Energy Management Of Electric Vehicles Research Articles

Meta-Learning-Based Predictive Energy Management for 4WD Battery Electric Vehicles

Meta-Learning-Based Predictive Energy Management for 4WD Battery Electric Vehicles

Reinforcement learning-based heuristic planning for optimized energy management in power-split hybrid electric heavy duty vehicles

In this work, we systematically integrate relevant expertise, specifically on the optimal brake-specific fuel consumption (BSFC) curve, battery characteristics and terrain information into the development of an energy management plan for heavy-duty power-split hybrid electric vehicles. We utilize deep deterministic policy gradient (DDPG) algorithm as one of the most sophisticated reinforcement learning technique. Initially, we begin by explaining the vehicle configuration's system modeling. Subsequently, we then present an energy management approach based on deep Q-learning concepts. A novel algorithm, Deep Deterministic Policy Gradient, for energy management control, have been created to combat the "curse of dimensionality" in reinforcement learning. The new AMSGrad optimization technique is used by DDPG algorithm to update the weight of neural networks. We robustly train the proposed control system in realistic driving environment. The Knowledge Incorporation (KI) based DDPG based system is compared systematically to the conventional DDDPG methodology and the benchmark Dynamic Programming (DP) method, the latter of which usually uses the RMSProp Optimizer in its formulation. The results show that as compared to the typical DQL policy, deep reinforcement learning approaches, notably expert Knowledge incorporation KI-DDPG and terrain information with the AMSGrad optimizer, achieve faster training speeds and reduced fuel consumption while maintaining the terminal state of charge (SOC).

Research on the configuration design and energy management of a novel plug-in hybrid electric vehicle based on the double-rotor motor and hybrid energy storage system

Research on the configuration design and energy management of a novel plug-in hybrid electric vehicle based on the double-rotor motor and hybrid energy storage system

Optimization Strategies for Real-time Energy Management of Electric Vehicles Based on LSTM Network Learning

The orderly control of electric vehicle load can improve the load characteristics of regional power grid and reduce the charging cost. Since it is impossible to predict the accurate access time and charging demand of electric vehicles in the future, it is impossible to make a global optimal arrangement for accessing the grid when electric vehicles are charging. Aiming at this problem, a real-time energy management system and optimization strategy of electric vehicle based on deep long-term and short-term memory neural network are proposed. Firstly, a three-tier electric vehicle management architecture including power grid layer, regional energy management system and charging station energy management system is constructed to manage large-scale electric vehicles in layers and regions; Then, a region station interaction strategy based on deep long-term and short-term memory neural network is proposed. The historical optimal solution solved by historical load information is used to train the learning network to guide the new real-time optimization; The proposed strategy can further reduce the charging cost and improve the peak valley characteristics of regional load on the premise of ensuring the charging demand of users. Finally, a simulation example is given to verify the effectiveness and superiority of the proposed layered architecture and management strategy.

Cooperative economic dispatch of EV-HV coupled electric-hydrogen integrated energy system considering V2G response and carbon trading

With the increasing penetration of renewable energy, the Power-to-hydrogen technology accelerates the adoption of new energy vehicles, including both hydrogen vehicles (HV) and electric vehicles (EV). Simultaneously, the integration of Vehicle-to-Grid (V2G) technology further promotes the development of electric-hydrogen integrated energy systems coupled with transportation systems. In this study, an optimal scheduling model is developed for an EV-HV coupled electric-hydrogen integrated energy system, taking into account V2G response and carbon trading. Firstly, to address the randomness of renewable energy and loads, the Latin hypercube sampling method in conjunction with the Kantorovich scenario reduction method, is employed for scenario generation and simplification. Secondly, an optimization model is developed for the operation of hydrogen-blended gas turbines and the energy management of EVs and HVs. To encourage the participation of EVs and HVs, a reward mechanism for V2G responses is introduced, complemented by a time-of-use tariff, to guide orderly charging and discharging. Furthermore, the influence of the operating modes of EVs and HVs, as well as the hydrogen blending ratio, on the total system cost and carbon emissions is examined. An industrial park is selected as an illustrative example to showcase the effectiveness of the proposed method, demonstrating satisfied economic and environmental performances.

