No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
An Information Security Solution for Vehicle-to-Grid Scheduling by Distributed Edge Computing and Federated Deep Learning
Abstract
This work proposes an information security vehicleto- grid (V2G) scheduling solution, which combines Federated deep learning with distributed edge computing for V2G operation. In this framework, each charging point is equipped with an intelligent computing module to conduct distributed edge scheduling for the connected electric vehicle (EV), so that not only the computation of inference process is efficient, but also the privacy-preserving of EV users is guaranteed. Besides, the desensitized V2G data of charging points are used to train the deep neural network model in each charging station. Therefore, the accurate future data acquisition problem and the uncertainty handling challenges under traditional optimization methods is avoided. At the same time, the spatial-based and time-based clustering methods are applied to improve the accuracy of prediction. Finally, through federated learning, each charging station uploads the local model to the cloud server, and a stochastic client selection pattern is designed to improve the scalability of model aggregation in the cloud server. In this way, the digital assets of each charging station are protected, and computing and communication costs are reduced. Simulation results on real datasets show that the proposed framework has superior performance in terms of training accuracy, communication burden, and computing performance, while maintaining the privacy of EV users and the digital assets of charging stations.
... To optimize charging station selection, the central controller (GC) aggregates the status of charging stations and charging requests, making global decisions [21]. Some studies have proposed charging station selection strategies based on minimizing waiting times, but the real-time uncertainty of charging station statuses affects their applica-Sustainability 2025, 17, 2501 3 of 48 tion [22]. ...
... This priority classification method differs from conventional approaches that primarily rely on battery status indicators, such as state of charge (SOC) and energy demand. Existing studies, predominantly from the perspective of power grid optimization, define priority levels based on factors such as remaining battery capacity, relaxation time, and the ratio of charging energy to charging time [21][22][23][24]. However, these methods often overlook user experience and real-world charging behavior patterns. ...
As the adoption of electric vehicles (EVs) continues to rise, the pressure on charging station resources has intensified, particularly under high-load conditions, where limited charging infrastructure struggles to meet the growing demand. Issues such as uneven resource allocation, prolonged charging wait times, fairness concerns among different user groups, and inefficient scheduling strategies have significantly impacted the overall operational efficiency of charging infrastructure and the user experience. Against this backdrop, the effective management of charging infrastructure has become increasingly critical, especially in balancing the diverse mobility needs and service expectations of users. Traditional charging scheduling methods often rely on static or rule-based strategies, which lack the flexibility to adapt to dynamic load environments. This rigidity hinders optimal resource allocation, leading to low charging pile utilization and reduced charging efficiency for users. To address this, we propose an Adaptive Charging Priority (ACP) strategy aimed at enhancing charging resource utilization and improving user experience. The key innovations include (1) dynamic adjustment of priority parameters for optimized resource allocation; (2) a dynamic charging station reservation algorithm based on load status and user arrival rates to prioritize high-priority users; (3) a scheduling strategy for low-priority vehicles to minimize waiting times for non-reserved vehicles; and (4) integration of real-time data with the DDPDQN algorithm for dynamic resource allocation and user matching. Simulation results indicate that the ACP strategy outperforms the FIFS and RFWDA strategies under high-load conditions (High-priority vehicle arrival rate: 22 EV/h, random vehicle arrival rate: 13 EV/h, maximum parking duration: 1200 s). Specifically, the ACP strategy reduces charging wait times by 96 s and 28 s, respectively, and charging journey times by 452 s and 73 s. Additionally, charging station utilization increases by 19.5% and 11.3%. For reserved vehicles, the ACP strategy reduces waiting times and journey times by 27 s and 188 s, respectively, while increasing the number of fully charged vehicles by 104. For non-reserved vehicles, waiting and journey times decrease by 213 s and 218 s, respectively, with a 75 s increase in fully charged vehicles. Overall, the ACP strategy outperforms traditional methods across several key metrics, demonstrating its advantages in resource optimization and scheduling.
... The authors detailed the vehicleto-grid scheme, combined with renewable energy sources, edge community, photovoltaics, and an internet of smart charging points, obtaining a higher efficiency compared with existing methods. Additionally, Shang et al. [15] contributed to an innovative vehicleto-grid (V2G) scheduling framework that leverages federated DL and distributed edge computing, offering enhanced efficiency, privacy preservation for EV users, and reduced computational and communication costs while providing a data-collecting approach and uncertainty barrier for traditional optimization methods. ...
The global transition to sustainable energy systems has placed the use of electric vehicles (EVs) among the areas that might contribute to reducing carbon emissions and optimizing energy usage. This paper presents a bibliometric analysis of the interconnected domains of EVs, artificial intelligence (AI), machine learning (ML), and deep learning (DL), revealing a significant annual growth rate of 56.4% in research activity. Key findings include the identification of influential journals, authors, countries, and collaborative networks that have driven advancements in this domain. This study highlights emerging trends, such as the integration of renewable energy sources, vehicle-to-grid (V2G) schemes, and the application of AI in EV battery optimization, charging infrastructure, and energy consumption prediction. The analysis also uncovers challenges in addressing information security concerns. By reviewing the top-cited papers, this research underlines the transformative potential of AI-driven solutions in enhancing EV performance and scalability. The results of this study can be useful for practitioners, academics, and policymakers.
