Advancing Electric Vehicle Battery Analysis with Digital Twins in Intelligent Transportation Systems

In Intelligent Transportation Systems (ITS), vehicle-to-grid networks offer a promising solution to support the widespread adoption of electric vehicles (EVs) by enabling bidirectional power flow between the grid and EV batteries. However, the degradation of EV batteries over time poses challenges in assessing their reliability and minimizing system downtime. Traditional methods, such as complete charge and discharge cycles, could be more practical in dynamic operating conditions. This study, which looks at how virtual and real worlds can work together in ITS, solves this issue by showing a new way to measure how battery performance drops using a digital twin (DT) and the deep deterministic policy gradient (DDPG) method. To calculate the deterioration of battery performance and state of health (SoH), the DT records the complex interactions among state-of-charge (SoC), cell voltage, and health indicators (HI). The suggested method virtually drains the DT to estimate the actual battery capacity by using HI as a temporal measurement and the DDPG technique to train the DT model. This allows for an in-depth evaluation of performance degradation and SoH. The DT also calculates fuel consumption, offering essential battery efficiency information. In addition to demonstrating the usefulness of the DT in conjunction with the DDPG algorithm for assessing EV battery performance deterioration, SoH, and fuel consumption, experimental and simulation results also highlight the method’s potential in dynamic operating environments. Concerning practical EV applications, this comprehensive method helps to guarantee the safety, dependability, and efficiency of batteries within the framework of virtual-real integration in the ITS.