Convolutional Neural Network-Based False Battery Data Detection and Classification for Battery Energy Storage Systems
Hyun-Jun Lee, Kyoung‐Tak Kim, Joung‐Hu Park, Gomanth Bere, Justin J. Ochoa, Taesic Kim
Abstract
Battery energy storage systems (BESSs) rely on battery sensor data and communication. It is crucial to evaluate the trustworthiness of battery sensor and communication data in (BESS) since inaccurate battery data caused by sensor faults, communication failures, and even cyber-attacks can not only impose serious damages to BESSs, but also threaten the overall reliability of BESS-based applications (e.g., electric vehicles (EVs), power grids). This paper proposes a battery data trust framework that enables detect and classify false battery sensor data and communication data by using a deep learning algorithm. The proposed convolutional neural network (CNN)-based false battery data detection and classification (FBD <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> C) model could potentially improve safety and reliability of the BESSs. The proposed algorithm is validated by simulation and experimental results.