Fig 9 - uploaded by Tianyu Yang
Content may be subject to copyright.
Source publication
With the growing application of electric vehicles (EVs), it is of great significance to have a deep understanding of EV users driving and charging patterns for charging forecasting. However, the rapid growth scale of EV taxis with charging patterns that are closely coupled with human behaviours of temporal-spatial charging choices was not compatibl...
Context in source publication
Context 1
... further case study aims to test different ratios of the application of WFP, i.e. varied knowledge of EV historical data would bring about different forecasting results. Only HA is used in Case A and WFP in Case B. While Cases C, D, and E were provided with more abundant information, making it possible for different ratios of WIP. Fig. 9 gives the RMSE in different ...
Similar publications
Citations
... V2G strategies involve many factors, such as EV ownership, charging characteristics (Yang et al., 2017), user charging habits, CS configuration, distribution network capacity, multi-level charging management (Heilmann and Friedl, 2021), grid network planning, and macro policies (Wu et al., 2020). There have been many studies on V2G applications. ...
Existing vehicle-to-grid (V2G) applications are aimed at the power grid and the government. It is difficult for charging stations (CSs) to execute the schedules in real time. To figure out the multiple-layer energy management from the perspective of CS, the dispatch potential assessment model is constructed based on the EV users’ charging demand and Minkowski summation. And the optimal energy management schedule model of CS with ESS is proposed considering peak shaving and valley filling under the time-in-use tariff. Besides, the real-time charging control model of EVs in CS is designed under the premise of meeting the charging needs. The simulation results show that the proposed strategy can promote CS operation revenues and track the scheduling plan of CS. The arbitrage of tariffs and peak shaving ancillary services are realized while the charging loads of CSs are smoothed by the charging/discharging of ESS. The proposed strategy is applicable for the CS aggregators and can help the grid operators for dispatch schedules.
... However, such user profile-based forecasting techniques often violate the privacy of the user and expose private information. Global positioning system (GPS) data were used in [8] to collect the SOC information and model the EV charging. The second type of charging load forecasting method uses the charging station data to forecast the demand [9]. ...
The rapid growth of electric vehicles (EVs) is likely to endanger the current power system. Forecasting the demand for charging stations is one of the critical issues while mitigating challenges caused by the increased penetration of EVs. Uncovering load-affecting features of the charging station can be beneficial for improving forecasting accuracy. Existing studies mostly forecast electricity demand of charging stations based on load profiling. It is difficult for public EV charging stations to obtain features for load profiling. This paper examines the power demand of two workplace charging stations to address the above-mentioned issue. Eight different types of load-affecting features are discussed in this study without compromising user privacy. We found that the workplace EV charging station exhibits opposite characteristics to the public EV charging station for some factors. Later, the features are used to design the forecasting model. The average accuracy improvement with these features is 42.73% in terms of RMSE. Moreover, the experiments found that summer days are more predictable than winter days. Finally, a state-of-the-art interpretable machine learning technique has been used to identify top contributing features. As the study is conducted on a publicly available dataset and analyzes the root cause of demand change, it can be used as baseline for future research.
... The prediction of electric vehicle charging station (EVCS) scenarios are often based on existing historical data. Vehicle GPS data [5] and historical electricity price data [6] can be collected to make a decision after car owners' comparison. Reference [7] applied hierarchical methods after dimensionality reduction, and data were input into multiple benchmark prediction models. ...
... Due to the gradual emergence of queuing, the decisions made by users in the face of queuing at peak charging hours make load dispersion more obvious. When ETPR increases from 40% to 50%, the peak charging loads of EVCS 4,5,6 with low values at noon increase from 50.6%, 29.7% and 38.4% of full load to 79.7%, 71.1%, and 77.9%, respectively. ...
