Energy management systems (EMSs), implemented in the electronic control unit (ECU) of an actual vehicle with electrified powertrain, is a much simpler version of the theoretically developed EMS. Such simplification is done to accommodate the EMS within the given memory constraint and computational capacity of the ECU. The simplification should ensure reasonable performance compared to theoretical EMS under real-life driving scenarios. The process of simplification must be effective to create a versatile and utilitarian EMS. Hence, it is comprised of a rigorous analysis of results obtained from theoretical EMS under various driving scenarios. This review paper broadly categorizes most of the reported utilitarian EMSs into three major categories and discusses the processes of simplification associated with each category. The utilitarian EMSs are classified based on their dependency on either online computation or offline pre-computation or even both for spewing control decisions. The paper delineates the chronological steps of a utilitarian EMS development, starting from the theoretical background, the process of simplification, validation through model-in-the-loop, software-in-the-loop, hardware-in-the-loop simulation, dynamometer test, and on-road performance validation. Future trends of on-board EMSs are also discussed before the conclusion.

By increasing the electrified vehicles trend, it is crucial to have a survey of what is done before and what is the open challenge for improving this industry. Powertrain electrification has heightened the need for an energy management strategy, which has been a continuing concern in the development of electrified vehicles. An energy management control unit manages power flow between different energy sources in an electrified powertrain that directly affects vehicle performance. There are inadequate numbers of studies on the most recent energy management strategies, which are compatible with real-world scenarios. Intelligent energy management strategies requirements are discussed in detail, and it is categorized to principle-based, data-driven, and composite-based methods. Besides, enabling technologies for implementing an energy management system with a comparison of different controller chips are described to give readers an experimental view. Future trends and existing challenges are presented, which generate fresh insight into energy management strategies.

An online updating framework of an energy management system (EMS) for a multimode hybrid electric powertrain is proposed via cooperation between the asynchronous advantage actor–critic (A3C)-based deep reinforcement learning (DRL) agent and the Markov chain model (MCM). In the overall framework, the DRL agent periodically updates the energy management policy. The MCM expedites the policy update process by generating plenty of probable future drive cycles using recent historical driving data and supplying them to the training process. Assisted with the MCM, the proposed A3C-based energy management framework can yield near-optimal policy for any type of unknown drive cycle in the recent future. Two types of unknown drive cycles are chosen to demonstrate the efficacy of the proposed framework. Type I unknown drive cycle is also generated from the same recent historical driving data but was not included in the training dataset. Type II drive cycle is neither known to the framework nor generated from the same historical data. In type I unknown drive cycle, the trained A3C-based EMS achieves 99% of the fuel economy obtained by the global-optimal EMS and 0.12% deviation from charge sustainability. The trained A3C-based EMS consumes 6%–12% more fuel than the global-optimal EMS for type II unknown drive cycles.

This paper introduces a novel physics-informed exploration strategy for a deep reinforcement learning (DRL)-based energy management system (EMS), specifically targeting the challenge of dealing with constrained action sets. RL-based controllers for electrified vehicle energy management systems have faced obstacles stemming from the selection of infeasible actions, obstructing their practical deployment. The absence of a mechanism for assessing control action feasibility prior to application has compounded this issue, primarily due to the model-free nature of RL-based controllers. Adding a safety layer to the RL-based controller addresses the abovementioned issue, but this often results in suboptimal policies and necessitates an in-depth understanding of the powertrain. Alternatively, theoretical remedies incorporate penalty terms into the immediate reward function to manage infeasible conditions. However, this approach can slow down the training process as the agent learns to avoid infeasible actions. To surmount these challenges, this paper introduces a novel physics-informed exploration strategy, coupled with prioritized experience replay, enabling the agent to swiftly learn to avoid selecting infeasible control actions without the need for a separate safety layer. Real-time simulation results highlight the superior performance of the proposed DRL-based controller over the baseline DRL-based controller with a safety layer, particularly in terms of overall fuel consumption.