Emissions of greenhouse gasses and pollution have a major influence on the haulage sector. Electric vehicles and hybrid locomotives are two examples of battery-powered energy storage technologies that might have an advantageous impact on the transportation sector. In EVs, a battery management system has been designed in order to guarantee, dependable and effective battery performance under various driving and environmental conditions. A very accurate battery prototype that depends on various operating circumstances is created. The paper offers a succinct synopsis of numerous significant BMS technologies, highlighting the system’s ability to precisely detect battery voltage, charging and discharging current, and temperature. It has the ability to send data to a mixed-signal processor for battery module monitoring. The optimization-based systems produced superior power management results, but their increased computational overhead limited their capabilities. The machine learning-based methods lower the computational overhead, but the processing of battery data is heavily manual. The cost of processing data is higher for deep learning-based methods, which were recently used in the BMS to predict battery conditions. Although the cost of computation could be reduced, hybrid deep learning models were unable to achieve the best BMS solutions. AI has not yet been able to identify and track the SOC, SOH, RUL, and available power of EV batteries in an integrated fashion.