In view of the current multi-source information scenario, this paper proposes a decision-making method for electric vehicle charging stations (EVCSs) based on prospect theory, which considers payment cost, time cost, and route factors, and is used for electric vehicle (EV) owners to make decisions when the vehicle’s electricity is low. Combined with the multi-source information architecture composed of an information layer, algorithm layer, and model layer, the load of EVCSs in the region is forecast. In this paper, the Monte Carlo method is used to test the IEEE-30 model and the traffic network based on it, and the spatial and temporal distribution of charging load in the region is obtained, which verifies the effectiveness of the proposed method. The results show that EVCS load forecasting based on the prospect theory under the influence of multi-source information will have an impact on the space–time distribution of the EVCS load, which is more consistent with the decisions of EV owners in reality.
... In earlier studies [6], [7], the GPS data of conventional internal combustion engine vehicles (ICEVs) were considered as EVs and derived charging behaviors based on their travel behaviors. Current studies also use the GPS data of ICEVs to infer the feasibility and potentials of electrifying the existing transportation fleet [8], [9]. These data sources, however, can not account for the behavior of EVs since they are either smallscale data of limited ICEVs or GPS data of specific vehicle types, e.g., taxi fleet [6], [8], [9]. ...
... Current studies also use the GPS data of ICEVs to infer the feasibility and potentials of electrifying the existing transportation fleet [8], [9]. These data sources, however, can not account for the behavior of EVs since they are either smallscale data of limited ICEVs or GPS data of specific vehicle types, e.g., taxi fleet [6], [8], [9]. ...
... In this study, we seek to resolve the aforementioned drawbacks by using GPS data for EVs and developing machine learning models to estimate the daily CD. Unlike [8], [9] that considered GPS data of ICEVs as EVs, we have examined the data of actual EVs and provided extensive comparison on the traveling behavior of EVs and ICEVs commuting in the same urban network. Additionally, we have analyzed the CD of EVs based on their recorded state of charge (SOC) without making assumptions on EVs' initial SOC and energy consumption based on the traveling distances, which is a prevalent assumption made in different studies due to the lack of information in the data sets [3], [5], [15]. ...
The increasing market penetration of electric vehicles (EVs) may change the travel behavior of drivers and pose a significant electricity demand on the power system. Since the electricity demand depends on the travel behavior of EVs, which are inherently uncertain, the forecasting of daily charging demand (CD) will be a challenging task. In this paper, we use the recorded GPS data of EVs and conventional gasoline-powered vehicles from the same city to investigate the potential shift in the travel behavior of drivers from conventional vehicles to EVs and forecast the spatiotemporal patterns of daily CD. Our analysis reveals that the travel behavior of EVs and conventional vehicles are similar. Also, the forecasting results indicate that the developed models can generate accurate spatiotemporal patterns of the daily CD.
... In [19], a Markov chain model is introduced to evaluate different driver's reaction when EV is out of power. In [20], a global positioning system data was used to study the behaviour patterns of different EV users. In aforementioned studies [18][19][20], the differences in random mobility of EVs and in drivers' reaction to accident are considered. ...
... In [20], a global positioning system data was used to study the behaviour patterns of different EV users. In aforementioned studies [18][19][20], the differences in random mobility of EVs and in drivers' reaction to accident are considered. ...
Abstract Widespread adoption of electric vehicles (EVs) would significantly increase the electrical load demand in power distribution networks. Most previous studies investigated EV charging demand based on drivers’ trip habits, but the impact of psychological bearing ability (PBA) about the range anxiety on EV drivers’ charging decision are ignored. Here a novel forecast method considering drivers’ PBA for predicting nodal charging demand of EVs is proposed. The charging decision model considering PBA is established based on an improved Richards model, and the spatial‐temporal dynamics model is established based on the non‐homogeneous Markov chain (NMC) and random trip chain. Meanwhile, the Monte Carlo simulation (MCS) is adopted to avoid the disaster of dimensionality in large scale EVs charging problem. The proposed method is illustrated by an actual system integrated traffic network and power grid. The simulation results demonstrate that drivers’ PBA will significantly affect the charging decision, then changes the spatial‐temporal distribution of charging power demand. The conclusion is that the drivers with lower PBA have a higher charging demand, and the impact of drivers’ PBA on charging power has a close relation with the initial battery level (IBL) of EVs.
