Centralized intelligent fault localization approach for renewable energy-based islanded microgrid systems

The islanded microgrid systems require adaptive and rapid disturbance detection techniques due to their insufficient kinetic energy reserve and quick response of power electronic inverters of distributed renewable energy sources. To achieve this requirement, this chapter explores the issues in islanded AC microgrids and develops near-real-time intelligent disturbance detection and protective solutions for their stable operation. In the proposed approach, a centralized voltage signal-based fault detection and classification method is proposed using digital signal processing tools and machine learning techniques for islanded AC microgrids. The features used for fault detection and classification are instant changes in voltage amplitude, phase angle, and frequency of the measured phase voltages. Further, detection framework involves three different classifiers which will be collectively trained to achieve fast and efficient abnormality detection. This method has the capability to detect any kind of system disturbance and can differentiate the faults from nonfault disturbances in both balanced and unbalanced systems. The training performance accuracies of the proposed approach are 95%, 99.8%, and 99% for all the three classifiers, respectively, and the fault classification performance accuracy is 100% with a detection time of 0.9 ms.