ANN based binary backtracking search algorithm for virtual power plant scheduling and cost-effective evaluation

Abstract

This paper reports of an artificial neural network (ANN) based binary backtracking search algorithm (BBSA) for optimal scheduling controller applied in IEEE 14-bus system for controlling microgrids (MGs) formed virtual power plant (VPP) The model was simulated and validated on actual parameters and load data. The algorithm deals with best binary fitness function to find the best cell and creates the optimum scheduling using the actual data for wind speed, solar radiation, fuel conditions, battery charging/discharging, and specific hour demand. The goal is to regulate the power-sharing via prioritizing the utilization of renewable sources in lieu of the national grid purchases. The developed ANN-based BBSA controller predicts the optimal schedules of the sources via ON and OFF status. The 25 DGs showed the enhancement of ANN-BBSA gives a mean absolute error (MAE) of 6.2e−3 with a correlation coefficient of 0.99993, which is closed to 1. The results showed a significant reduction in the cost and emission by 41.88% and 40.7%, respectively. The developed algorithms reduced the energy cost while delivered reliable power towards grid decarbonization.