Real‐time implementation of battery bank charge–discharge based on neural inverse optimal control

Abstract

In a renewable energy generation system, the batteries are one of the main components for energy storage. To maximise the useful life of batteries, it is important to ensure a safe and effective rate in the process of battery charging and discharging. To control these processes, different electronic circuits can be used, of which, the most commonly implemented is the DC–DC buck–boost converter. Two different topologies with their corresponding controllers are needed because the energy transfer is bidirectional. This work develops a unique neural inverse optimal controller with online identification for both charge and discharge processes of the battery bank. The main feature of the proposed controller is that it does not present dependence on the converter parameter variations; for this reason, it can be applied for systems with different power requirements without considerable changes in its application. This study discusses the development and real-time operation of a neural controller based on the inverse optimal control algorithm for charge–discharge of a battery bank.