... Additionally, identical to [72] which considers randomly initializing the weight of the deep neural network (DNN)-based network at the first iteration, we consider initializing the weights of TNet and SNet randomly in the beginning round. Moreover, regarding the availability of the clients, inspired by [73] which considers randomly selecting EV charging stations to join the FL process in each round, we also adopt the stochastic selection for determining the availability of the clients (i.e., DLESs of prosumers) in each round. The settings of the parameters are summarized in Table IV. ...
In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers' network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independent and identically distributed (non-IID), and the boundary between benign and malicious traffic becomes blurred. To this end, we propose an edge-assisted federated prototype knowledge distillation (E-FPKD) approach, where each client is deployed on a dedicated local edge server (DLES) and can report its availability for joining the federated learning (FL) process. Prior to the E-FPKD approach, to enhance accuracy, the Pearson Correlation Coefficient is adopted for feature selection. Regarding the proposed E-FPKD approach, we integrate the knowledge distillation and prototype aggregation technique into FL to deal with the non-IID challenge. To address the boundary issue, instead of directly calculating the distance between benign and malicious traffic, we consider maximizing the overall detection correctness of all prosumers (ODC), which can mitigate the computational cost compared with the former way. After detection, a rule-based method will be triggered at each DLES for cyber-attack intervention. Experimental analysis demonstrates that the proposed E-FPKD can achieve the largest ODC on NSL-KDD, UNSW-NB15, and IoTID20 datasets in both binary and multi-class classification, compared with baselines. For instance, the ODC for IoTID20 obtained via the proposed method is separately 0.3782% and 4.4471% greater than FedProto and FedAU in multi-class classification.
... In this context, the vehicular electric network (V2G) is not immune from these security threats. Different types of attacks can be recorded against the V2G network [1], [13][14], such as: Denial of Service. A DoS attack refers to an attempt to disrupt the normal operation of the network by flooding it with a high volume of malicious traffic or requests, thereby depleting its resources and preventing it from responding to legitimate requests. ...
The growing adoption of Electric Vehicles (EVs) presents pressing challenges and opportunities for power systems and market dynamics. This paper comprehensively reviews state-of-the-art operational optimization techniques for EV charging, including model predictive control, reinforcement learning, and distributed approaches. The study examines strategies to address uncertainties in renewable generation, market pricing, and EV charging behavior. Advanced pricing schemes like distribution locational marginal pricing and game-based methods are explored to align profitability with system stability. The significance of bidirectional charging in reducing peak loads, supporting ancillary services, and balancing battery degradation with user satisfaction is also discussed. Finally, emerging challenges in privacy, multi-energy coupling, and regulation are presented, emphasizing research directions to enhance grid resilience, economic viability, and sustainability. This review offers valuable insights for policymakers, energy utilities, and EV stakeholders to facilitate a smooth and cost-effective transition toward an electrified and decarbonized transportation and power sector.
In the context of user-side demand response, flexible resources in buildings such as air conditioners and electric vehicles are characterized by small individual capacities, large aggregate scales, and geographically dispersed distributions, necessitating integration by intelligence buildings (IRs). However, the optimization scheduling of IR clusters often involves detailed energy consumption data, posing privacy issues such as revealing household routines. The traditional aggregator-IRs bi-level architecture typically employs centralized or game-theoretic strategies for optimization scheduling, which struggle to balance efficiency and privacy simultaneously. To address this issue, this paper proposes a bi-level optimization scheduling strategy that balances efficiency and privacy. First, deep reinforcement learning models are established for both the aggregator and the IRs to address efficiency. Then, the trained demand response models of the IRs are encapsulated into strategy black boxes and uploaded to the aggregator’s deep reinforcement learning model. Throughout this process, the aggregator remains unaware of the user-side data, thus protecting user privacy. Additionally, considering that training IR strategy black box models is a parallel and similar process, this paper introduces the paradigm of federated learning to reduce learning costs and improve training efficiency on the IRs side. Furthermore, an adaptive clustering federated deep reinforcement learning method is proposed to address the heterogeneity of the IRs. Finally, case studies demonstrate the feasibility and effectiveness of the proposed method.
As one of the most promising elements in Intelligent Transportation Systems (ITSs), connected electric vehicles (CEVs) can be collectively utilized to improve the quality of essential transportation services. However, involving CEVs to provide vehicle-to-grid (V2G) services becomes a crucial problem since they are selfish and belong to different parties. To solve this problem, we propose an efficient federated CEV scheduling framework that implements noncooperative online incentive approach. In particular, the proposed system is designed for providing privacy-preserving power grid signals to each CEV aggregator (CEVA) within the citywide region. To motivate the CEVs to participate in V2G services, a noncooperative interaction scheme is designed between the selfish CEVs and each CEVA. The purpose of the game is to let the CEVA to determine the real-time electricity trading prices, while the CEVs decide their own real-time service schedules. Case studies assess the feasibility and effectiveness of proposed noncooperative incentive approach, in which the efficient motivation on the CEVs contribute to a high quality V2G services. Additionally, the use of sufficient online parking allocation method can further increase the quality of V2G services.
