Learning-based demand-supply-coupled charging station location problem for electric vehicle demand management

Global climate change is affecting human life more seriously than ever before. Countries around the world have identified cars as a significant source of pollution, leading to an increased interest in eco-friendly automobiles. Electric vehicles (EVs), which are characteristically eco-friendly, have become a choice for future transportation system. In this paper, we proposed a strategy for determining the appropriate placement of large-scale charging stations using K-mean algorithm. Also, the initial results were validated utilizing actual electricity usage data from the existing chargers. Currently in Korea, a typical public charging station has two to three chargers to support EV users. As EVs become more popular, new problems arise, such as charger hopping and/or long waiting lines. In order to address these new issues, a large-scale charging station concept which houses more than ten chargers, is suggested. In doing so, a strategic approach for selecting close-to-ideal locations for the charging stations is introduced to maximize the charging station’s effectiveness. In this study, Jeju Island, Korea, which has many EVs, was used as a testbed. With the wealth of EV chargers and their usage data, initial validation of the proposed methodology was made possible. During the evaluation of the best possible locations for the largescale charging stations, we considered the locations of tourist attractions and convenient support facilities, as well as the population. After the evaluations, the proposed locations were validated using actual long-term charger usage data on Jeju Island. The demonstrated strategy for identifying appropriate locations for large-scale charging stations can be used by other tourist heavy islands or even small countries.

In order to encourage energy conservation and emission reduction, electric vehicles (EV) have gradually become one of the most important emerging strategic industries in many countries. With the gradual maturity and application of battery technology, policies support of new energy industry and the marketization of EV in many countries, the location problem of charging stations has become one part of the urban development strategies, but the bottleneck that hinders the development of new EV is the factors of vehicle life and the battery life. The focus of problem solving is the reasonable location and deployment of charging stations. Therefore, the charging station location problem has become a research hotspot in recent years. The EV charging station location is essentially an application scenario of facility location problem. As a long-standing problem, many researchers have proposed many classic models and algorithms, this paper reviews the research progress and existing problems related to charging station location in recent years from the aspects of algorithm and model, and finally gives some future research directions.

As electric vehicles are more adopted extensively, the charging station location and distribution problem is becoming more important. Efficient charging station planning can solve major problems, such as driving-range anxiety and the stagnation of new electric vehicle consumers. For efficient charging station planning, the influence of charging station location should be identified. This paper analyzes the electric taxi's driving patterns with constraint of insufficient charging stations. Comparing the driving patterns between general taxi and electric taxi, specific driving patterns can be revealed due to the location of charging station. Daejeon city in South Korea is selected for the experiment study area to examine the difference of driving patterns. The driving patterns caused by charging behavior are analyzed by real taxi trajectory data. In this study, the measures of driving patterns are analyzed by the sum of trip length in each cell and origin-destination direction pattern with the real data of taxis. In the initial planning phase of installing charging stations, the results of this paper can be efficiently applied to a relatively extensive area to encourage the usage of electric vehicles.

The method of route optimization of electric vehicle

With the aim of promoting energy conservation and emission reduction, electric vehicles (EVs) have gained significant attention as a strategic industry in many countries. However, the insufficiency of accessible charging infrastructure remains a challenge, hindering the widespread adoption of EVs. To address this issue, we propose a novel approach to optimize the placement of charging stations within a road network, known as the charging station location problem (CSLP). Our method considers multiple factors, including fairness in charging station distribution, benefits associated with their placement, and drivers’ discomfort. Fairness is quantified by the balance in charging station coverage across the network, while driver comfort is measured by the total time spent during the charging process. Then, the CSLP is formulated as a reinforcement learning problem, and we introduce a novel model called PPO-Attention. This model incorporates an attention layer into the Proximal Policy Optimization (PPO) algorithm, enhancing the algorithm’s capacity to identify and understand the intricate interdependencies between different nodes in the network. We have conducted extensive tests on urban road networks in Europe, North America, and Asia. The results demonstrate the superior performance of our approach compared to existing baseline algorithms. On average, our method achieves a profit increase of 258.04% and reduces waiting time by 73.40%, travel time by 18.46%, and charging time by 40.10%.

