Review on Scheduling, Clustering, and Forecasting Strategies for Controlling Electric Vehicle Charging: Challenges and Recommendations

Al-Ogaili, Ali Saadon; Hashim, Tengku Juhana Tengku; Rahmat, Nur Ezan; Ramasamy, Agileswari K.; Marsadek, Marayati; Faisal, Mohammad; Hannan, M. A.

doi:10.1109/access.2019.2939595

Cited by 195 publications

(119 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [30] reviewed charging station location problem, which is concerned with the location and deployment of charging stations. Perhaps the most related work to the one proposed in this paper is presented in [31], where the authors review scheduling, clustering, and forecasting strategies for EV charging. It also presents a review of data-driven approaches along with other approaches such as optimization and how they have been used for EV charging strategies.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches for EV Charging Behavior: A Review

et al. 2020

View full text Add to dashboard Cite

As the smart city applications are moving from conceptual models to development phase, smart transportation is one of smart cities applications and it is gaining ground nowadays. Electric Vehicles (EVs) are considered one of the major pillars of smart transportation applications. EVs are ever growing in popularity due to their potential contribution in reducing dependency on fossil fuels and greenhouse gas emissions. However, large-scale deployment of EV charging stations poses multiple challenges to the power grid and public infrastructure. To overcome the issue of prolonged charging time, the simple solution of deploying more charging stations to increase charging capacity does not work due to the strain on power grids and physical space limitations. Therefore, researchers have focused on developing smart scheduling algorithms to manage the demand for public charging using modeling and optimization. More recently, there has been a growing interest in data-driven approaches in modeling EV charging. Consequently, researchers are looking to identify consumer charging behavior pattern that can provide insights and predictive analytics capability. The purpose of this paper is to provide a comprehensive review for the use of supervised and unsupervised Machine Learning as well as Deep Neural Networks for charging behavior analysis and prediction. Recommendations and future research directions are also discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches for EV Charging Behavior: A Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Review papers [9]and [10] focused on modeling EV use and provided a review of technical approaches that used a statistical method based on empirical data or a probabilistic model of elemental factors, such as fleet distance, departure time, return time, parking location, and parking period. Daina et al classified the modeling method into three types: a method that aggregates statistical data, an activity-based method, and a method that uses the Markov chain model we used [9].…”

Section: Previous Workmentioning

confidence: 99%

Driving Simulator for Electric Vehicles Using the Markov Chain Monte Carlo Method and Evaluation of the Demand Response Effect in Residential Houses

Iwafune¹,

Ogimoto²,

Kobayashi³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

It is essential to secure flexible resources in power systems to increase the proportion of variable renewable energy generation systems. One flexible resource is demand response (DR) of the batteries of electric vehicles (EVs). In this study, we propose an electric vehicle driving simulator using the Markov chain Monte Carlo (MCMC) method and an EV demand response evaluation model. The former is a highly versatile EV driving simulator that can produce a random driving pattern based on actual EV fleet data, taking into account various features. The latter is a residential DR evaluation model that minimizes a household electricity bill based on the simulated fleet data and enables realistic DR operation using three processes: forecasting, planning, and operation. The contribution of this paper is to enable evaluation of realistic EV battery value in various housing and EV utilization combinations. We found that the EV battery control provides an economic benefit of US$62 (5% of the night-charging case cost) with only charge control and US$370 (31%) with charge and discharge control, as the average expected value based on our assumption of evaluation. Because 40-kWh EV batteries have a sufficiently large capacity to store surplus power from a rooftop PV, they can be operated by determining the operation schedule based on a fixed-fee structure without forecasting or planning.

show abstract

“…On the other hand, this program has a significant impact on distribution network performance and operation. A comprehensive review on scheduling, strategies for connecting and controlling EVs is presented in [28]. In [29] a charging and discharging strategy based on the market price is presented, however, in this paper effect of charging/discharging program on load profile and EV behavior is not considered in the proposed strategy.…”

Section: Introductionmentioning

confidence: 99%

Optimal Allocation of Electric Vehicle Charging Stations With Adopted Smart Charging/Discharging Schedule

et al. 2020

View full text Add to dashboard Cite

Modeling and allocation of the Electric vehicles Charging Stations (EVCS) within the distribution network, as per the growing use of Electric vehicles (EVs) is a challenging task. In this paper, to manage the EVCS, first, with the aim of peak shaving, valley filling, and flattening the load curve of the network, the optimal planning of EV's charging/discharging is devised. In this regard, after modeling involving random variables, a novel hybrid method, based on the Multi Objective Particle Swarm Optimization (MOPSO) optimization algorithm and sequential Monte Carlo simulation is presented. The purpose of the presented optimal charge/discharge schedule is to control the rate and time of charging/ discharging of EVs. In the proposed model, various battery operation strategies, including Uncontrolled Charging Mode (UCM), Controlled Charging Mode (CCM), and Smart Charge/Discharge Mode (SCDM) are also considered. In the next step, in order to implement the charge/discharge schedule of the EVCS profitably, a new formulation is presented for the allocation of two EVCSs (administrative and residential EVCS). In the proposed formulation, various objective functions such as power loss reduction, reducing power purchases from the upstream network, reducing voltage deviation in buses, improving reliability is addressed. Moreover, to incentivize the owner to construct the EVCS with adopted charging/discharging schedule, the optimal profits sharing between Distribution System Operator (DSO) and EVCS owner is also performed. The proposed formulation is applied to a standard network (IEEE 69 buses) and encouraging results are achieved.

show abstract

Review on Scheduling, Clustering, and Forecasting Strategies for Controlling Electric Vehicle Charging: Challenges and Recommendations

Cited by 195 publications

References 108 publications

Machine Learning Approaches for EV Charging Behavior: A Review

Machine Learning Approaches for EV Charging Behavior: A Review

Driving Simulator for Electric Vehicles Using the Markov Chain Monte Carlo Method and Evaluation of the Demand Response Effect in Residential Houses

Optimal Allocation of Electric Vehicle Charging Stations With Adopted Smart Charging/Discharging Schedule

Contact Info

Product

Resources

About