Due to developments in vehicle engineering and communication technologies, vehicular networks have become an attractive and feasible solution for the future of electric, autonomous, and connected vehicles. Electric autonomous vehicles will require more data, computing resources, and communication capabilities to support them. The combination of vehicles, the Internet, and cloud computing together to form vehicular cloud computing (VCC), vehicular edge computing (VEC), and vehicular fog computing (VFC) can facilitate the development of electric autonomous vehicles. However, more connected and engaged nodes also increase the system’s vulnerability to cybersecurity and privacy breaches. Various security and privacy challenges in vehicular cloud computing and its variants (VEC, VFC) can be efficiently tackled using machine learning (ML). In this paper, we adopt a semi-systematic literature review to select 85 articles related to the application of ML for cybersecurity and privacy protection based on VCC. They were categorized into four research themes: intrusion detection system, anomaly vehicle detection, task offloading security and privacy, and privacy protection. A list of suitable ML algorithms and their strengths and weaknesses is summarized according to the characteristics of each research topic. The performance of different ML algorithms in the literature is also collated and compared. Finally, the paper discusses the challenges and future research directions of ML algorithms when applied to vehicular cloud computing.
In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers’ network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independent and identically distributed (non-IID), and the boundary between benign and malicious traffic becomes blurred. To this end, we propose an edge-assisted federated prototype knowledge distillation (E-FPKD) approach, where each client is deployed on a dedicated local edge server (DLES) and can report its availability for joining the federated learning (FL) process. Prior to the E-FPKD approach, to enhance accuracy, the Pearson Correlation Coefficient is adopted for feature selection. Regarding the proposed E-FPKD approach, we integrate the knowledge distillation and prototype aggregation technique into FL to deal with the non-IID challenge. To address the boundary issue, instead of directly calculating the distance between benign and malicious traffic, we consider maximizing the overall detection correctness of all prosumers (ODC), which can mitigate the computational cost compared with the former way. After detection, a rule-based method will be triggered at each DLES for cyber-attack intervention. Experimental analysis demonstrates that the proposed E-FPKD can achieve the largest ODC on NSL-KDD, UNSW-NB15, and IoTID20 datasets in both binary and multi-class classification, compared with baselines. For instance, the ODC for IoTID20 obtained via the proposed method is separately 0.3782% and 4.4471% greater than FedProto and FedAU in multi-class classification.
An accurate electrical load forecast is essential for the effective implementation of vehicle-to-grid (V2G) technology to achieve optimal electric vehicle (EV) charging decisions, consequently, ensuring the security and stability of power grid. While prevailing evaluation metrics prioritize forecast quality, they often overlook the significant influence a forecast exerts when integrated into the V2G scheduling optimization. In this paper, a reliable metric is proposed for forecasts in the context of V2G scheduling from the perspective of forecast value. Firstly, we conducted meticulously designed experiments to expose the limitations of forecast quality metrics in the context of V2G scheduling, as well as reveal three key findings. Subsequently, to address computational challenges and enhance representativeness of scheduling results, statistical features of EV charging are used to construct the aggregate model of EV fleet. Then, a reliable metric called V2G scheduling value error (V2G-SVE) is proposed to evaluate the degradation rate of scheduling performance as the score for forecasting performance. Finally, extensive case studies provide compelling evidence for the effectiveness and broad applicability of V2G-SVE. Beyond proposing an evaluation metric, this paper also aims to provide valuable insights about potential direction of improvement for future load forecasting technology.
Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (FedAvg) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once in a while. Despite its simplicity, it lacks theoretical guarantees under realistic settings. In this paper, we analyze the convergence of FedAvg on non-iid data and establish a convergence rate of O(1 T) for strongly convex and smooth problems, where T is the number of SGDs. Importantly, our bound demonstrates a trade-off between communication-efficiency and convergence rate. As user devices may be disconnected from the server, we relax the assumption of full device participation to partial device participation and study different averaging schemes; low device participation rate can be achieved without severely slowing down the learning. Our results indicates that heterogeneity of data slows down the convergence, which matches empirical observations. Furthermore, we provide a necessary condition for FedAvg on non-iid data: the learning rate η must decay, even if full-gradient is used; otherwise, the solution will be Ω(η) away from the optimal.
After a large number of electric vehicles (EVs) are connected to the integrated energy system, disorderly charging and discharging of EVs will have a negative impact on the safe and stable operation of the system. In addition, EVs’ uncertain travel plans and the stochastic fluctuation of renewable energy output and load power will bring risks and challenges. In view of the above problems, this paper establishes a hierarchical stochastic optimal scheduling model of an electric thermal hydrogen integrated energy system (ETH-IES) considering the EVs vehicle-to-grid (V2G) mechanism. The EVs charging and discharging management layer aims to minimize the variance of the load curve and minimize the dissatisfaction of EV owners participating in V2G. The multi-objective sand cat swarm optimization (MSCSO) algorithm is used to solve the proposed model. On this basis, the daily stochastic economic scheduling of ETH-IES is carried out with the goal of minimizing the operation cost. The simulation results show that the proposed strategy can better achieve a win-win situation between EV owners and microgrid operators, and the operation cost of the proposed strategy is reduced by 16.55% compared with that under the disorderly charging and discharging strategy, which verifies the effectiveness of the proposed model and algorithm.