Bu çalışmada Elektrikli Araçla Periyodik Teknisyen Rotalama ve Şarj İstasyonu Yeri Belirleme Problemi tanımlanmıştır. Problemde farklı coğrafi bölgelerde bulunan müşterilere bir dizi önleyici ve düzeltici bakım ve yedek parça tedariki hizmetleri sunulmaktadır. Ayrıca müşteriler, planlama ufku boyunca farklı zaman dilimlerinde bu ve benzeri hizmetleri talep edebilmektedir. Farklı yetkinliklere sahip olan teknisyenlerden takımlar oluşturulup müşterilerin bulunduğu ortamda talep edilen hizmetler sağlanmaktadır. Hali hazırda iş gücü çizelgeleme ve rotalama probleminin NP-zor sınıfta yer aldığı göz önüne alınırsa, tanımlanan problemde aynı sınıfta yer almaktadır. Literatürden farklı olarak bu çalışmada, teknisyenlerin müşterilere ulaşmada klasik içten yanmalı motorlu araçlar kullanması yerine elektrikli araçlarla müşterilere ulaşması göz önüne alınmıştır. Bu sayede fosil yakıt kullanımı azaltılarak, bu yakıtların ulaşım kaynaklı çevresel etkilerinin azaltılması gerçekleşebilecektir. Ayrıca, çevre dostu elektrikli araçların işletme maliyetlerinin klasik içten yanmalı motorlu araçlara göre daha az olması da işletmelerin karşısına ekonomik bir alternatif olarak ortaya çıkmaktadır. Elektrikli araçların avantajlarının yanı sıra kısıtlı menzili onları istasyon kullanmaya bağımlı kılmaktadır. Bu sebepten ötürü bu araçların fosil yakıt kullanan araçlarla rekabet edebilmesi için rotalama planlarının da etkin bir şekilde yapılması gerekmektedir. Tanımlanan problemde planlama ufku boyunca takımlar için günlük çizelge ve rota oluşturmanın yanı sıra, elektrikli araçların şarj durumunun takibi ve istasyon yeri belirleme kararı da bulunmaktadır. Ayrıca teknisyenlerin yasal dinlenme süreleri de göz önüne alınmıştır. Belirli çalışma süresini tamamlayan teknisyenlerin mola vererek dinlenmesi sağlanmıştır. Önerilen karma tam sayılı programlama ile problem modellenmiştir. Gerçek hayat verisinden üretilen veri seti kesin yöntemle çözülmüştür. Ayrıca üretilen farklı boyutlardaki problemlerin çözümü için değişken komşu arama sezgiseli kullanılmıştır. Elde edilen kesin sonuçlar değişken komşu arama sezgiseli ile karşılaştırılmıştır. Gerçekleştirilen hesaplamalı karşılaştırma analizleri sezgisel yöntemin optimum çözümü bulabildiğini ve CPLEX çözücüsünden daha iyi sonuçlar ürettiğini ortaya koymaktadır.

In recent years there is the tendency to charge Electric Vehicles (EVs) with clean sources of energy. Due to this tendency, scientific literature focused on problems of locating and sizing Photovoltaic (PV) Charging Stations (CSs). In this paper, we studied the case of the localization and sizing of PV powered CSs in the region of Valle de Aburrá, Colombia, which is the region of the country with the fastest growth of EV adoption. Looking to utilize the largest amount of PV power, we considered Level 1 (low-power) PV-grid CSs. The use of other PV charging systems, like level 3 (high-power) charging, would require covering bigger roof areas with PV panels, more than the available on an urban landscape. Considering that this problem takes into account low-power CSs, candidate CS locations are places where people go for extended periods of time, with large roof areas and parking availability. In this problem, the decision variables are the location of the CSs, the amount of charging spots at each selected location, and the size of the PV system. These decisions aim to minimize the added annualized cost of the PV systems, the annualized cost of the charging spots in the selected CSs, and the cost of energy purchased from the grid in a year. For calculating the amount of power that the PV systems are capable of generating, we obtained the typical irradiation curves for each candidate CS location. For solving the studied problem, we propose a Mixed Integer Linear Programming (MILP) formulation.