Fuzzy Logic-Based Energy Management System for Regenerative Braking of Electric Vehicles with Hybrid Energy Storage System

Electric vehicles (EVs), which are environmentally friendly, have been used to minimize the global warming caused by fossil fuels used in vehicles and increasing fuel prices due to the decrease in fossil resources. Considering that the energy used in EVs is obtained from fossil resources, it is also important to store and use energy efficiently in EVs. In this context, recovery from a regenerative braking system plays an important role in EV energy efficiency. This paper presents a fuzzy logic-based hybrid storage technique consisting of a supercapacitor (SC) and battery for efficient and safe storage of a regenerative braking system. First, the constraints of the battery to be used in the EV for fuzzy logic control are identified. Then, the fuzzy logic system is created and tested in the ADVISOR and Siemens Simcenter Flomaster programs in the New European Driving Cycle (NEDC) driving cycle. A SC was selected for primary storage to prevent the battery from being continuously charged from regenerative braking, thus reducing its lifetime. In cases where the vehicle consumes more energy than the average energy consumption, energy consumption from the battery is reduced by using the energy stored in the SC, and the SC energy is discharged, making preparations for the energy that will come from the next regenerative braking. Thus, the high current values transferred to the battery during regenerative braking are effectively limited by the SC. In this study, the current values on the battery in the EV with a hybrid storage system decreased by 29.1% in the ADVISOR program and 28.7% in the Simcenter Flomaster program. In addition, the battery generated 46.84% less heat in the hybrid storage system. Thus, the heating and capacity losses caused by this current on the battery were minimized. The presented method provides more efficient energy management for EVs and plays an important role in maintaining battery health.

Enhanced extended-input LSTM with an adaptive singular value decomposition UKF for LIB SOC estimation using full-cycle current rate and temperature data

Accurately estimating the state of charge (SOC) of lithium-ion batteries by the battery management system (BMS) is crucial for efficient energy management and power distribution control in electric vehicles (EVs). By far, data-driven methods have been extensively used in estimating the SOC of lithium-ion batteries to efficiently operate EVs with limited resources. However, the learning ability of these methods needs further enhancement. Therefore, this paper aims to analyze the SOC performance of an extended-input long short-term memory (ELSTM) model. The inputs of the ELSTM are improved with identified battery parameters based on an adaptive multi-timescale identification method with frequency difference decomposition. Second, an adaptive singular value decomposition-transformed unscented Kalman filter (ASVDUKF) is proposed to integrate all unknown variables and guarantee the positive definiteness of the error covariance matrix into a vector to form a multi-fusion model that robustly outputs the denoised and optimized SOCs based on the estimations of the ELSTM. The SOC results demonstrate that the ELSTM outperforms the LSTM, which uses conventional input data. Following that, the ELSTM-ASVDUKF model ensures high accuracy and stability with optimal mean absolute error, root-mean-square error, and mean absolute percentage error of 0.0939%, 0.1074%, and 0.1257%, respectively. The proposed model is validated using various full-cycle current rate and temperature data from two different batteries, establishing it as a promising solution for future development.

Transactive energy management of solar-based range anxious electric vehicle integrated parking lots

Electric vehicles (EVs) are regarded as essential solutions for alleviating climate change and energy crises. EVs can store excess Photovoltaic (PV) generation and transfer energy to other EVs, reducing distribution network upgrade costs. However, the limited range of EVs coupled with inadequate charging infrastructure leads to range anxiety among EV users, thereby becoming a barrier to implementing a transactive energy management system. This research quantifies the range anxiety among EV users and proposes a novel trading mechanism for transactive trading between workplace EVs. The case study solved for a commercial region in Auckland shows a 3–10% reduction in charging cost compared to a conventional V2G system. Further analysis shows that public charging stations can also result in cost savings from 1% to 5%. Still, their impact is limited compared to the number of discharging EVs participating in transactive trading. The uncertainty analysis of PV generation under different scenarios also shows the cost savings of the proposed strategy. The simulation results verify the feasibility and effectiveness of the proposed strategy while alleviating range anxiety among EV users.

Plug‐In Hybrid Electric Vehicle Energy Management with Clutch Engagement Control via Continuous‐Discrete Reinforcement Learning

Energy management strategy (EMS) is a key technology for plug‐in hybrid electric vehicles (PHEVs). The energy management of certain series–parallel PHEVs involves the control of continuous variables, such as engine torque, and discrete variables, such as clutch engagement/disengagement. Herein, a control‐oriented model is established for a series–parallel plug‐in hybrid system with clutch engagement control from the perspective of mixed‐integer programming. Subsequently, an EMS based on continuous‐discrete reinforcement learning (CDRL), which enables simultaneous output of continuous and discrete variables, is designed. During training, state‐of‐charge (SOC) randomization is introduced to ensure that the hybrid system exhibits optimal energy‐saving performance in both high and low SOC. Finally, the effectiveness of the proposed CDRL strategy is verified by comparing EMS based on charge‐depleting charge‐sustaining (CD‐CS) with rule‐based clutch engagement control and dynamic programming (DP). In the simulation results, it is shown that, under a high SOC, the CDRL strategy proposed in this article can improve energy efficiency by 8.3% compared to CD‐CS, and the energy consumption is just 6.6% higher than the global optimum based on DP, while under a low SOC, the numbers are 4.1% and 3.9%, respectively.