The use of Electric Vehicles (EVs) is almost inevitable in the near future for the sake of the environment and our plant’s long-term sustainability. The availability of an Electric-Vehicle-Charging Station (EVCS) is the key challenge that owners are worried about. Therefore, we suggest benefiting from individual EVs that have excess energy and are willing to share it with other EVs in order to maximize the availability of EVCSs without the need to rely on the existing charging infrastructure. The Internet of Electric Vehicles (IoEV) is gradually gaining traction, allowing for a more efficient and intelligent transportation system by leveraging these capabilities between EVs. However, the IoEV is considered a trustless environment, with untrustworthy trading partners such as data sellers, buyers, and brokers. Data exchanged between the EV and the Energy AGgregator (EAG) or EV/EV can be used to analyze users’ behavior and compromise their privacy. Thus, a Vehicle-to-Vehicle (V2V)-charging system that is both secure and private must be established. Several V2V-charging systems with security and privacy features have been proposed. However, even if the transmitted communications are entirely anonymous, anonymity alone will not prevent the tracking adversary from reconstructing the target vehicle’s route. These systems frequently fail to find a balance between privacy concerns (e.g., trade traceability to achieve anonymity, and so on) and security measures. In this paper, we propose an efficient privacy-preserving and secure authentication based on Elliptic Curve Qu–Vanstone (ECQV) for a V2V-charging system that fulfils the essential requirements and re-authentication protocol in order to reduce the overhead of future authentication processes. The proposed scheme utilizes the ECQV implicit-certificate mechanism to create credentials and authenticate EVs. The proposed protocols provide efficient security and privacy to EVs, as well as an 88% reduction in computational time through re-authentication, as compared to earlier efforts.
To explore the impact of promotion of electric vehicles on carbon emissions in China, this paper used the principal component analysis (PCA)-logistic regression model to predict the demand for traditional vehicles, and used the scenario analysis method to analyze the proportion of electric vehicles in traditional vehicles qualitatively. Then this paper calculated the carbon emissions during the power generation process based on the existing power structure. In addition, the IPCC carbon emission calculation method is used to compare the CO2 emissions produced by electric vehicles and fuel vehicles with similar vehicle quality while driving the same distance and consuming different energy sources. The results showed that the CO2 emissions of electric vehicles accounted for only 37.05% of fuel vehicles. By 2050, the annual electricity demand of electric vehicles will be 828.7, 776.9, and 752.1 billion kWh under the radical scenario, the reference scenario, and the negative scenario, respectively. According to the current power structure, the carbon emissions will be 1.2, 1.1, and 1 billion tons, respectively. The rapid growth of electric vehicles has a substantial impact on the grid load. Studying the changes in CO2 emissions from energy substitution is significant to formulate the development strategy of the automobile industry and adjust energy structure policies.
A transition to electric vehicles (EVs) is widely assumed to be an important step along the road to environmental sustainability. However, large scale adoption of EVs may put electricity grids under critical strain, since peaks in electricity demand are likely to increase radically. Efforts to manage demand peaks through pricing schemes may create new peaks at low-price periods, if large numbers of EV owners use smart charging to benefit from low prices. This effect is expected to be amplified when EV owners adopt smart decision support to assist them with optimal charging decisions. Therefore, energy policymakers are interested in advanced pricing schemes that can smooth demand or induce demand that comes as close as possible to a desired profile. We show, through simulations calibrated with real-world data, that current approaches to electricity pricing are limited in their ability to induce desired demand profiles. To address this challenge, we present adaptive pricing, a method to learn from EV owner reactions to prices and adjust announced prices accordingly. Our method draws on the Green Information Systems principles and can assist grid operators in ensuring the reliable operation of the grid. We evaluate our results in simulations, where we find that adaptive pricing outperforms current electricity pricing schemes, yielding results close to the theoretically optimal ones. We test our method in inducing both flat and extremely volatile demand profiles, and we see that in both cases it manages to induce EV charging close to the ideal scenario under perfect information.
As a neoteric high-tech product, electric vehicles (EVs) can effectively solve the problems of energy shortages and environmental pollution. On the one hand, EV can relieve the peak load of a smart grid and improve the electricity system operation. On the other hand, EV’s electricity trading information can provide useful data for vehicle management departments to electricity scheduling. However, hackers can easily obtain data from the central database to simulate both parties involved, which leads to the receiver getting unauthorized information. For these challenges, we propose a novel secure electricity trading and incentive contract model based on the basic rules of China’s electricity market. The digital signature technology adopts elliptic curve bilinear pairing to guarantee the reliability and integrity of the transaction information. Energy blockchain is utilized for encryption and distributed storage of energy data with the possession of tamper-proof and traceability. The consistency part of the data block applies a practical Byzantine fault-tolerant (PBFT) algorithm, which not only increases transaction throughput but also reduces transmission delay. The incentive contract based on revenue rewards can promote the benign interaction of EVs. The security analysis reveals that this scheme can achieve better results. Compared with other schemes, our scheme saves about 64.55% of the communication overhead and validates the same number of signed messages in a shorter time. Incentive contracts based on game theory can facilitate EV electricity trading through energy coin rewards. This mechanism makes EV more willing and active to participate in transactions that guarantee the activity and stability of the network.