Sharing charging stations are an effective solution for daily usage of electric vehicles charging, however, the area with high demand cannot provide enough stations while there are plenty of stations left idle in remote areas with less demand. The core of the problem is the imbalance of demand and supply. In other word, we need to allocate the charging station to the appropriate locations to balance demand and supply. This study aims to solve the problem of locating charging stations for public electric vehicles (PUEVs), to improve the sharing charging level. We take into consideration the factors affecting charging station locations including mileage, PUEV distribution and passenger distribution. A Non-deterministic Polynomial (NP) model aiming to minimize the total vehicle service distance is developed. We use an agent-based model to simulate the optimized charging station location based on Anylogic. Through a case study of Beijing, we test the model in five situations. This paper concludes that priority, mileage, PUEV distribution and passenger distribution are the key factors affecting the location of PUEV charging stations, with exogenous variables such as the type of circuit and the voltage drawn as constants. The results of one situation show that the existing layout of the charging stations is unreasonable when charging frequency is sharply variant; this paper optimizes the existing location by improving the constraint for the smallest number of charging stations; the proposed model can be used for EV charging stations’ location in densely populated metropolis.

Electric vehicles (EVs) are becoming a popular mode of transportation. However, one of the main concerns for EV and CNG owners is the availability and accessibility of charging stations. In this project, we present the development and implementation of an EV and CNG charging station finder web application. The app uses the Google Maps API to display the location of nearby pay stations and provide details such as connection type, availability and price. The app also allows users to filter charging and CNG stations according to their preferences and report charging stations as false or unserviceable. User testing is done to evaluate the usability and performance of the application. The results show that the app is easy to use and provides accurate and up-to date information on payment facilities In this system, the User is able to manage All his EVs inside the app plus he has search/book as lot in advance in the charging station. The User can also search an EV station based on nearby, city or kilometers. The System also provides a Roadmap if you enter source & destination with the charging stations on the way according to the kilometers entered. Admin will manage all the stations and slots. The need for developing infrastructure such as charging stations is undeniable. This EV Charging Station web application has been developed to help EV drivers locate available charging stations near them. After locating a charging station, users can also book a slot at the station to charge their vehicle. EV owners can also use this system to plan their trips more efficiently. Users simply need to specify the source and destination. Based on these two parameters, this system prepares a roadmap with all available charging stations along the journey.

In cities of low level of electromobility, it is particularly important to plan possibly the most efficient distribution of first-established charging stations. Since it contributes to building trust to electric vehicles, locations of charging stations should correspond to the actual needs of users to promote electromobility and maximize its implementation effect. The article presents a decision-making support method that helps to determine locations of the first charging stations in a given area. The method is based on the assumption that charging stations are set up at existing petrol stations. The method has been applied for the area of the city of Sosnowiec.

A well-developed electric vehicle (EV) charging infrastructure is a key prerequisite for addressing their growing charging needs and driving the rapid development of EVs. However, the fluctuation of renewable energy generation, the load change of distribution network and the uncertainty of electric vehicle charging demand make the node load of distribution network uncertain, which poses a challenge to the safe operation of the grid. Therefore, a two-stage robust optimization model considering the planning of charging station construction is proposed in this study. Firstly, a robust optimization framework for the location and capacity of EV charging stations in the distribution network is constructed, and the charging demand uncertainty is innovatively modeled as DDUs. Then parametric column and constraint generation (C&CG) algorithm is used to solve the two-stage optimization problem with DDUs. Finally, the validity of the model is verified based on IEEE 33-node system.

