Modeling and implementation of a novel active voltage balancing circuit using deep recurrent neural network with dropout regularization

Abstract

Recurrent neural networks (RNN) emerged as powerful tools to model and analyze the nonlinear behavior of electronic circuits accurately and quickly.Efforts to improve the accuracy of RNN will lead to the design of better-quality products, which is essential in various fields such as the design of energy harvesting (EH) systems. EH techniques can provide the electrical energy needed for low-power electronics without the need for a battery or with minimal dependency. Due to the importance of the active voltage balancing circuit in EH systems, we have proposed a new macromodeling method called dropout local-feedback deep recurrent neural network (Dropout-LFDRNN) to model and analyze this circuit along with two other nonlinear circuits asexamples. This technique is an advance over the LFDRNN macromodeling method, and based on the obtained results from the measurements, we were able to build a fast macromodel for the active balancing circuit, which outperforms conventional deep recurrent neural network modeling method in terms of accuracy without sacrificing speed. It is worth mentioning that this proposed technique in this paper can be considered a viable approach for modeling and analysis of nonlinear electronic components and circuits. In addition to the advantage of generating a more accurate model, the model based on the Dropout-LFDRNN approach is much faster than the existing transistor-level models.

Intelligent wide‐area damping controller for static var compensator considering communication delays

“…Since dynamic inputs and outputs can be easily mapped using the neural network, which has led to the development of various neural network-based adaptive control schemes. [31][32][33][34] These controllers have also been applied with the SVC for oscillation damping application and have been found to overperform the conventional controllers. [20][21][22][23][24] In this study, a linear-neuro-adaptive controller (LNAC) is presented to provide enhanced oscillation damping under varied operating scenarios.…”

“…Online system identification‐based control scheme is therefore required, which assesses the system's changing dynamic scenarios and accordingly modifies the control signal in real time (online). Since dynamic inputs and outputs can be easily mapped using the neural network, which has led to the development of various neural network‐based adaptive control schemes 31–34 . These controllers have also been applied with the SVC for oscillation damping application and have been found to overperform the conventional controllers 20–24 …”