An integrated energy storage framework with significant energy management and absorption mechanism for machine learning assisted electric vehicle application

Abstract

Regarding environmental friendliness, low maintenance needs, and statuses as a renewable technology, Hybrid Electric Vehicles (HEV) have become more and more popular around the world. In this, the energy management system is crucial for the effective storage of power and regulation of the energy flow system. As a result, Hybrid Energy Storage Systems (HESS) has increased interest due to their superior capabilities in system performance and battery capacity when compared to solo energy sources. Additionally, the primary problem interaction applications, including such battery electric vehicles, are the energy storage system. Multiple energy storage technologies, including battery packs, flywheels, super-capacitors and fuel cells, are combined into a HESS due to their complementing properties. The goal of this setup is to make renewable energy sources more reliable by storing power generated from intermittent sources or by providing backup energy generation from traditional energy sources. A HESS could be utilized as an alternate energy storage system to help them make up for their lack of power density. HESS needs a smart Energy Management System (EMS) to function properly since it combines the dynamic characteristics of a battery and a SuperCapacitor (SC). The motive of the study is to suggest an actual power management control system to accomplish these objectives. The plan is built using a wavelet transform, deep learning mechanism, and fuzzy logic together. A useful tool for separating the various frequency elements of a load's power requirements to reflect the properties of a battery or supercapacitor is the wavelet transform. It is challenging to immediately apply it in a system, though. Because of this, the traditional optimization-model-based facility energy management system encounters substantial difficulties with online forecast and calculation. To solve this problem, the paper proposes a ML technique dependent on a Long Short-Term Memory (LSTM). The suggested control system structure allows for the separation of the offline and online stages of the LSTM technique. The LSTM is being used to map states (inputs) to decisions (outputs) based on system training during the offline stage. As a result, the supercapacitor receives an online calculation and distribution of the high-frequency power requirement. The SOC of the supercapacitor is kept within the appropriate range via fuzzy logic control. To evaluate the efficacy of the suggested energy management control technique, a 70 V battery with 92 V supercapacitor hybrid energy storage devices for hardware platforms have been created.