Search

• A review is conducted on the application of RL algorithms for EV charging scheduling. • 111 relevant articles are analyzed from multiple perspectives. • Evidence from the literature reveals that RL is increasingly contributing to the field of EV charging scheduling. • Several research challenges and possible future research directions are identified. As climate change and environmental concerns have become increasingly pressing issues, electric vehicles (EVs) have emerged as a viable and environmentally-friendly alternative to their traditional gasoline-powered counterparts. With the growing popularity of EVs, it is widely recognized that scheduled EV charging is of vital importance in enhancing users' satisfaction, improving the profitability of charging stations, and ensuring the secure operation of power grids. Therefore, effective charging scheduling is crucial to achieve EV integration into modern mobility and further promote mass EV adoption. However, EV charging scheduling problems (CSPs) present a significant challenge to conventional methods owing to the complex nature of the decision environment. Reinforcement learning (RL) has gained considerable attention for addressing various CSPs with a Markov decision process (MDP) formulation. This paper aims to conduct a systematic review of existing studies that utilize RL to tackle CSPs. Firstly, we present a summary of the state-of-the-art CSPs and RL algorithms, followed by a review of previous research studies and a discussion of the current challenges in this field. Finally, several unresolved issues and possible future research topics are identified based on our review findings. [ABSTRACT FROM AUTHOR]

This paper investigates the electric vehicle (EV) charging scheduling problem for public EV charging stations (EVCSs) that can accommodate heterogeneous charging demands, aiming to flatten the aggregate load on the power grid and reduce the peak demand. In contrast to existing works that mainly focus on a single scheduling strategy, a two-level hierarchical charging scheduling method is proposed, which includes an online booking system (OBS) and a pricing-based charging control system (PCCS). Specifically, the implementation of OBS can reduce the service capacity of bookable chargers, whereas PCCS can facilitate the redistribution of charging demand from peak to off-peak time periods. Moreover, the nonlinear charging profile of the battery is incorporated into the model to better reflect the real charging process. A deep reinforcement learning (DRL)-based approach with a discrete Markov decision process (MDP) formulation is designed to find the optimal scheduling solution, where deep Q-network (DQN) and deep deterministic policy gradient (DDPG) are combined to handle the hybrid action space with both discrete and continuous actions. A comprehensive set of experiments is carried out to examine the effectiveness of the developed two-level scheduling scheme. The results indicate that the proposed method improves the scheduling effectiveness compared to single-strategy methods by 6.7% to 49.44%. [ABSTRACT FROM AUTHOR]

This study addresses the optimal electric vehicle (EV) charging station deployment problem (CSDP) on coupled transportation and power distribution networks, which is one of the critical issues with the mass adoption of EVs in the recent years. In contrast to existing works that mainly employ heuristics and exact algorithms, we propose a finite-discrete Markov decision process (MDP) formulation defined in a reinforcement learning (RL) framework to mitigate the curse of dimensionality problem. The RL-based approach aims to determine the location of a set of EV charging stations with limited capacity by minimizing the total investment cost while satisfying the coupled network constraints. Specifically, a long short-term memory (LSTM)-based recurrent neural network (RNN) with an attention mechanism is used to train the model based on an offline strategy. The model parameters are learned by the policy gradient algorithm with a learned baseline function. Numerical experiments on multiple problem sizes are conducted to assess the efficiency and feasibility of the proposed solution method. We experimentally show that our approach is efficient to solve the CSDP and outperforms other baseline approaches in solution quality with competitive computational time. • We propose an RL framework to address the EV charging station deployment problem. • An RNN-based model is developed to find the optimal policy. • A policy gradient method is used to train the agent based on an offline strategy. • Experiments are conducted to test the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Metal/composite hybrid thin-walled structures exhibit tremendous merits on the balance design among material costs, weight reduction and mechanical performances. In spite of these advantages, their underlying energy dissipating mechanisms and the influence law of key factors (such as mechanical properties, hybrid ratio, loading angle, etc.) on crushing behavior are still not well illustrated. This study aims to comprehensively explore the crushing deformation characteristics and underlying energy dissipating mechanisms of various square aluminum/CFRP hybrid structures (i.e., aluminum tube internally strengthened with CFRP namely CFRP/AL; aluminum tube externally strengthened with CFRP namely AL/CFRP tubes). Specifically, several axial quasi-static compression tests are performed to compare crushing behavior and performances of between hybrid tubes together with the corresponding net aluminum and CFRP tubes. Experimental results indicate that the total energy absorption of the CFRP/AL hybrid tubes is considerably higher than that of the summation of corresponding individual tubes. Subsequently, finite element models are developed for CFRP/AL hybrid columns to explore the underlying energy-absorbing mechanisms (the contribution of each constituent part on total energy absorption) and the influence law of key factors (mechanical properties, hybrid ratio, loading angle), which cannot be observed from experimental results. Numerical results indicate that the main reasons for the improvement in total energy absorption of CFRP/AL hybrid tubes are the altered deformation pattern of the outer aluminum tube and the significantly increased friction energy. Further, their outer aluminum tube seems to be more likely to generate plastic folding deformation rather than splaying progressive failure mode with increasing initial yield stress. The hybrid ratio and CFRP layer thickness jointly determine the deformation pattern of the CFRP/AL hybrid columns. Finally, it is also found that the load carrying capacity and energy-absorbing characteristics of CFRP/AL hybrid columns gradually reduce with increasing loading angle. The present study is expected to illustrate the potential of such hybrid structure as a crashworthy device and offer some design guidance for application and dissemination. • Crushing behavior of square aluminum/WF-CFRP hybrid structures under axial and oblique loading are investigated. • The underlying energy dissipating mechanisms of square aluminum/WF-CFRP hybrid columns are explored. • The influence mechanisms on crushing behavior of aluminum/WF-CFRP hybrid structures are illustrated. [ABSTRACT FROM AUTHOR]

