Article
Automation & Control Systems
Mostafa Mahfouz, Reza Iravani
Summary: This article presents a supervisory controller for operating an electric vehicle fast charging station in autonomous mode when the supply grid is unavailable. The controller is based on the supervisory control theory and ensures seamless transition between different modes of operation.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Environmental Studies
Tai-Yu Ma, Simin Xie
Summary: A new online vehicle-charging assignment model is proposed to reduce charging delays in electrified shared mobility services, showing promising results in minimizing charging operation time with an efficiency optimization approach.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2021)
Article
Thermodynamics
Peter Makeen, Hani A. Ghali, Saim Memon, Fang Duan
Summary: This paper proposes a novel smart techno-economic operation method for electric vehicle charging stations (EVCS) controlled by an aggregator based on a hierarchal model. The deterministic charging scheduling is used to balance the generated and consumed power and surplus power is supplied to the utility grid. Mixed-integer linear programming (MILP) is used to solve the first stage, and Markov Decision Process Reinforcement Learning (MDP-RL) is used to maximize the charging station profit. The outcomes show a sufficient techno-economic hierarchical model for normal operation.
Article
Energy & Fuels
Hongtao Ren, Yue Zhou, Fushuan Wen, Zhan Liu
Summary: This paper proposes a collaborative policy based on Markov Decision Process for real-time allocation of electric vehicle charging power and battery energy storage system discharging power control, in order to integrate extreme fast charging stations with the power distribution network without negatively impacting service quality.
Review
Thermodynamics
Dingsong Cui, Zhenpo Wang, Peng Liu, Shuo Wang, David G. Dorrell, Xiaohui Li, Weipeng Zhan
Summary: This paper provides a comprehensive overview of the operation optimization approaches for EV battery swapping and charging stations. It analyzes the mathematical methods used in the process and examines the current operation mode and optimization objectives. The paper also discusses the merits and drawbacks of previous studies and suggests future research opportunities.
Article
Chemistry, Multidisciplinary
Andrija Petrusic, Aleksandar Janjic
Summary: This article introduces a multicriteria methodology for scheduling a hybrid EV charging station, incorporating renewable energy sources and battery storage to mitigate grid stress, and solving the problem using a genetic algorithm optimization procedure.
APPLIED SCIENCES-BASEL
(2021)
Review
Energy & Fuels
Mohammad Shafiei, Ali Ghasemi-Marzbali
Summary: This paper discusses the design and development of fast charging stations, along with the challenges and future directions of electric vehicle charging.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Automation & Control Systems
Mao Tan, Zhuocen Dai, Yongxin Su, Caixue Chen, Ling Wang, Jie Chen
Summary: With the increase in the number of electric vehicles, battery swapping is seen as promising due to its short waiting time. However, it is challenging to achieve efficient scheduling in a large scale battery swap station due to the uncertainty of the power grid and EV behavior. To address this, a new bi-level scheduling model is proposed, combining deep reinforcement learning for optimal power allocation and MILP subproblems for battery dispatching. Experimental results show excellent performance and cost reduction, benefiting both the battery swap station and the power grid in peak shaving and valley filling.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Energy & Fuels
Carola Leone, Carlo Peretti, Andrea Paris, Michela Longo
Summary: The installation of Ultra-Fast Charging stations (UFCS) is crucial for promoting the global shift to electric mobility. However, integrating UFCSs with energy transmission and distribution grids poses technical challenges due to their high energy demand in a short period of time. To address this, this paper conducts an optimization study to determine the optimal size of Photovoltaic (PV) power plants and Battery Energy Storage Systems (BESS) in the station systems. The results demonstrate that incorporating PV plants and BESS can increase the profitability of UFCSs by 7.5% compared to a solution without additional components.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Engineering, Civil
Zhonghao Zhao, Carman K. M. Lee, Jingzheng Ren, Yung Po Tsang
Summary: This study aims to determine the best deployment plan for EV fast charging stations in a transportation network with limited budget. The objective is to maximize the quality of service with respect to waiting time and range anxiety from the perspective of EV customers. The study proposes a novel reinforcement learning framework using a finite discrete Markov decision process to address the curse of dimensionality problem and a recurrent neural network with an attention mechanism for unsupervised learning.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Energy & Fuels
Nikhil Kumar, Tushar Kumar, Savita Nema, Tripta Thakur
Summary: This paper proposes a two-stage sustainable framework for joint allocation of fast charging EVCS, solar PV, and BESS. The framework optimizes the location and sizing of PV integrated EVCS in the first stage, and calculates the size of BESS and additional PV capacity in the second stage. Numerical results demonstrate multiple benefits of the proposed framework.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Engineering, Electrical & Electronic
Vandana Jain, Bhim Singh, Seema
Summary: This work presents a charging station with a battery energy storage (BES) system, which enhances the power quality of the grid. The positive sequence components of the grid voltages are evaluated to estimate the unit templates and reference grid currents. The electric vehicle (EV) and BES are connected through a bidirectional buck-boost converter, allowing the EV to take power from the solar array during the daytime and from the grid when the solar power is unavailable. Tests conducted on a hardware prototype demonstrate the satisfactory response of the system under different dynamics conditions.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2023)
Article
Engineering, Electrical & Electronic
Ciro Attaianese, Antonio Di Pasquale, Pasquale Franzese, Diego Iannuzzi, Mario Pagano, Mattia Ribera
Summary: This paper proposes an online scheduling algorithm for UFCSs equipped with Battery Energy Storage Systems, which considers both infrastructure and EVs constraints. The algorithm takes into account the efficiency of the infrastructure and the dependence of the maximum EV charging rate on the State of Charge (SoC).
