Artificial Neural Network Based Virtual Sensor for Distributed Controlled DC Microgrids

The measured output current data of distributed energy resources is crucial in realizing cyber-physical DC microgrids (DCMG) and achieving distributed control objectives. This paper proposes an artificial neural network-based output current estimation at the secondary control level. The estimated output current value is used to implement distributed control successfully for the DCMG. The proposed artificial neural network (ANN) acts as a virtual sensor to alleviate problems associated with physical sensors, such as faults and biasing effects. The ANN’s input features and training performance are detailed for the considered DCMG. The performance of the proposed virtual sensor-based distributed controlled DCMG is validated on an experimental hardware setup under multiple load changes and communication delays.

I. Introduction

Direct current microgrids (DCMG) are gaining popularity due to the availability of DC sources like photovoltaic (PV), fuel cells and batteries, etc., and developments in power electronic converters and DC loads. These sources, storage units, and loads are distributed at different locations to form distributed generations (DGs) in the DCMG. The effective way of utilizing these sources in the DCMG is by interconnecting and creating energy management among these distributed energy resources (DERs) [1]. Centralized energy management systems provide control and optimal operation commands to the different DGs from a single centralized controller. However, the centralized controller is highly subjected to a single point of failure and requires communication from all the DGs in the DCMG. Distributed control is a more effective way of controlling interconnected DERs in the DCMG using distributed communication. Moreover, distributed controlled DCMGs are flexible and easily scalable for future expansion [2].