Fast Islanding Detection for Distribution System including PV using Multi-Model Decision Tree Algorithm
عنوان مقاله: Fast Islanding Detection for Distribution System including PV using Multi-Model Decision Tree Algorithm
شناسه ملی مقاله: JR_MJEE-14-4_004
منتشر شده در در سال 1399
شناسه ملی مقاله: JR_MJEE-14-4_004
منتشر شده در در سال 1399
مشخصات نویسندگان مقاله:
Rasool Ebrahimi - Smart Microgrid Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
Ghazanfar Shahgholian - Department of Electronics Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
Bahador Fani - Department of Electronics Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
خلاصه مقاله:
Rasool Ebrahimi - Smart Microgrid Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
Ghazanfar Shahgholian - Department of Electronics Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
Bahador Fani - Department of Electronics Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran.
Modern distribution system including Distributed Generation (DG) requires reliable and fast islanding detection algorithms in order to determine the grid status. In this paper, a new multi-model classification-based method is proposed, in order to detect islanding condition for photovoltaic units. Decision tree is chosen as the classification algorithm to classify input feature vectors. The final result is based on voting among three decision tree algorithms. First order derivatives of electrical parameters are employed to construct feature vectors. To cover intermittent nature of renewable sources, different generating states for PV unit are assumed. Probable events are simulated under different system operating states to generate classification data set. The proposed method is tested on typical distribution system including the PV unit, different loads, and synchronous generator. This study showed that this method succeeds in highly fast islanding detection. This quick response can be used in micro-grid application as well as anti-islanding strategy. The results revealed that the proposed voting-base algorithm could classify instances with very high accuracy which leads to reliable operation of distributed generation units.
کلمات کلیدی: Data mining, distributed generation, Intelligent Classification, Micro-grid, Passive Islanding Detection
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1603758/