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Review
Engineering, Multidisciplinary
Pankaj Sharma, Rani Chinnappa Naidu
Summary: This paper highlights the use of retired electric vehicle batteries for charging EVs in a centralized charging station system. It discusses the power flow from the grid, solar PV, and retired EV batteries to the charging station, as well as various schemes for EVs in India and barriers to EV adoption. The review focuses on modeling and optimization using retired EV batteries, and considers future possibilities for their use.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Thermodynamics
Mohammad Shafiei, Ali Ghasemi-Marzbali
Summary: This paper aims to design a fast-charging station that considers parameters such as solar panel capacity, storage systems, wind turbine, Demand Response (DR) program, and stochastic model of Renewable Energy Sources (RESs). The findings revealed that using load management at the charging station increases profitability and reduces initial capital investment. A hybrid algorithm is proposed to forecast wind speed changes. The total 10-year cost is reduced by 17.85% and 3.31% in the presence of Demand Response (DR) for the first and second ownerships, respectively.
Article
Environmental Studies
Irfan Ullah, Kai Liu, Toshiyuki Yamamoto, Rabia Emhamed Al Mamlook, Arshad Jamal
Summary: This study aims to tackle the challenge of predicting electric vehicle energy consumption using advanced machine learning models, extreme gradient boosting, and light gradient boosting machine, comparing them with traditional machine learning models, multiple linear regression, and artificial neural network. The results show that models based on extreme gradient boosting and light gradient boosting machine outperformed multiple linear regression and artificial neural network, providing more accurate predictions for electric vehicle energy consumption.
ENERGY & ENVIRONMENT
(2022)
Article
Engineering, Civil
Shasha Liu, Toshiyuki Yamamoto, Enjian Yao, Toshiyuki Nakamura
Summary: Understanding the variability of travel patterns is crucial for improving public transport services. In this study, we developed a novel measure that considers multiple dimensions of travel behavior to quantify intrapersonal and interpersonal variability in weekly public transport usage. Analyses based on smart card data and an anonymous cardholder database revealed the influence of gender and age on travel pattern variability.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Shasha Liu, Toshiyuki Yamamoto, Enjian Yao
Summary: Research has found that the choices of travel mode and distance are not independent decisions, as individuals usually consider the preferences and needs of other household members. The dependency between mode choice and travel distance is influenced by unobserved factors. Walk mode choice is more dependent on travel distance compared to other travel modes, and the correlation between mode choice and travel distance is higher in complex individual tours. Ignoring this dependency or not considering intra-household interactions may lead to over- or under-estimation of the effects of changes in exogenous variables.
Article
Economics
Shasha Liu, Toshiyuki Yamamoto
Summary: This study examines the role of stay-at-home requests and travel restrictions in preventing the spread of COVID-19 using a model that incorporates population mobility. The findings show that people significantly reduced travel during the state of emergency, leading to effective control of the pandemic.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2022)
Article
Economics
Jiangbo Wang, Toshiyuki Yamamoto, Kai Liu
Summary: Understanding the mechanism of continuous subscribing behavior is crucial for the operation and survival of customized bus systems. This study reveals differences in subscribing behavior between active and inactive users and the influence of various factors on their subscription behavior.
