Reliability evaluation of composite generation and transmission systems via binary logistic regression and parallel processing

Campos, Fabrício S.V.; Assis, Fernando A.; Silva, Armando M. Leite da; Coelho, A.; Moura, Rodolfo A. R.; Schroeder, Marco Aurélio O.

doi:10.1016/j.ijepes.2022.108380

Cited by 14 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Logistic Regression : Logistic regression, a prevalent linear technique employed for classification, utilizes a logistic function to model the probability of a specific class or event [ 96 ]. The following equation represents the logistic function:

…”

Section: Methodsmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Klaar,

Seman,

Mariani

et al. 2024

Sensors

View full text Add to dashboard Cite

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from the time series data. This paper proposes a combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods, combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

show abstract

…”

Section: Methodsmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Klaar,

Seman,

Mariani

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Logistic Regression: Logistic regression, a prevalent linear technique employed for classification, utilizes a logistic function to model the probability of a specific class or event [96]. The following equation represents the logistic function:…”

Section: Classification Methodsmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Medium Voltage Insulator Classification based on Ultrasound Sensor

Klaar,

Seman,

Mariani

et al. 2024

Preprint

View full text Add to dashboard Cite

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from time series data. This paper proposes the combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves respectively an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

show abstract

“…To solve this problem, two perspectives of research emerged: (i) pattern detection; and (ii) variance reduction techniques (VRTs). The first one attempts to directly reduce the runtime of adequacy analysis, either by constructive polynomial neural networks GMDH [6,7], k-nearest neighbour algorithm [8], support vector machine [9], convolutional neural network [10], logistic regression [11] etc. The second one was also applied via several techniques: control variates [12], antithetic variates [13], Latin hypercube sampling [14,15], state space pruning [16], continuous time Markov chain model [17], subset simulation [18], uniform design [19].…”

Section: Introductionmentioning

confidence: 99%

Composite reliability assessment of systems with grid‐edge renewable resources via quasi‐sequential Monte Carlo and cross‐entropy techniques

Manso,

Leite da Silva,

Milhorance

et al. 2023

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

The still growing share of intermittent renewable sources in the electric energy matrix is a factor that greatly increases the complexity of modelling electrical power systems. Although its exploitation is conditioned to the geographic location where the natural resource emerges itself, when this location coincides with the grid‐edge of the system, close to the consumer, the composite reliability assessment is exposed to the combination of two problems: (i) representation of the intermittent energy availability of generators; and (ii) failure event rarity. To address the first problem, a fast Monte Carlo tool capable of representing chronological aspects can be used. For the second problem, an efficient variance reduction technique that adapts well to the composite problem of generation and transmission must be established. Therefore, a quasi‐sequential Monte Carlo simulation tool aided by importance sampling via the cross‐entropy method is proposed as an efficient and robust procedure for evaluating the composite reliability of systems with renewable participation at grid‐edge. The method is evaluated through a modified version of the IEEE Reliability Test System ‐ 1996, which presents renewable generation in consumer load buses and rarity in the composite failure.

show abstract

Reliability evaluation of composite generation and transmission systems via binary logistic regression and parallel processing

Cited by 14 publications

References 21 publications

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Medium Voltage Insulator Classification based on Ultrasound Sensor

Composite reliability assessment of systems with grid‐edge renewable resources via quasi‐sequential Monte Carlo and cross‐entropy techniques

Contact Info

Product

Resources

About