Fault Detection, Isolation and Service Restoration in Modern Power Distribution Systems: A Review

Srivastava, Ishan; Bhat, Sunil; Vardhan, B V Surya; Bokde, Neeraj Dhanraj

doi:10.3390/en15197264

Cited by 19 publications

(10 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MAE predicts the average of the modulated difference between actual and predicted, which is computed in (5). The average of the squared difference between average and predicted values are given by MSE which is calculated in (6). R 2 explains the variance in the linear dependency of a predicted value with respect to the true value which is determined in (7).…”

Section: Statistical Parameter Descriptionsmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Analysis of Hyperparameter Tuned Stochastic Short Term Load Forecasting for Power System Operator

et al. 2023

Self Cite

View full text Add to dashboard Cite

Intermittency in the grid creates operational issues for power system operators (PSO). One such intermittent parameter is load. Accurate prediction of the load is the key to proper planning of the power system. This paper uses regression analyses for short-term load forecasting (STLF). Assumed load data are first analyzed and outliers are identified and treated. The cleaned data are fed to regression methods involving Linear Regression, Decision Trees (DT), Support Vector Machine (SVM), Ensemble, Gaussian Process Regression (GPR), and Neural Networks. The best method is identified based on statistical analyses using parameters such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), R2, and Prediction Speed. The best method is further optimized with the objective of reducing MSE by tuning hyperparameters using Bayesian Optimization, Grid Search, and Random Search. The algorithms are implemented in Python and Matlab Platforms. It is observed that the best methods obtained for regression analysis and hyperparameter tuning for an assumed data set are Decision Trees and Grid Search, respectively. It is also observed that, due to hyperparameter tuning, the MSE is reduced by 12.98%.

show abstract

Section: Statistical Parameter Descriptionsmentioning

confidence: 99%

“…The emergence of machine learning techniques has helped power system operators to predict load using various stochastic approaches. In some recently reported work, machine learning methodology is used to solve outage management problems in power distribution systems [6].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Analysis of Hyperparameter Tuned Stochastic Short Term Load Forecasting for Power System Operator

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this sense, during various decades, efforts were focused on controllability, reliability, reduced costs, and efficiency; however, sophisticated technologies are emerging for a sustainable and resilient future of power grids [2]. Moreover, various technologies have appeared and are assuming predominance, promoting a set of pertinent synergies among diverse areas [3]. A review on multilevel power management systems for future power grids is presented in [4], wherein benefits, drawbacks, challenges, and limitations are discussed.…”

Section: Electrical Power Gridsmentioning

confidence: 99%

The Future of Electrical Power Grids: A Direction Rooted in Power Electronics

Monteiro

Afonso

2023

Energies

View full text Add to dashboard Cite

Electrical power grids are changing with a focus on ensuring energy sustainability and enhanced power quality for all sectors. Over the last few decades, there has been a change from a centralized to a decentralized paradigm, which is the consequence of a large-scale incorporation of new electrical technologies and resultant equipment. Considering the foreseeable continuation of changes in electrical power grids, a direction rooted in power electronics with a focus on hybrid AC/DC grids, including the support of solid-state transformers and unified systems, is presented in this paper. Converging on hybrid AC/DC grids, DC grids (structured as unipolar and bipolar) and coupled and decoupled AC configurations are analyzed. On the other hand, in the context of solid-state transformers, feasible structures are analyzed, including the establishment of hybrid AC/DC grids, and the assessment of gains for boosting power quality is presented. Unified power electronics systems are also of fundamental importance when contextualized within the framework of future power grids, presenting higher efficiency, lower power stages, and the possibility of multiple operations to support the main AC grid. In this paper, such subjects are discussed and contextualized within the framework of future power grids, encompassing highly important and modern structures and their associated challenges. Various situations are characterized, revealing a gradual integration of the cited technologies for future power grids, which are also known as smart grids.

show abstract

“…Some researchers focus on substation fault detection systems, and various methods for substation fault diagnosis have been proposed. These methods mainly include expert systems [2] , artificial neural networks [3] , Petri nets [4] , Bayesian networks [5] , and so on. For example, Samimi et al [6] give the comprehensive use of sensors including electrical sensors, mechanical sensors, optical sensors, chemical sensors, and acoustic sensors to monitor the operational statuses of substations.…”

Section: Introductionmentioning

confidence: 99%

Fault detection method for substation in smart power grid: a random forest approach

Cai,

Xia,

Zhu

et al. 2024

Fourth International Conference on Machine Learning and Computer Application (ICMLCA 2023)

View full text Add to dashboard Cite

As the scale and complexity of power grid continue to increase, some abnormal events pose a significant threat to the security and stability of the power grid. This paper presents a novel approach based on the Random Forest algorithm for the substation fault detection. The approach is designed to improve the accuracy and efficiency of fault detection of substation equipment. By utilizing the machine learning techniques, specifically taking the decision tree algorithm as the base model, and following the principles of ensemble learning, a Random Forest algorithm is designed from multiple decision trees. The bagging technique is employed to create an ensemble learning model. The data preprocessing phase includes some crucial steps such as feature selection, interpolation preprocessing, normalization preprocessing, and the creations of training and testing sets. Additionally, appropriate evaluation metrics are chosen to assess the performance of our proposed approach. The experiments conducted on substation fault data collected from Suzhou City from January 2023 to August 2023 demonstrate the effectiveness of the approach. The dataset comprises six monitoring signals regarding the substations, with labels indicating the respective types of substation faults. The experiment results indicate that our proposed Random Forest-based approach achieves a extremely high accuracy rate compared to other baseline approaches. This approach can also help to enhance the substation fault detection capabilities and ensure the reliability and stability of power grid system.

show abstract

Fault Detection, Isolation and Service Restoration in Modern Power Distribution Systems: A Review

Cited by 19 publications

References 110 publications

A Comparative Analysis of Hyperparameter Tuned Stochastic Short Term Load Forecasting for Power System Operator

A Comparative Analysis of Hyperparameter Tuned Stochastic Short Term Load Forecasting for Power System Operator

The Future of Electrical Power Grids: A Direction Rooted in Power Electronics

Fault detection method for substation in smart power grid: a random forest approach

Contact Info

Product

Resources

About