A Hybrid Algorithm Combining Data-Driven and Simulation-Based Reinforcement Learning Approaches to Energy Management of Hybrid Electric Vehicles

Energy management strategy (EMS) is one of the key technologies that improves the fuel efficiency of hybrid electric vehicles (HEVs) by governing the energy flow between the fuel tank and the electric energy storage. With the rapid development of artificial intelligence especially after the great success of AlphaGo, reinforcement learning (RL) has opened up a new window for EMS. Although many RL-based solutions have been successfully applied to EMS tasks, most current RL-based approaches only consider RL as an offline optimization tool, i.e., RL is used to solve optimization problems given a simulation model. This method may be utilized to realize optimal control in simulation, but there is no guarantee that a well-behaved performance can also be achieved in the real-physical world due to the simulation-to-real gap. Meanwhile, for many industrial EMS tasks especially when optimizing an existing controller, a high-fidelity simulator may be unavailable, but some logging data generated by some suboptimal existing controller and simple models of the principal powertrain components neglecting detailed component dynamics could exist. In this context, a hybrid algorithm combining data-driven and simulation-based RL approach is proposed that tries to learn experience from both the real logging data and simulated simple model. Based on the hardware-in-the-loop (HIL) results, a near optimal policy can be obtained (fuel consumption is decreased by approximately 6.10%) by this hybrid algorithm from a small batch logging data and a simple simulated model when compared with the dynamic programming (DP) method using a high-fidelity simulation model mimicking the real-physical world.

State of Health Estimation for Lithium-Ion Batteries Under Arbitrary Usage Using Data-Driven Multimodel Fusion

Accurately estimating the state of health (SoH) of batteries is indispensable for the safety, reliability, and optimal energy and power management of electric vehicles. However, from a data-driven perspective, complications, such as dynamic vehicle operating conditions, stochastic user behaviors, and cell-to-cell variations, make the estimation task challenging. This work develops a data-driven multi-model fusion method for SoH estimation under arbitrary usage profiles. All possible operating conditions are categorized into six scenarios. For each scenario, an appropriate feature set is extracted to indicate the SoH. Based on the obtained features, four machine learning algorithms are applied individually to train SoH estimation models using time-series data. In addition to the estimates at the current time step, a histogram data-based and online adaptive model is taken from previous work for predicting the next-step SoH. Then, a Kalman filter is applied to systematically fuse the results of all the estimation and prediction models. Experimental data collected from different types of batteries operated under diverse profiles verify the effectiveness and practicability of the developed method, as well as its superiority over individual models.

Online Adaptive Model Identification and State of Charge Estimation for Vehicle-Level Battery Packs

Accurate state of charge (SOC) estimation of traction batteries plays a crucial role in energy and safety management for electric vehicles. Existing studies focus primarily on cell battery SOC estimation. However, numerical instability and divergence problems might occur for a large-size lithium-ion battery pack consisting of many cells. This paper proposes a high-performance online model identification and SOC estimation method based on an adaptive square root unscented Kalman filter (ASRUKF) and an improved forgetting factor recursive least squares (IFFRLS) for vehicle-level traction battery packs. The model parameters are identified online through the IFFRLS, where the conventional method might encounter numerical stability problems. By updating the square root of the covariance matrix, the divergence problem in the traditional unscented Kalman filter is solved in the ASRUKF algorithm, where the positive semi-definiteness of the covariance matrix is guaranteed. Combined with the adaptive noise covariance matched filtering algorithm and real-time compensation of system error, the proposed method solves the problem of ever-degrading estimation accuracy in the presence of time-varying noise with unknown statistical characteristics. Using a 66.2-kWh vehicle battery pack, we experimentally verified that the proposed algorithm could achieve high estimation accuracy with guaranteed numerical stability. The maximum error of SOC estimation can be bounded by 1%, and the root-mean-square error is as low as 0.47% under real-world vehicle operating conditions.

Energy management of electric vehicle using a new strategy based on slap swarm optimization and differential flatness control

Optimal energy management of electric vehicles using slap swarm optimization and differential flatness control has been proposed. A battery–supercapacitor power system is adopted. Each source is connected in parallel to the DC-bus using DC–DC bidirectional converters and supplies a synchronous reluctance motor (SynRM) based drive. The proposed EMS fundamental forces lie in using a combination of complementary proprieties of two approaches, a Slap Swarm optimization Algorithm and Differential Flatness (DF). With a fast optimization mechanism, the Slap Swarm optimization algorithm allows adapting in real-time conditions the DF gains to optimize the system performances. On its side, DF uses predefined trajectories respecting the physical proprieties of the system, which is a powerful tool to guarantee the dynamic constraints of the sources when ensuring desired robust control proprieties. To check the feasibility and performance of the suggested EMS, comprehensive processor-in-the-loop co-simulations of the electric vehicle were carried out using the C2000 launchxl-f28379d DSP board. The main goal of the proposed EMS is to guarantee the DC-bus stabilization, reducing the DC-bus voltage ripples (Δv = 5 V) and the voltage overshoots 15 V (3.2%), respect the source dynamics, and satisfy the SynRM motor power demand. Furthermore, the algorithm minimizes induced harmonics by the drive (10.49%), reducing the battery current ripple by 17.15A, thereby enhancing the battery lifecycle.