... In addition to GPS trajectory data and the data on charging sessions, some other big data sources, such as mobile phone data Yang et al. 2017), have also been used for the analysis of EV charging behavior as supplementary data. For example, Xu et al. (2018) estimated individual mobility of PHEV drivers using the mobile phone activity of 1.39 million residents in the San Francisco Bay Area, which was further used to analyze their charging behaviors. ...
The market penetration rate of electric vehicle (EV) is on the rise globally. However, the use behaviors of private EVs have not been well understood, in part due to the lack of proper datasets. This paper used a unique dataset containing trajectories of over 76,000 private EVs (accounting for 68% of the private EV fleet) in Beijing to uncover trip, parking and charging patterns of private EVs, so as to better inform policy making and infrastructure planning for different EV-related stakeholders, including planners, vehicle manufacturers, and power grid and infrastructure companies. We conducted both statistical and spatiotemporal analyses. In terms of statistical patterns, most of the EV trip distances (over 71%) were shorter than 15 km. Also, most of parking events (around 76%) lasted for less than 1 h. From a spatial perspective, the densities of trip Origins and Destinations (ODs), parking events and charging events in the central districts tended to be much higher than those of the other districts. Furthermore, the number of intra-district trips tended to be much higher than the number of inter-district trips. In terms of temporal trip patterns, there were two peak periods on working days: a morning peak period from 7 to 9 AM, and an afternoon peak period from 5 to 7 PM; On non-working days, there was only one peak period from 9 AM to 5 PM; while the temporal charging patterns on working and non-working days had a similar trend: most of EV drivers got their EVs charged overnight. Finally, we demonstrated how to apply the observed statistical and spatiotemporal patterns into policy making (i.e., time-of-use tariff) and infrastructure planning (i.e., deployment of normal charging posts, enroute fast charging stations and vehicle-to-grid enabled infrastructures).
... For example, a rapid transit system, consisting of small driverless electric vehicles traveling on a dedicated lane, has been developed to provide passengers with non-stop transit from origin to destination in urban areas [75]. In addition, several countries have set up a carpooling program to promote the use of electric cars and to map the performance [79] of the car-sharing service, including capillarity, flexibility, space, time, co-modality, rate, availability of incentives, types of vehicles, ease of access, ease of payment and reservation (See Table VI) [76]. ...
... In addition, several carpooling initiatives have been implemented to foster electric vehicle use. Table VII illustrates the contribution of ITS in electric vehicles by providing relevant information to drivers [79]. ...
Cities around the world are expanding dramatically, with urban population growth reaching nearly 2.5 billion people in urban areas and road traffic growth exceeding 1.2 billion cars by 2050. The economic contribution of the transport sector represents 5% of the GDP in Europe and costs an average of US $482.05 billion in the United States. These figures indicate the rapid rise of industrial cities and the urgent need to move from traditional cities to smart cities. This article provides a survey of different approaches and technologies such as intelligent transportation systems (ITS) that leverage communication technologies to help maintain road users safe while driving, as well as support autonomous mobility through the optimization of control systems. The role of ITS is strengthened when combined with accurate artificial intelligence models that are built to optimize urban planning, analyze crowd behavior and predict traffic conditions. AI-driven ITS is becoming possible thanks to the existence of a large volume of mobility data generated by billions of users through their use of new technologies and online social media. The optimization of urban planning enhances vehicle routing capabilities and solves traffic congestion problems, as discussed in this paper. From an ecological perspective, we discuss the measures and incentives provided to foster the use of mobility systems. We also underline the role of the political will in promoting open data in the transport sector, considered as an essential ingredient for developing technological solutions necessary for cities to become healthier and more sustainable.
... In this paper, the EVs are considered as the DR. Different from the general DR, the scheduling of EVs is affected by the driving of customs [15,16]. To research the scheduling of microgrid with EVs, there are two important pieces of knowledge of EVs need to introduce, the daily mileage and the return time of the last trip [17,18]. ...
