Application of Dual-Tree Complex Wavelet Transform in Islanding Detection for a Hybrid AC/DC Microgrid with Multiple Distributed Generators

Abstract

This paper presents the design and validation of a novel adaptive islanding detection method (AIDM) for a hybrid AC/DC microgrid network using a combination of Artificial Intelligence (AI) and Signal Processing (SP) approaches. The proposed AIDM is aimed to detect and discriminate between the different fault/disturbance conditions that result in islanding and/or non-islanding conditions in a hybrid microgrid. For the islanding and non-islanding conditions detection by the AIDM, firstly, fault/disturbance signals are obtained from a test microgrid. Secondly, these signals are decomposed using Dual-Tree Complex Wavelet Transform. Thirdly, a Synthetic Minority Oversampling Technique (SMOTE) is applied for data preprocessing to increase the accuracy of the classifier. Finally, an artificial neural network (ANN) is used as the classifier for training and testing the proposed AIDM for different microgrid configurations and event scenarios. The proposed method is tested with different data categories from three different microgrid test systems with different scenarios. All modeling and simulations are executed in MATLAB Simulink Version 2023a. Results indicate that the proposed scheme could detect and discriminate between islanding and non-islanding conditions accurately in terms of dependability, precision, and accuracy. An average accuracy of 99–100% could be achieved when tested and validated with microgrid networks adapted from IEEE 13-bus systems.

Keywords

• artificial neural network
• adaptive islanding detection method
• Dual-Tree Complex Wavelet Transform
• islanding detection approach
• hybrid AC/DC microgrid
• Synthetic Minority Oversampling Technique