 5), θ is the mapping of the sigmoid function. The expression of the forgetting gate at t is shown in equation (7). In equation (7), σ is the sigmoid function, W f is the learnable weight parameter, and b f is the bias vector parameter.…”

Section: Journal Of Applied Mathematicsmentioning

confidence: 99%

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Shang

2023

Journal of Applied Mathematics

View full text Add to dashboard Cite

Flexible job-shop scheduling problem (FJSP) is a new research hotspot in the field of production scheduling. To solve the multiobjective FJSP problem, the production of flexible job shop can run normally and quickly. This research takes into account various characteristics of FJSP problems, such as the need to ensure the continuity and stability of processing, the existence of multiple objectives in the whole process, and the constant complexity of changes. It starts with deep learning neural networks and genetic algorithms. Long short-term memory (LSTM) and convolutional neural networks (CNN) are combined in deep learning neural networks. The new improved algorithm is based on the combination of deep learning neural networks LSTM and CNN with genetic algorithm (GA), namely, CNN-LSTM-GA algorithm. Simulation results showed that the accuracy of the CNN-LSTM-GA algorithm was between 85.2% and 95.3% in the test set. In the verification set, the minimum accuracy of the CNN-LSTM-GA algorithm was 84.6%, both of which were higher than the maximum accuracy of the other two algorithms. In the FJSP simulation experiment, the AUC value of the CNN-LSTM-GA algorithm was 0.92. After 40 iterations, the F1 value of the CNN-LSTM-GA algorithm remained above 0.8, which was significantly higher than the other two algorithms. CNN-LSTM-GA is superior to the other two algorithms in terms of prediction accuracy and overall performance of FJSP. It is more suitable for solving the discrete manufacturing job scheduling problem with FJSP characteristics. This study significantly raises the utilisation rate of the assembly shop’s equipment, optimises the scheduling of FJSP, and fully utilises each processing device’s versatile characteristics, which are quite useful for the production processes of domestic vehicle manufacturing companies.

show abstract

“…The simulation results demonstrated that the presented approach could lessen the likelihood of misclassification. Reference [70] proposed a comparative analysis of two different machine learning (ML) algorithms, i.e., ANN and SVM, for online transient stability prediction, considering various uncertainties, such as load, network topology, fault type, fault location, and Fault Clearing Time (FCT). The results for the IEEE 14-bus system demonstrated that both ANN and SVM can rapidly estimate the transient stability; however, ANN outclassed SVM as its classification performance and computational performance were established to be greater.…”

Section: Kernel Equationmentioning

confidence: 99%

Prediction of Probabilistic Transient Stability Using Support Vector Machine

Shahzad

2022

TEEE

Self Cite

View full text Add to dashboard Cite

Transient stability assessment is an integral part of dynamic security assessment of power systems. Traditional methods of transient stability assessment, such as time domain simulation approach and direct methods, are appropriate for offline studies and thus, cannot be applied for online transient stability prediction, which is a major requirement in modern power systems. This motivated the requirement to apply an artificial intelligence-based approach. In this regard, supervised machine learning is beneficial for predicting transient stability status, in the presence of uncertainties. Therefore, this paper examines the application of a binary support vector machine-based supervised machine learning, for predicting the transient stability status of a power system, considering uncertainties of various factors, such as load, faulted line, fault type, fault location and fault clearing time. The support vector machine is trained using a Gaussian Radial Basis function kernel and its hyperparameters are optimized using Bayesian optimization. Results obtained for the IEEE 14-bus test system demonstrated that the proposed method offers a fast technique for probabilistic transient stability status prediction, with an excellent accuracy. DIgSILENT PowerFactory and MATLAB was utilized for transient stability time-domain simulations (for obtaining training data for support vector machine) and for applying support vector machine, respectively.

show abstract

A comparative analysis of artificial neural network and support vector machine for online transient stability prediction considering uncertainties

Cited by 9 publications

References 59 publications

Parallel Integrated Model-Driven and Data-Driven Online Transient Stability Assessment Method for Power System

Parallel Integrated Model-Driven and Data-Driven Online Transient Stability Assessment Method for Power System

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Prediction of Probabilistic Transient Stability Using Support Vector Machine

Contact Info

Product

Resources

About