With an ever‐increasing number of plug‐in electric vehicles (PEVs), there is a fast‐growing interest in PEVs' charging impact on the stability and the operating cost of power grid as well as the ecological environment. The centralized coordinated charging method is one of the promising solutions to mitigate such undesired impacts as elevating load peaks, increasing energy losses, and decreasing node voltage. However, the computational complexity is a critical issue to obtain the coordinated charging strategies especially for a large number of PEVs. In this context, it is very essential to analyze the computational performance of the centralized coordinated charging methods. In this paper, a paradigm for analyzing the computational performance is provided. Three centralized methods with different standpoint, viz., to minimize carbon emissions, to minimize load variance, and to minimize generation cost, are investigated to conduct a computational performance analysis from the grid operator perspective. First, the optimization theory is employed to transform the three engineering problems into the mathematical programming models. Then, whether the mathematical programming models are convex or nonconvex is analyzed. The results show that the first two mathematical programming models are convex, and the third mathematical programming model is nonconvex. And it demonstrates that the centralized scheduling model that is convex programming has a better computational performance theoretically. At last, simulations are carried out to verify the theoretical computational performance for different types of centralized coordinated charging methods.
The use of Electric Vehicles (EVs) load management is relevant to support electricity demand softening, making the grid more economic, efficient, and reliable. However, the absence of flexible strategies reflecting the self-interests of EV users may reduce their participation in this kind of initiative. In this work, we are proposing an intelligent charging strategy using Machine Learning (ML) tools, to determine when to charge the EV during connection sessions. This is achieved by making real-time charging decisions based on various auxiliary data, including driving, environment, pricing, and demand time series, in order to minimize the overall vehicle energy cost. The first step of the approach is to calculate the optimal solution of historical connection sessions using dynamic programming. Then, from these optimal decisions and other historical data, we train ML models to learn how to make the right decisions in real time, without knowledge of future energy prices and car usage. We demonstrated that a properly trained deep neural network is able to reduce charging costs significantly, often close to the optimal charging costs computed in a retrospective fashion.
Electrification of transport offers opportunities to increase energy security, reduce carbon emissions, and improve local air quality. Plug-in electric vehicles (PEVs) are creating new connections between the transportation and electric sectors, and PEV charging will create opportunities and challenges in a system of growing complexity. Here, I use highly resolved models of residential power demand and PEV use to assess the impact of uncoordinated in-home PEV charging on residential power demand. While the increase in aggregate demand might be minimal even for high levels of PEV adoption, uncoordinated PEV charging could significantly change the shape of the aggregate residential demand, with impacts for electricity infrastructure, even at low adoption levels. Clustering effects in vehicle adoption at the local level might lead to high PEV concentrations even if overall adoption remains low, significantly increasing peak demand and requiring upgrades to the electricity distribution infrastructure. This effect is exacerbated when adopting higher in-home power charging.
Availability of the charging infrastructure is critical for a smooth rollout of wide-scale electric vehicle (EV) adoption. Safe integration of the charging infrastructure with the power grid heavily relies on an intelligent platform to support demand-side management and a secure information and communication system to coordinate events. However, security has been identified as an area falling short of the desired expectation in the smart grid, possibly introducing considerable risk to the reliability and stability of the power grid. In addition, a concrete demand-side management system that is compatible with state-of-the-art EVs is also lacking. This paper fills the gap by proposing a scalable defence-in-depth cybersecurity architecture for the charging infrastructure and a demand response scheme for smart EV charging. The feasibility of the system is demonstrated by implementation and testing on a real vehicle.
This paper presents the design and implementation of a single-phase on-board bidirectional plug-in electric vehicle (PEV) charger that can provide reactive power support to the utility grid in addition to charging the vehicle battery. The topology consists of two-stages: 1) a full-bridge ac–dc boost converter; and 2) a half-bridge bidirectional dc–dc converter. The charger operates in two quadrants in the active-reactive power (PQ) power plane with five different operation modes (i.e., charging-only, charging-capacitive, charging-inductive, capacitive-only, and inductive-only). This paper also presents a unified controller to follow utility PQ commands in a smart grid environment. The cascaded two-stage system controller receives active and reactive power commands from the grid, and results in line current and battery charging current references while also providing a stable dynamic response. The vehicle’s battery is not affected during reactive power operation in any of the operation modes. Testing the unified system controller with a 1.44 kVA experimental charger design demonstrates the successful implementation of reactive power support functionality of PEVs for future smart grid applications.
A high number of electric vehicles (EVs) in the transportation sector necessitates an advanced scheduling framework for e-mobility ecosystem operation to overcome range anxiety and create a viable business model for charging stations (CSs). The framework must account for the stochastic nature of all stakeholders’ operations, including EV drivers, CSs, and retailers and their mutual interactions. In this paper, a three-layer joint distributionally robust chance-constrained (DRCC) model is proposed to plan day-ahead grid-to-vehicle (G2V) and vehicle-to-grid (V2G) operations for e-mobility ecosystems. The proposed three-layer joint DRCC framework formulates the interactions of the stochastic behaviour of the stakeholders in an uncertain environment with unknown probability distributions. The proposed stochastic model does not rely on a specific probability distribution for stochastic parameters. An iterative process is proposed to solve the problem using joint DRCC formulation. To achieve computational tractability, the second-order cone programming reformulation is implemented for double-sided and single-sided chance constraints (CCs). Furthermore, the impact of the temporal correlation of uncertain PV generation on CSs operation is considered in the formulation. A simulation study is carried out for an ecosystem of three retailers, nine CSs, and 600 EVs based on real data from San Francisco, USA. The simulation results show the necessity and applicability of such a scheduling framework for the e-mobility ecosystem in an uncertain environment, e.g., by reducing the number of unique EVs that failed to reach their destination from 272 to 61. In addition, the choice of confidence level significantly affects the cost and revenue of the stakeholders as well as the accuracy of the schedules in real-time operation, e.g., for a low-risk case study, the total net cost of EVs increased by 247.3% compared to a high-risk case study. Also, the total net revenue of CSs and retailers decreased by 26.6% and 10.6%, respectively.