Disturbance observer based control for passive multi‐actuator systems with aggregation and distribution

AbstractThis paper presents a disturbance observer‐based controller for a class of multi‐actuator systems that possess passivity properties. By distributing the input and aggregating the output using the same vectors, the original plant is transformed into an aggregation‐and‐distribution plant (ADP), which is also passive. Based on the ADP, this paper derives the conditions for the controller to sufficiently ensure that the overall system has a finite L2‐gain. The conditions can be checked via the passivity notation of several transfer functions. It is not required to establish the overall system's dynamical equation, thereby alleviating the design burden. The additional objective can be attained by performing an optimization on the aggregation/distribution vectors. Several practical applications are introduced as motivating examples, and the effectiveness of the proposed method is demonstrated by the integration of motion control and energy management for electric vehicles.

Research on Mode Switching and Energy Management of Hybrid Electric Vehicle

Aiming at the optimization of mode switching control and energy management strategy for parallel hybrid electric vehicles, a mode switching control method and A-ECMS steady-state energy management strategy is proposed. Firstly, in order to effectively suppress the impact caused by mode switching, and a fuzzy controller is designed for clutch engagement displacement. Then, on the basis of ensuring the smoothness of mode switching, A-ECMS control strategy based on SOC feedback is established. Finally, Isight and Cruise are used to build a co-simulation platform, and multi-island genetic algorithm is used to study the influence of initial value selection of equivalent factor on the controller. The results show that the proposed mode switching control and energy management control strategy, combined with A-ECMS strategy, can effectively improve the vehicle fuel economy on the basis of ensuring the mode switching smoothness.

Energy Management in Plug-In Hybrid Electric Vehicles: Preheating the Battery Packs in Low-Temperature Driving Scenarios

Energy Management in Plug-In Hybrid Electric Vehicles: Preheating the Battery Packs in Low-Temperature Driving Scenarios

Energy management of hydrogen hybrid electric vehicles — A potential analysis

The hydrogen combustion engine (H2ICE) is known to be able to burn H2, producing no CO2 emissions and extremely low engine-out NOxeo emissions. In this work, the potential to reduce the NOxeo emissions through the implementation of electric hybridization of an H2ICE-equipped passenger car (H2-HEV), combined with a dedicated energy management system (EMS) is discussed. Achieving a low H2 consumption and low NOxeo emissions are conflicting objectives, the trade-off of which depends on the EMS and can be represented as a Pareto front. The dynamic programming algorithm is used to calculate the Pareto-optimal EMS calibrations for various driving missions. Through the utilization of a dedicated energy management calibration, H2-HEVs exhibit the potential to decrease the NOxeo emissions by more than 90%, while, decreasing the H2 consumption by over 16%, compared to a comparable non-hybridized H2-vehicle. The present paper represents the initial potential analysis, suggesting that H2-HEVs are a viable option towards a CO2-free mobility with extremely low NOxeo emissions.

A dynamic programming approach for energy management in hybrid electric vehicles under uncertain driving conditions

ABSTRACT This paper addresses the limited adaptability and the computational burden of energy management systems (EMSs) for hybrid electric vehicles (HEVs) implemented via dynamic programming (DP)-based approaches. First, a deterministic dynamic programming (DDP) framework is presented to solve HEV EMS problems subject to a specific driving cycle. To address this limitation, an improved DDP approach, integrating the actual travelled position of the vehicle into the control law, is proposed. This way, a given DDP-based EMS can be applied to all the driving cycles, yet still measured on the same road. Stochastic dynamic programming (SDP)-based EMSs are also developed and prove to be more adaptive to driving scenarios completely different from the ones used for their computation. Real-world driving cycles are employed in all the presented cases, while a reduced HEV powertrain model is used to alleviate the typical DP computational burden.

Energy Management of a Plug-in Hybrid Electric Vehicle Using Bayesian Optimization and Soft Actor-Critic Algorithm

Energy Management of a Plug-in Hybrid Electric Vehicle Using Bayesian Optimization and Soft Actor-Critic Algorithm

Modelling and simulation of energy management of power-split hybrid electric vehicles using the discrete event system specification

Modelling and simulation of energy management of power-split hybrid electric vehicles using the discrete event system specification