Demand-Side Management Using Deep Learning for Smart Charging of Electric Vehicles

López, Karol Lina; Gagné, Christian; Gardner, Marc-André

doi:10.1109/tsg.2018.2808247

Cited by 161 publications

(54 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a single user, demand charge management via V1G can synchronize the charging to the over-generation of the roof-mounted photovoltaic plant so to maximize self-consumption [47]; similarly, V1G can apply a time-of-use tariff in order to reduce the electricity bill [48]. Similarly, demand charge management via V1G can coordinate the charging of electric vehicles in a car park [49,50] or in a narrow geographical border [51], applying machine learning methods [52,53], taking into account the users' preferences [54] or the batteries' state of health [55], thus limiting the demand during peak hours and, in general, providing valuable grid services to network operators. Given the different impact of V1G and V2G on the battery charging infrastructure and economics, today's investments are mainly aimed at supporting the massive deployment of electric vehicles and to ensure the extensive presence of charging points with one-way chargers.…”

Section: Smart Chargingmentioning

confidence: 99%

How Smart Metering and Smart Charging may Help a Local Energy Community in Collective Self-Consumption in Presence of Electric Vehicles

et al. 2020

View full text Add to dashboard Cite

The 2018/2001/EU renewable energy directive (RED II) underlined the strategic role of energy communities in the EU transition process towards sustainable and renewable energy. In line with the path traced by RED II, this paper proposes a solution that may help local energy communities in increasing self-consumption. The proposed solution is based on the combination of smart metering and smart charging. A set of smart meters returns the profile of each member of the community with a time resolution of 5 s; the aggregator calculates the community profile and regulates the charging of electric vehicles accordingly. An experimental test is performed on a local community composed of four users, where the first is a consumer with a Nissan Leaf, whereas the remaining three users are prosumers with a photovoltaic generator mounted on the roof of their home. The results of the experimental test show the feasibility of the proposed solution and demonstrate its effectiveness in increasing self-consumption. The paper also calculates the subsidy that the community under investigation would receive if the current Italian incentive policies for renewables were extended to local energy communities; this subsidy is discussed in comparison with the subsidies that the three prosumers individually receive thanks to the net metering mechanism. This paper ends with an economic analysis and calculation of savings on bills when the four users create the local energy community and adopt the proposed combination of smart metering and smart charging.

show abstract

Section: Smart Chargingmentioning

confidence: 99%

How Smart Metering and Smart Charging may Help a Local Energy Community in Collective Self-Consumption in Presence of Electric Vehicles

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [8], an online learning to optimize EVs' charging demands using previous-day pricing profiles from the distribution company was proposed. Alternatively, the authors in [9] designed a smart charging policy for EVs using machine learning tools including deep neural network (DNN), shallow neural network (SNN), and kNN to decide the charging time when the EVs are connected to the CSs. Nonetheless, these approaches only consider energy demand prediction independently at each EV or CS, and thus they may not be effective for the whole EV network.…”

Section: Introductionmentioning

confidence: 99%

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Saputra

Hoang

Nguyen

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

177

View full text Add to dashboard Cite

In this paper, we propose novel approaches using state-of-the-art machine learning techniques, aiming at predicting energy demand for electric vehicle (EV) networks. These methods can learn and find the correlation of complex hidden features to improve the prediction accuracy. First, we propose an energy demand learning (EDL)-based prediction solution in which a charging station provider (CSP) gathers information from all charging stations (CSs) and then performs the EDL algorithm to predict the energy demand for the considered area. However, this approach requires frequent data sharing between the CSs and the CSP, thereby driving communication overhead and privacy issues for the EVs and CSs. To address this problem, we propose a federated energy demand learning (FEDL) approach which allows the CSs sharing their information without revealing real datasets. Specifically, the CSs only need to send their trained models to the CSP for processing. In this case, we can significantly reduce the communication overhead and effectively protect data privacy for the EV users. To further improve the effectiveness of the FEDL, we then introduce a novel clustering-based EDL approach for EV networks by grouping the CSs into clusters before applying the EDL algorithms. Through experimental results, we show that our proposed approaches can improve the accuracy of energy demand prediction up to 24.63% and decrease communication overhead by 83.4% compared with other baseline machine learning algorithms.

show abstract

“…The proposed charging guidance strategies lack the embodiment of the self-interest of EV users, leading to a reduction in users' participation in the charging guidance process [11]. The essence of the users' charging demand is derived from the users' travel demand, that is, the users initiate the charging request because the remaining mileage of the EV is not enough to reach the destination smoothly.…”

Section: Introductionmentioning

confidence: 99%

Dynamic-Area-Based Shortest-Path Algorithm for Intelligent Charging Guidance of Electric Vehicles

et al. 2020

View full text Add to dashboard Cite

With the increasing popularization and competition of electric vehicles (EVs), EV users often have anxiety on their trip to find better charging stations with less travel distance. An intelligent charging guidance strategy and two algorithms were proposed to alleviate this problem. First, based on the next destination of EV users’ trip, the strategy established a dynamic-area model to match charging stations with users’ travel demand intelligently. In the dynamic area, the Dijkstra algorithm is used to find the charging station with the shortest trip. Then, the area extension algorithm and the charging station attribution algorithm were developed to improve the robustness of the dynamic area. The two algorithms can automatically adjust the area size according to the number of charging stations in the dynamic area to reduce the number of nodes traversed by the Dijkstra algorithm. Finally, simulation examples were used to verify the effectiveness of the proposed model and algorithms. The results showed that the proposed intelligent charging guidance strategy can meet the travel demand of users. It is a promising technique in smart cities to find better travel trips with less travel distance and less computed time.

show abstract

Demand-Side Management Using Deep Learning for Smart Charging of Electric Vehicles

Cited by 161 publications

References 28 publications

How Smart Metering and Smart Charging may Help a Local Energy Community in Collective Self-Consumption in Presence of Electric Vehicles

How Smart Metering and Smart Charging may Help a Local Energy Community in Collective Self-Consumption in Presence of Electric Vehicles

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Dynamic-Area-Based Shortest-Path Algorithm for Intelligent Charging Guidance of Electric Vehicles

Contact Info

Product

Resources

About