Neural network predictive control in renewable systems (HKT-PV) for delivered power smoothing

Abstract

The reduction of power fluctuations from intermittent renewable sources is one of the most pressing challenges today. Recent research has shown that prediction and control mechanisms, when combined with energy storage systems, significantly contribute to improving these techniques. However, substantial research gaps still exist regarding the optimization of energy storage system operability. This article introduces an innovative power smoothing method based on neural network predictive control, in conjunction with the exponential moving average method. The proposed approach encompasses the ability to substantially reduce energy fluctuations, optimize battery state of charge, and mitigate ramp rates, thereby preventing deep discharges that shorten battery lifespan. Furthermore, the control system's primary objective is to optimize energy exchange with the grid, surpassing the performance offered by other conventional power smoothing methods. The control system excels in optimizing energy exchange within the network, surpassing conventional methods. Extensive testing on the University of Cuenca microgrid reveals a consistently more stable and higher battery charge compared to conventional methods. Numerical results for underscore the method's effectiveness with a fluctuation suppression rate of 30.78% compared to 34.85% (low pass filter) and 36.22% (ramp rate) methods respectively. The enhanced voltage profiles at the common coupling point ensure the delivery of high-quality and stable power.