This paper studies the problem of determining the strategic location of charging stations and their capacity levels under stochastic electric vehicle flows and charging times taking into account the route choice response of users. The problem is modeled using bilevel optimization, where the network planner or leader minimizes the total infrastructure cost of locating and sizing charging stations while ensuring a probabilistic service requirement on the waiting time to charge. Electric vehicle users or followers, on the other hand, minimize route length and may be cooperative or noncooperative. Their choice of route in turn determines the charging demand and waiting times at the charging stations and hence, the need to account for their decisions by the leader. The bilevel problem reduces to a single-level mixed-integer model using the optimality conditions of the follower’s problem when the charging stations operate as M/M/c queues and the followers are cooperative. To solve the bilevel model, a decomposition-based solution methodology is developed that uses a new logic-based Benders algorithm for the location-only problem. Computational experiments are performed on benchmark and real-life highway networks, including a new eastern U.S. network. The impact of route choice response, service requirements, and deviation tolerance on the location and sizing decisions are analyzed. The analysis demonstrates that stringent service requirements increase the capacity levels at open charging stations rather than their number and that solutions allowing higher deviations are less costly. Moreover, the difference between solutions under cooperative and uncooperative route choices is more significant when the deviation tolerance is lower. History: This paper has been accepted for the Transportation Science Special Issue on 2021 TSL Workshop: Supply and Demand Interplay in Transport and Logistics. Funding: This research was supported by the Ontario Graduate Scholarship when Ö. B. Kınay was a PhD candidate at the University of Waterloo, and this support is acknowledged. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2021.0494 .

Charging station location problem for maximizing the space-time-electricity accessibility: A Lagrangian relaxation-based decomposition scheme

With the increasing population, using petroleum and its derivatives in transportation has caused serious environmental problems, including global warming and urban air pollution. This situation has led to the widespread adoption of alternative fuel vehicles, especially Electric Vehicles (EVs), and determining station locations has become a popular research topic. Among the contributions of these studies to the literature are identifying the optimal locations for fast charging stations and space planning. Although numerous routing and charging calculation programs exist for EVs, nature-inspired optimization algorithms can be a valuable approach to addressing the challenges in routing and optimal placement. At the current stage of EV technology, when parameters such as vehicle range and available charging station locations are considered, there is a shortage of charging stations to facilitate efficient intercity travel. Therefore, determining the optimal locations for Electric Vehicles Fast Charging Stations (EVFCS) is a vital issue that needs to be addressed. Failure to identify optimal locations and to adequately plan fast charging stations may lead to problems for both EV owners and charging system operators, such as failing to meet charging demand at the desired level or underutilizing the planned fast charging stations. The main objective of station location planning is to obtain an optimal solution that maximizes the flow volume while simultaneously minimizing the installation costs of charging stations. This paper presents a comparative review of various EV optimal positioning techniques and algorithms used. In addition, it aims to determine the most suitable EVFCS points within the boundaries of Kavacik region of Beykoz district of Istanbul province by applying the geographical proximity-based Haversine algorithm and Analytical Hierarchy Process (AHP) algorithms, which are Multi-Criteria Decision-Making (MCDM) methods, separately.

The high share of electric vehicles (EVs) in the transportation sector is one of the main pillars of sustainable development. Availability of a suitable charging infrastructure and an affordable electricity cost for battery charging are the main factors affecting the increased adoption of EVs. The installation location of fixed charging stations (FCSs) may not be completely compatible with the changing pattern of EV accumulation. Besides, their power withdrawal location in the network is fixed, and also, the time of receiving the power follows the EVs’ charging demand. The EV charging demand pattern conflicts with the network peak period and causes several technical challenges besides high electricity prices for charging. A mobile battery energy storage (MBES) equipped with charging piles can constitute a mobile charging station (MCS). The MCS has the potential to target the challenges mentioned above through a spatio-temporal transfer in the required energy for EV charging. Accordingly, in this paper, a new method for modeling and optimal management of mobile charging stations in power distribution networks in the presence of fixed stations is presented. The MCS is powered through its internal battery utilizing a self-powered mechanism. Besides, it employs a self-driving mechanism for lowering transportation costs. The MCS battery can receive the required energy at a different time and location regarding EVs accumulation and charging demand pattern. In other words, the mobile station will be charged at the most appropriate location and time by moving between the network buses. The stored energy will then be used to charge the EVs in the fixed stations’ vicinity at peak EV charging periods. In this way, the energy required for EV charging will be stored during off-peak periods, without stress on the network and at the lowest cost. Implementing the proposed method on a test case demonstrates its benefits for both EV owners and network operator.