Multiobjective Intelligent Energy Management for Hybrid Electric Vehicles Based on Multiagent Reinforcement Learning

A Novel Intelligent Controller-Based Power Management System With Instantaneous Reference Current in Hybrid Energy-Fed Electric Vehicle

“…( 15). (15) Where R1 and C1 are the parallel resistance and capacitance, VTER and IBAT are the terminal voltage and current delivered by the battery and V1 is the voltage drop across the R1 C1 combination of the battery cell. The battery power used in this simulation is 81 kWh with a nominal voltage of 540 V. A single battery has 12 V and 150 Ah capacity and 45 batteries connected in series provide 540 V and 150 Ah capacity.…”

“…The emerging control methodology of PMS in EVs is known as the multi-objective algorithm (MOA), which controls the firing angle of the power modulator connected between the source and EV motor. The reinforcement learning and model predictive control methodologies are employed in MOA to control the 75 kW motor load with multiple drive cycles [15], [16]. Equivalent consumption of the dynamic factor control scheme controls the battery and two motor-generator pairs for PMS operation and this work has been tested with four different drive cycles in simulation but no hardware implementation [17].…”

Machine Learning-Based Regression Models for State of Charge Estimation in Hybrid Electric Vehicles: A Review

“…Machine learning's capacity for adaptation to diverse conditions, nonlinear relationship modeling, and real-time processing aligns seamlessly with the intricacies of SOC estimation in HEVs [22]. Unlike traditional methods that rely on predefined algorithms, machine learning models can evolve and improve their performance over time, making them well-suited for the dynamic nature of HEV operations [23].…”

“…Regression models within the domain of machine learning play a pivotal role in predicting continuous variables, making them particularly apt for estimating SOC. These models establish a mathematical relationship between input features and the target variable, allowing for the precise prediction of SOC based on the given data [24].…”

Reinforcement learning-based control for the thermal management of the battery and occupant compartments of electric vehicles

“…The superiority of this strategy compared to dynamic programming (DP) was demonstrated by the results. 27 Based on the results of relevant researchers, it can thus be found that reinforcement learning is well suited for D-BTMS. Therefore, it can be used to optimize the energy consumption of the system as well as for precise control of the system by correlating the temperature and energy consumption signals of the system with certain reward signals.…”