An Intelligent Data Mining-Based Fault Detection and Classification Strategy for Microgrid

Abstract

The specific characteristics and operations of microgrid cause protection problems due to high penetration of distributed energy resources. To resolve these issues, the proposed scheme employs the Hilbert transform and data mining approach to protect the microgrid. First, the Hilbert transform is used to preprocess the faulted voltage and current signals to extract the sensitive fault features. Then, the obtained data set of the extracted features is input to the logistic regression classifier for fault detection. Later, fault classification is done by training the AdaBoost classifier. In the proposed scheme, the simulation results for feature extractions are evaluated on a standard International Electrotechnical Commission (IEC) medium voltage microgrid, compatible with MATLAB/SIMULINK software environment, whereas, Python is used for training and testing of data mining model. The results are evaluated under grid-connected and islanded modes for both looped and radial configurations by simulating various fault and no-fault cases. The results show that the accuracy of the proposed logistic regression and AdaBoost classifier is higher when compared to decision tree, support vector machine, and random forest methods. The results further validate the robustness of the proposed method against the measurement noise.

Probabilistic weighted voting model using multiple machine learning methods for fault detection and classification

“…A comprehensive comparison has been carried out regarding method, location measurement, noise effect, overall accuracy, class size, statistical analysis and performance (Mishra and Rout, 2018;Bukhari et al, 2020;Mishra et al, 2019;Abdelgayed et al, 2018;Gush et al, 2019;Baloch and Muhammad, 2021). In only these studies (Mishra et al, 2019;Gush et al, 2019;Baloch and Muhammad, 2021), the effects of noisy samples have been considered to verify the proposed method's effectiveness.…”

Research on Spatial and Dynamic Planning Methods for Settlement Buildings Based on Data Mining

“…e quality of the data preparation stage directly affects the feasibility of the subsequent steps or the quality and effectiveness of the whole mining [23]. Usually, the data preparation stage can be subdivided into three steps: data integration, data cleaning, and data preprocessing.…”

A Symmetrical-Asymmetrical Fault Characteristics Analysis within Cogeneration Power Plant in Izmir, Turkey: An Experimental Assessment

“…A new concept has emerged in order to use energy efficiency and different resources. Dissimilar, the conventional centralized generation, distributed generation (DG) aims a strategy in which a part of the electric power is produced and transmited to clients with small production units allocated near to the burdens [1][2][3][4]. The widespread use of DG not only increases economic efficiency, but also benefits improvements in energy reliability [5].…”