Retail electricity markets require development to become transparently functioning, operate in near real-time, permit the integration of smart technology, improve customer engagement, better reflect wholesale prices, be driven by optimal sustainability metrics and mitigate against unexpected price spikes, so that society transitions to net zero in a just manner. This study postulates that it is essential that future retail electricity markets are designed by cross-linking current analytical approaches and integrating proprietary and open-source modelling tools, by adopting the latest development frameworks across data science, software development, cloud computing and Internet of Things interconnectivity. Current analytical methods applicable for retail electricity market design are reviewed and multi-criteria decision analyses are applied to assess modelling tool and development framework effectiveness. A key finding of this study is that current analytical methods applied in the research domain are typically segregated or siloed. As current analytical methods tend to focus on specific clusters, such as electricity customer profiling, demand response and dynamic pricing, peer-to-peer electricity trading, interconnectivity of Internet of Things devices and distribution-level power dynamics, rather than the integration of these clusters and how each analytical method interacts with each other. Similarly, this study finds that modelling tools are also typically segregated or siloed, focusing on energy system planning, electricity market simulation, power system simulation and energy consumption analysis. To provide the necessary tools to design future retail electricity markets, this study suggests that robust modelling tool integration is required.
With the advent of smart cities, residential consumers have evolved towards the concept of prosumers. This paradigm calls for new businesses like energy communities. Energy management of such frameworks is essential to maximize the collective welfare. This paper addresses this issue by developing an energy management framework that accounts for flexible demand, storage devices and electric vehicles. Its two-level structure allows to address the energy exchanging among prosumers in the 1st stage, while the 2nd stage focuses on optimally schedule the different collective assets. A novel stochastic-interval model is proposed to handle with uncertainties from demand, renewable generation, vehicles’ behaviour and energy pricing. A case study is performed on a six-prosumer community. Results serve to validate the new tool and analyse the importance of smart devices. In addition, the new proposal allows to adopt different operating strategies. Actually, the total operating cost may increase by 90% if a pessimistic point of view is adopted while the importance of the vehicle-to-grid capability is marginal otherwise. Furthermore, the energy purchased could be reduced by 7% when adopting a community arrangement, supposing an improvement in the economy and environmental indicators of the network. Other relevant aspects are identified and discussed in depth.
As the global fleet of Electric Vehicles keeps increasing in number, the Vehicle To Grid (V2G) paradigm is gaining more and more attention. From the grid point of view an aggregate of electric vehicles can act as a flexible load, thus able to provide balancing services. The problem of computing the optimal day-ahead charging schedule for all vehicles in the fleet is a challenging one, especially because it is affected by many sources of uncertainty. In this paper we consider the uncertainty deriving from arrival and departure times, arrival energy and services market outcomes. We propose a general optimization framework to deal with the day ahead planning that encompasses different kind of use-cases. We adopt a robust paradigm to enforce the constraints and an expectation paradigm for the cost function. For all constraints and cost terms we propose an exact formulation or a very tight approximation, even in the case of piece-wise linear battery dynamics. Numerical results corroborates the theoretical findings.
With the popularity of electric vehicles (EVs), vehicle-to-grid (V2G) technology is attracting increasing attention due to its crucial merit of enabling bidirectional power flows between EVs and grid, so as to enhance the grid security and stability by regulated dispatching. However, existing V2G approaches are confronted with several unrealizable challenges because of high computational complexity for large-scale EVs and impracticality for future power data acquisition. In this paper, an edge computing framework is proposed in a distributed manner to ensure the dispatching efficiently and provide the raw dataset flexibly. Meanwhile, the long short-term memory (LSTM) network is applied to prediction merely by the past and present power data. Moreover, attention mechanism and data clustering are utilized to improve the prediction accuracy and operation robustness. Experiments involving real dataset demonstrated that the proposed V2G scheme is able to achieve very satisfactory dispatching performance with the prediction accuracy up to 98.89%.
The smart power grid is a critical energy infrastructure where real-time electricity usage data is collected to predict future energy requirements. The existing prediction models focus on the centralized frameworks, where the collected data from various Home Area Networks (HANs) are forwarded to a central server. This process leads to cybersecurity threats. This paper proposes a Federated Learning (FL) based model with privacy preservation of smart grids data using Serverless cloud computing. The model considers the Blockchain-enabled Dew Servers (BDS) in each HAN for local data storage and local model training. Advanced perturbation and normalization techniques are used to reduce the inverse impact of irregular workload on the training results. The experiment conducted on benchmarks datasets demonstrates that the proposed model minimizes the computation and communication costs, attacking probability, and improves the test accuracy. Overall, the proposed model enables smart grids with robust privacy preservation and high accuracy.
