A Robust Fault Detection and Location Prediction Module Using Support Vector Machine and Gaussian Process Regression for AC Microgrid
| Autor: | Adhishree Srivastava, S. K. Parida |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Support vector machine
Control and Systems Engineering Computer science Robustness (computer science) Reliability (computer networking) Real-time computing Microgrid Sensitivity (control systems) Electrical and Electronic Engineering Fault (power engineering) Grid Industrial and Manufacturing Engineering Fault detection and isolation |
| Zdroj: | IEEE Transactions on Industry Applications. 58:930-939 |
| ISSN: | 1939-9367 0093-9994 |
| Popis: | Better reliability of power supply is assured with the inculcation of DGs in a distribution network. Smart sensors and latest grid communication protocols have played a crucial role in the development of intelligent MGs. Conventional protection schemes do not provide reliable performance when implemented in MGs. This paper proposes an approach which requires root mean square value of one cycle three phase voltage and current measurements during fault. These data are treated as inputs for developing a fault isolation and locator module. This module is supposed to be available at central protection system, and is designed using ML based techniques viz. GPR for fault location prediction and SVM for fault identification. Effectiveness of the proposed methodology is evaluated by considering practical grid scenarios with load variation and different DG penetration level. Further, the robustness of the proposed model is assessed by performing sensitivity analysis with consideration of variation in line parameters and load as well as effect of DG correlation. A 7-bus meshed AC MG test system consisting of three DGs and two grid sources is modelled in SIMULINK platform, and is used to demonstrate the proposed module. Data analytics tools of MATLAB 2020a has been explored to develop a machine learning-based fault isolation and location module for MGs. The proposed scheme has also been validated with real time MG data obtained from OPAL-RT real time simulator OP-4510. The accuracy in predicted results proves that the proposed scheme is pertinent for real time practical applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|