Artificial neural network assisted robust droop control of autonomous microgrid

Electric grid is vulnerable to power imbalance and inertia is the grid's response to overcome such disturbance. Augmentation of power electronic converter based renewable energy technologies like Photovoltaic Generators (PVG) and batteries in utility grid significantly reduces inertia. Inertia degradation is indicated by sharp Rate of Change of Frequency (ROCOF) events due to any grid component failure or imbalance. Fixed gain feedback Proportional Integral Derivative (PID) control is insufficient to deal with varying ROCOF events. This work proposes Sliding Mode (SM) robust droop control scheme assisted by Artificial Neural Network (ANN) algorithm for an islanded PVG integrated microgrid. Droop response is governed by swing equation that uses PVG Maximum Power Point (MPP) forecasted by ANN. ANN forecast is compared with optimized Gaussian process regression algorithm based on mean squared error and speed of training as key performance indicator. The algorithms are trained and validated based on climate dataset of Islamabad, Pakistan. SM control performance is compared with various PID gain settings and qualified as the most suitable against variable source, load and ROCOF scenarios. Finally, significance of accurate MPP forecast for droop control is established by comparing the ANN and deterministic forecaster assisted droop response in a microgrid case study.