It is an effective way to regard the electric vehicles as the demand response for reducing the negative impact of large‐scale introduction on the power system. Aiming at the microgrid with demand response, the adaptive uncertainty sets‐based two‐stage robust optimisation method is established in this study. The coordination of micro‐gas turbine, energy storage, and demand response etc. are considered in the economic dispatch model. To effectively consider the uncertain variable contained in the microgrid, the concept of adaptive uncertainty sets is proposed in this study. The uncertainty sets are achieved by the long short‐term memory network and modified fuzzy information granulation. To handle the adaptive uncertainty sets‐based robust optimisation model, the column and constraint generation algorithm and strong duality theory are introduced to decompose the model into a master problem and a subproblem with mixed‐integer linear structure. To verify the performance of the proposed adaptive uncertainty sets‐based two‐stage robust optimisation method, measured data from a plateau city of China are introduced in the simulation test. The simulation results demonstrate the effectiveness of the model and solution strategy.
... For example, a HitL system for EV charging and driving can introduce temporal uncertainty and spatial diversity into the charging behavior of the system. Correspondingly, ubiquitous sensing such as wireless sensor networks can make data acquisition more accessible [22] and thus reduce the uncertainty of the system [23]. Navigation information or incentives can be sent to the EV users to change their behavior and improve the system performance [15,17,18]. ...
... EVs can be considered as the interconnection of a traffic network (as traffic flow on roads), a power system (as charging load connected to electric power grids), and a human system (affected by user decisions and behavior) [23]. Individual users and their vehicles constitute fleets, which form on-road traffic flow in an IETS. ...
... System constraints include road capacity constraints in Eq. (21) and traffic load transition Eqs. (22) and (23). The uncertainty of upcoming changes in traffic load is defined in ...
This paper solves the vehicle assignment problem of an operating entity with dispatchable vehicles (e.g., an urban Integrated Energy-Traffic System (IETS) coordinator or an e-hailing company) in the context of energy-traffic coordinated modeling and analysis. Current research on electric vehicle (EV) scheduling and optimization has broadly assumed that human beings are rational decision-makers and obey the scheduling plan. In contrast, we proposed a user-centric dynamic pricing scheme that improves the system performance by incentivizing human participants to follow the expected behavioral patterns from a Cyber-Physical-Human System (CPHS) perspective. The interdisciplinary fields of power systems, traffic systems, and human decision-making were used to study the interactions in the CPHS. The proposed incentive scheme was applied to the urban IETS scenarios based on real-world Global Positioning System (GPS) data of EV taxis, and the results showed that it effectively optimized the integrated system.
... In the introduced computing architecture, these clustered vehicles work as opportunistic edge nodes to sense, process, and upload the real-time data, contributing to an efficient EVN operation [132], [133]. For instance, the real-time vehicular travelling data not only helps the operator track the on-road traffic condition [134], but also contributes to accurate EV travelling pattern prediction [135]. Their on-board computers empower them as edge computing nodes to perform a variety of computing tasks such as energy data pre-processing and battery management. ...
The connected vehicle paradigm empowers vehicles with the capability to communicate with neighboring vehicles and infrastructure, shifting the role of vehicles from a transportation tool to an intelligent service platform. Meanwhile, the transportation electrification pushes forward the electric vehicle (EV) commercialization to reduce the greenhouse gas emission by petroleum combustion. The unstoppable trends of connected vehicle and EVs transform the traditional vehicular system to an electric vehicular network (EVN), a clean, mobile, and safe system. However, due to the mobility and heterogeneity of the EVN, improper management of the network could result in charging overload and data congestion. Thus, energy and information management of the EVN should be carefully studied. In this paper, we provide a comprehensive survey on the deployment and management of EVN considering all three aspects of energy flow, data communication, and computation. We first introduce the management framework of EVN. Then, research works on the EV aggregator (AG) deployment are reviewed to provide energy and information infrastructure for the EVN. Based on the deployed AGs, we present the research work review on EV scheduling that includes both charging and vehicle-to-grid (V2G) scheduling. Moreover, related works on information communication and computing are surveyed under each scenario. Finally, we discuss open research issues in the EVN.