Although AI-empowered schemes bring some sound solutions to stimulate more reasonable energy distribution schemes between charging stations (CSs) and charging station providers (CSPs), frequent data sharing between them is possible to incur many security and privacy breaches. To solve these problems, federated learning (FL) is an ideal solution that only requires CSs to upload local models instead of detailed data. Although the CSs' electricity consumption needs not to be exposed to the server directly, FL-based schemes still have been excavated several security threats such as information exploiting attacks, data poisoning attacks, model poisoning attacks, and free-riding attacks. Hence, in this paper, both the effectiveness of energy management and the potential risks of FL for electric vehicle infrastructures (EVIs) are considered, we propose a lightweight authentication FL-based energy demand prediction for EVIs with premium-penalty mechanism. Security analysis and performance evaluation prove that our proposed framework can generate an accurate electricity demand prediction framework to defend multiple FL attacks for EVIs.
Vehicle-to-grid (V2G) technology plays an important part in achieving carbon neutrality. Hence, reducing the execution time under the real-time application becomes an urgent issue. In this paper, we develop a cyber-physical co-modeling to fulfill the fundamental insights into the internet of smart charging points (ISCP), wherein the local controllers are designed near the plug-in electric vehicles (PEVs), and are coordinated with each other. In perspective of energy dispatching, a hierarchical V2G scheduling is implemented in a distributed way to decompose the optimization problem into several sub-problems. Besides, the parallel computing is applied in the V2G problem to accelerate the speed of obtaining results. Moreover, the voltage regulation is applied near the energy coordinator with high-performance computer rather than by the local controller. In perspective of network communication, the small-world network is applied to ensure the communication efficiency and decrease the wiring costs. Besides, the privacy-preserving of both the energy coordinator and the PEV users is guaranteed by processing and storing the sensitive information of the two participants nearby. Finally, the cyber-physical co-modeling is performed in Matlab and Network Simulator 2. Results show load flatting, self-consumption of photovoltaic output, voltage regulation, and up/down regulation are achieved. Moreover, the delay of small-world network is 90.94 times faster than that of lattice network, and the cost of small-world network is nearly 500 times less than that of full mesh network. Particularly, the execution time for V2G operation at one-time interval is less than 1 s.
The Global EV Outlook is an annual publication that identifies and
discusses recent developments in electric mobility across the globe.
It is developed with the support of the members of the Electric
Vehicles Initiative (EVI).
Combining historical analysis with projections to 2030, the report
examines key areas of interest such as electric vehicle (EV) and
charging infrastructure deployment, energy use, CO2 emissions and
battery demand. The report includes policy recommendations that
incorporate learning from frontrunner markets to inform policy makers
and stakeholders that consider policy frameworks and market
systems for electric vehicle adoption.
This edition also features an update of the electric heavy-duty vehicle
models coming onto commercial markets and slotted for release in
the coming few years, and on the status of development of
megachargers. It compares the electric vehicle supply equipment per
EV with the recommended AFID targets. It also analyses the impact
of EV uptake on governments’ revenue from fuel taxation. Finally, it
makes available for the first time two online tools: the Global EV Data
Explorer and Global EV Policy Explorer, which allow users to
interactively explore EV statistics and projections, and policy
measures worldwide.
The full report is freely downloadable from the IEA website: https://www.iea.org/reports/global-ev-outlook-2021
The vehicle-to-grid (V2G) technology creates a cost-effective alternative solution for the integration of electric vehicles (EVs) into smart grids. Two mainstreams of operation modes exist for the V2G implementation, viz. the centralized and decentralized V2G operation mode. In previous studies, researchers used to assume that EV users involved would participate in a special mode for the coordinated V2G strategy. In fact, the requirements of EV users on the V2G operation vary from individual to individual, depending on the type of EV usage, the charging preference of EV users, and the urgency degree of EV charging. Therefore, it is essential to develop a user-oriented V2G scheme with multiple operation modes to make more EVs participate in the V2G operation for coordinated charging. In this paper, the peak shaving capacity of a user-oriented V2G scheme with multiple operation modes is surveyed compared to the conventional charging mode. The city of Shenzhen, China, is taken as a case study to evaluate the power demand of EV charging during peak hours for different scenarios. In order to obtain the coordinated EV charging strategy, the global/divided scheduling optimization model is developed for the centralized/decentralized V2G strategy. The global scheduling method devotes to minimizing the total EV charging costs whereas the divided scheduling method aims to minimize the individual EV charging costs based on the time of use pricing system. Results reveal that the power demand during peak periods is decreased by 0.93 GW or 5.89% for a modest case in a user-oriented V2G scheme in contrast to the conventional charging mode.
In order to accommodate additional plug‐in electric vehicle (PEV) charging loads for existing distribution power grids, the vehicle‐to‐grid (V2G) technology has been regarded as a cost‐effective solution. Nevertheless, it can hardly scale up to large PEVs fleet coordination due to the computational complexity issue. In this paper, a centralized V2G scheme with distributed computing capability engaging internet of smart charging points (ISCP) is proposed. Within ISCP, each smart charging point equips a computing unit and does not upload PEV sensitive information to the energy coordinator, to protect PEV users’ privacy. Particularly, the computational complexity can be decreased dramatically by employing distributed computing, viz., by decomposing the overall scheduling problem into many manageable sub‐problems. Moreover, six typical V2G scenarios are analyzed deliberately, and based on that, a load peak‐shaving and valley‐filling scheduling algorithm is built up. The proposed algorithm can be conducted in real‐time to mitigate the uncertainties in arrival time, departure time, and energy demand. Finally, the proposed scheme and its algorithm are verified under the distribution grid of the SUSTech campus (China). Compared with uncoordinated charging, the proposed scheme realizes load peak‐shaving and valley‐filling by 11.98% and 12.68%, respectively. The voltage values are ensured within the limitation range by engaging power flow calculation, in which the minimum voltage values are increasing and the maximum voltage values are decreasing with the expansion of PEV penetration. What is more, the computational complexity of peak‐shaving and valley‐filling strategy is near‐linear, which verifies the proposed scheme can be carried out very efficiently.
