State of Charge (SoC) Estimation of Battery Energy Storage System (BESS) Using Artificial Neural Network (ANN) Based on IoT- Enabled Embedded System

Abstract

The battery energy storage system (BESS) plays a significant role in the microgrid system to harness renewable energy sources. BESS generally consists of battery modules connecting in series or parallel configurations to achieve operational voltage and capacity. In such a complex system, a battery management system (BMS) is necessary to guarantee safety, reliability, and efficiency while in operation. One critical function of BMS is the state of charge (SoC) estimation of the battery system. It is necessary to have a battery monitoring system based on the internet of things (IoT) enabled devices that can transmit SoC data in real-time. This paper proposed SOC estimation using an artificial neural network (ANN) to reduce the estimation error due to physical parameters and reduce computation cost using an IoT-enabled embedded system. The experimental setup is set using 15 cells of high capacity of lithium ferro phosphate (LFP) prismatic batteries with nominal voltage 3.2VDC and 100Ah. The battery cells are connected in series to achieve a BESS nominal voltage of 48VDC. The result of SoC estimation shows the ANN model provides better accuracy than the support vector machine method. Both qualitative perspective (curve plot) and quantitative perspective (model metrics) justify the accuracy of the ANN model. The ANN model also successfully deploys on MCU as an IoT-enabled embedded system.