JOURNAL OF CHOICE MODELLING
(2022)
Article
Energy & Fuels
Irfan Ullah, Kai Liu, Toshiyuki Yamamoto, Muhammad Zahid, Arshad Jamal
Summary: Electric vehicles are crucial for smart transportation systems, but limited driving range, prolonged charging times, and inadequate charging infrastructure hinder their adoption. This study employed four different ensemble machine learning algorithms to predict the charging time of electric vehicles, with the XGBoost model achieving the highest accuracy. Additionally, the newly developed SHAP approach was used to interpret the outputs of the ML algorithm.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Article
Transportation
Yuanfang Zhu, Meilan Jiang, Toshiyuki Yamamoto
Summary: The proposed method aims to improve the accuracy and efficiency of the local map-matching algorithm without affecting its efficiency by using an incremental map-matching algorithm, identifying mismatching links, and correcting error links. Experimental results show that the proposed method significantly increases the accuracy and efficiency of map-matching, outperforming benchmark global map-matching algorithms in terms of error rate and computation time.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Transportation Science & Technology
Zhiju Chen, Kai Liu, Jiangbo Wang, Toshiyuki Yamamoto
Summary: The problem of learning from imbalanced ride-hailing demand data is a new challenge. To achieve better prediction performance, a bagging learning approach based on H-ConvLSTM is proposed, which sets multiple thresholds and selects the best submodel to predict the ride-hailing demand.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Chemistry, Physical
Urwah Khan, Toshiyuki Yamamoto, Hitomi Sato
Summary: This study investigated the discontinuance rate of HFCV ownership among adopters in Aichi Prefecture, Japan, and found a high rate of discontinuance. Dissatisfaction with driving range and future viability were the main factors leading to discontinuance. To reduce the discontinuance rate and maintain the presence of HFCVs in the market, Japanese stakeholders need to address the concerns of HFCV owners.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2022)
Article
Transportation
Irfan Ullah, Kai Liu, Toshiyuki Yamamoto, Md Shafiullah, Arshad Jamal
Summary: This study predicts the charging time of electric vehicles using machine learning algorithms and optimizes the algorithm parameters to improve accuracy and robustness. The results show that machine learning models based on the gray wolf optimizer perform better in predicting charging time.
TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH
(2023)
Article
Engineering, Civil
Kai Liu, Zhiju Chen, Toshiyuki Yamamoto, Liheng Tuo
Summary: This paper investigates the issue of demand prediction in ride-hailing dispatching and proposes a method based on a convolutional long short-term memory model combined with a hexagonal convolution operation. Experimental analysis using empirical data for Chengdu, China shows that the proposed approach outperforms conventional methods in terms of prediction accuracy. The comparison of 36 spatiotemporal granularities reveals that a hexagonal spatial partition with an 800 m side length and a 30 min time interval achieves the best comprehensive prediction accuracy, although departure demands and arrival demands exhibit different variation trends in prediction errors for various spatiotemporal granularities.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Meilan Jiang, Hitomi Sato, Xiaoshu Diao, Ghasak I. M. A. Mothafer, Toshiyuki Yamamoto
Summary: This study investigates the influence factors of bicycle accidents for different age groups in traffic analysis zones using a multivariate Poisson gamma mixture model. The results show that children are more likely to have accidents in residential areas, while young and adult groups have more accidents in areas with many companies. All age groups are more prone to accidents in areas with many shops. The elderly group is greatly affected by both the number of bicycle trips and spatial spillover effect, making them the most susceptible to bicycle accidents among all age groups.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Transportation
Shasha Liu, Toshiyuki Yamamoto, Toshiyuki Nakamura
Summary: Understanding trends in public transport usage by older people over the years is important for the long-term planning and development of age-friendly public transport. Using six years of smartcard transaction data from Shizuoka, Japan, a latent Markov model is developed to analyze the evolution of public transport usage by older people. The results suggest that age, gender, and residential built environment influence trends in public transport usage by older adults, and there are five latent states for older men and women, respectively, demonstrating the existence of unobserved heterogeneity.
TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH
(2023)
Article
Transportation
Jiangbo Wang, Kai Liu, Toshiyuki Yamamoto, De Wang, Guoxu Lu
Summary: This study empirically explores the impact of the built environment on demand-responsive transit (DRT) use through a case study of a successful DRT system in Dalian, China. The results suggest that factors such as residential population, employment density, land use composition, connectivity, and accessibility contribute to DRT use. The findings highlight the potential marketing direction for DRT systems in serving niche markets poorly served by regular transit services.
TRAVEL BEHAVIOUR AND SOCIETY
(2023)
Article
Economics
Ning Huan, Toshiyuki Yamamoto, Enjian Yao
Summary: Empirical experience in Europe and China shows that seamless intermodal connections are crucial for expanding the market share of air and high-speed rail (HSR) integration services. However, there are practical obstacles to integrating air and HSR systems. This study proposes a method for improving synchronous operations of air and HSR by unilaterally scheduling airline timetable and airfare. The empirical case study demonstrates that the optimal scheduling solution significantly reduces air-HSR connection time and highlights the importance of efficient shuttle systems, baggage through-check, and flexible ticket services.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2023)