A single plug-in electric vehicle (PEV) cannot participate in reserve and day-ahead markets as they cannot meet the energy requirements of independent system operators (ISO). However, they can be gathered by a PEV aggregator and play a role in so called markets. On the other hand the PEV aggregators are to deal with the uncertainties that go along with these markets and can highly affect their profit. In order to cover these uncertainties scenario-based stochastic approach can be taken into to account to optimally schedule the PEV aggregators so that the maximum profit is obtained. The main contribution of this paper is to involve risk related uncertainties through the downside risk constraints (DRC) which results in risk-constrained stochastic optimization model. The main advantage of this method is that it can provide the owner of PEV aggregator with decisions that are made by considering various quantities for risk. CPLEX solver of GAMS software is employed to solve the problem which is formulated as mixed-integer linear programming (MILP) model. To investigate the accomplishment of DRC, risk-averse state of model is compared to risk-neutral which in former one the profit is reduced meanwhile that risk-in-profit (RIP) is declined.
The concept of the Social Internet of Things (SIoT) can be viewed as the integration of prevailing social networking and the Internet of Things (IoT), which is making inroads into the daily operation of many industries. Smart grids, which are cost-effective and environmentally-friendly applications, are a promising field of the SIoT. However, security and privacy concerns are the dark aspects of smart grids. The goal of this paper is to address the security and privacy issues in the vehicle-to-grid (V2G) networks with the intention of promoting a more extensive deployment of V2G networks for smart grids. Driven by this motivation, in this paper, we propose a robust key agreement protocol that can achieve mutual authentication without exposing the real identities of users. Efficiency is also a major concern in resource-constrained environments. By leveraging only hash functions and bitwise exclusive-OR (XOR) operations, the proposed protocol is highly efficient compared with pairing-based protocols. In addition, we define a formal security model for our privacy-preserving key agreement protocol for V2G networks. Using this model, a formal security analysis shows that the proposed protocol is secure. Moreover, an informal security analysis demonstrates that our protocol can withstand different types of attacks.
This paper presents a new distributed smart charging strategy for grid integration of plug-in electric vehicles (PEVs). The main goal is to smooth the daily grid load profile while ensuring that each PEV has a desired state of charge (SOC) level at the time of departure. Communication and computational overhead, and PEV user privacy are also considered during the development of the proposed strategy. It consists of two stages: (i) an offline process to estimate a reference operating power level based on the forecasted mobility energy demand and base loading profile, and (ii) a real-time process to determine the charging power for each PEV so that the aggregated load tracks the reference loading level. Tests are carried out both on primary and secondary distribution networks for different heuristic charging scenarios and PEV penetration levels. Results are compared to that of the optimal solution and other state-of-the-art techniques in terms of variance and peak values, and shown to be competitive. Finally, a real vehicle test implementation is done using a commercial-of-the-shelf charging station and an electric vehicle.
Electric Vehicles (EVs) are an important source of uncertainty, due to their variable demand, departure time and location. In smart grids, the electricity demand can be controlled via Demand Response (DR) programs. Smart charging and vehicle-to-grid seem highly promising methods for EVs control. However, high capital costs remain a barrier to implementation. Meanwhile, incentive and price-based schemes that do not require high level of control can be implemented to influence the EVs' demand. Having effective tools to deal with the increasing level of uncertainty is increasingly important for players, such as energy aggregators. This paper formulates a stochastic model for day-ahead energy resource scheduling, integrated with the dynamic electricity pricing for EVs, to address the challenges brought by the demand and renewable sources uncertainty.
As the light vehicle fleet moves to electric drive (hybrid, battery, and fuel cell vehicles), an opportunity opens for “vehicle-to-grid” (V2G) power. This article defines the three vehicle types that can produce V2G power, and the power markets they can sell into. V2G only makes sense if the vehicle and power market are matched. For example, V2G appears to be unsuitable for baseload power—the constant round-the-clock electricity supply—because baseload power can be provided more cheaply by large generators, as it is today. Rather, V2G's greatest near-term promise is for quick-response, high-value electric services. These quick-response electric services are purchased to balance constant fluctuations in load and to adapt to unexpected equipment failures; they account for 5–10% of electric cost—$ 12 billion per year in the US. This article develops equations to calculate the capacity for grid power from three types of electric drive vehicles. These equations are applied to evaluate revenue and costs for these vehicles to supply electricity to three electric markets (peak power, spinning reserves, and regulation). The results suggest that the engineering rationale and economic motivation for V2G power are compelling. The societal advantages of developing V2G include an additional revenue stream for cleaner vehicles, increased stability and reliability of the electric grid, lower electric system costs, and eventually, inexpensive storage and backup for renewable electricity.
Facilitating a sustainable electric vehicle transition through consumer utility driven pricing
- K Valogianni
A secure energy trading system for electric vehicles in smart communities using blockchain
- O Samuel