[Display omitted] • Impacting performances of both single aluminum stringers and aluminum/CFRP hybrid stringers were experimentally and numerically explored. • The energy-absorbing mechanisms of aluminum/CFRP hybrid stringers under impact loads were experimentally, numerically and analytically revealed. • The crashworthiness and lightweight performances of aluminum/CFRP hybrid stringers were optimized through a multi-objectives discrete optimization method accounting for multiple impact angles. Metal/composite hybrid structures exhibit advantages in crashworthiness and lightweightness and have been extended to many fields, including automobile, aerospace, and civil engineering. However, to date, studies on energy-absorbing mechanisms and the design methods of metal/hybrid structures are still insufficient. This study aims to develop an efficient and reliable optimization approach for structural lightweight design of aluminum/CFRP hybrid stringers. Both physical and virtual impact tests of single aluminum stringers and aluminum/CFRP hybrid stringers were carried out. The results show that the total energy absorption of the hybrid stringer are higher than the sum of the single aluminum stringer and the CFRP core. The energy absorption enhancement of the aluminum mainly contributed to the load-carrying improvement of the hybrid stringer because of the reinforcement effects caused by the internal CFRP core. Parametric studies indicate that the crashworthiness performances of the hybrid stringer can be improved by increasing the aluminum thickness, CFRP layer, and foam filling density, but the weight and the cost of the hybrid stringer also increase. The multi-objective discrete optimisation design can provide a cost-efficient approach to better balance the relationships among impact performance and material cost and structure weight for aluminum/CFRP hybrid stringers. [ABSTRACT FROM AUTHOR]

The multivariate, layered nature of traffic accident analysis (TAA) determines that any TAA method must be categorized according to causational factors and encompass all four basic traffic elements, i.e. driver, vehicle, road and environment. The Analytic Hierarchy Process (AHP) is used to sequence accident causation factors according to their relative importance, with the purpose of singling out the most influential ones. The Apriori algorithm is then applied to analyze the degree of an accident or the level of influence. Through applications, the method proves itself capable of determining the type and severity of accidents caused by multiple factors. The method also demonstrates improvement in the accuracy and efficiency of calculation in dealing with large data samples. [ABSTRACT FROM AUTHOR]

In the present study, thin-walled tubes filled with aluminum foam and CFRP skeleton (FCFTs) are developed and manufactured based on a multiple material system. The structural crashworthiness of the proposed design is investigated under quasi-static lateral loading. Further, the aluminum tube, the foam-filled tube and the tubes filled with CFRP skeleton are also designed and tested to perform a comparative study. It is found that the FCFT-1 (the tube filled with foam and CFRP skeleton with square cells) exhibits superior SEA (specific energy absorption), which is almost five times that of the individual aluminum tube, and almost 10% higher than that of the foam-filled tube. However, FCFT-2 (the tube filled with foam and CFRP skeleton with triangular cells) provides relatively lower energy-absorbing capacity, as its aluminum tube generates several axial cracks during crushing process leading to low deformation level of the foams. Furthermore, crush simulations are conducted to better understand the energy-absorbing mechanisms of the FCFT-1. The numerical results demonstrate that the plastic deformation of the separated foams makes up the major part of the total energy absorption. Besides, the performance improvement of FCFT-1 can be partly attributed to the fact that the separated foams generate larger plastic deformation during crushing process. Apart from this, the increased interaction effects between the separated foams and the CFRP skeleton lead to a higher FE (frictional energy), which also makes a slight contribution to the performance improvement of FCFT-1. Finally, parametric studies are performed to explore the influences of design parameters on the crashworthiness characteristics of FCFT-1. It is indicated that the energy-absorbing capacity can be slightly improved by raising cell number, proportion of 45° layer or foam density. The present work is expected to provide some insights for researchers and engineers to design such structures for energy absorption applications. • Lateral crushing of thin-walled tubes filled with aluminum foam and CFRP skeleton (FCFTs) is investigated. • Energy-absorbing mechanisms of FCFTs are explored. • A parametric study is further conducted to explore the influences of design parameters. [ABSTRACT FROM AUTHOR]