Reinforcement Learning-Enabled Electric Vehicle Load Forecasting for Grid Energy Management

This paper describes “smart charging” systems for plug-in hybrid electric vehicles (PHEVs). The principal design feature is that the system uses gathered information to adaptively control PHEV charging, and does so in a way that allows customer PHEVs to still be charged at a preferred rate (cost). This paper reviews the drivers for smart charging, including electric grid readiness for large adoption rates of PHEVs, and considers national, regional and local distribution level issues. At the distribution level, the effect of increased PHEV charging loads on transformers is considered. The current state of standardization is reviewed with emphasis on communication messages and use cases that reflect smart charging attributes. Centralized system approaches are described, such as integrating electric vehicle supply equipment (EVSE), i.e. chargers, into Advanced Metering Infrastructure (AMI) networks, and treating EVSEs as controllable loads for Demand Response programs. Metering and monitoring the transformers that feed EVSEs can drive a control scheme that is either centralized or distributed. Alternatives to AMI-integration for centralized networks are also reviewed, including commercially available systems. Additionally, smart charging is considered from the billing perspective, where system approaches are described that allow for identification and association between connected PHEVs, EVSEs, premise meters and other smart devices.

The government policies and cost benefits led to the surge in penetration of Plug-in Hybrid Electric Vehicles (PHEVs) and Battery Electric Vehicles (BEVs) into both public and private sectors, challenging the electric grid's potential to maintain its stability and efficiently serve the purpose. The penetration of PHEVs brings technological advancements and environmental benefits to the traditional transportation and electrical power systems. Designing of appropriate charging methods to satisfy PHEV owners helps to improve system performance and avoid transmission and distribution system expansion.;The primary objective of this thesis is to model a coordinated charging algorithm to charge maximum number of PHEVs with the existing infrastructure at a Charging Station (CS) located in residential locality. The stochastic driving patterns of PHEVs are studied and different charging strategies are developed. The Optimized charging scheme is obtained for American Electric Power utility distribution feeder modeled in OpenDSS. Further, PHEV customers are modeled into price responsive consumers capable of participating in Demand Response programs to economically charge their vehicles and render support to the stabilization of power system. Consumer behavior modeling has been done by developing extensive demand-price elasticity matrices (PEMs) which are utilized to calculate the level of demand response.;This thesis also proposes a concept of converting the existing Personal Rapid Transit (PRT) system from guideway power rail propelling vehicles to Battery Electric Vehicles (BEVs) by developing a novel routing algorithm based on the data provided by West Virginia University's Department of Transportation and Parking. This turns into a feasibility analysis of implementing new EV technologies in electrification of public transportation. The routing algorithm involves Mixed Integer Linear Programming (MILP) Optimization resulting in hourly schedule of all the vehicles satisfying the passenger demand. The effect of charging load of BEVs on the electrical distribution system is analyzed by performing a time series simulation on AEP distribution feeder.;Additionally, the impact of PHEV charging on power market prices i.e. Locational Marginal Prices (LMP) in a distribution microgid scenario is presented. Locational marginal pricing is a market based wholesale pricing approach adopted by six out of ten national electricity markets. The uncoordinated charging of EVs results in unplanned peak demand causing system changes and fluctuation of LMP. The stabilizing effect of coordinated charging scheme is demonstrated on IEEE 13 Node test system.

The key elements in an indirect V2G system architecture are aggregators. They act as an interface between the grid and a group of plug-in hybrid electric vehicles (PHEVs). In this paper, we design an optimal vehicle to grid (V2G) aggregator to control the charging and frequency regulation processes of a group of PHEVs. We consider a problem that an aggregator has to minimize the overall cost of PHEV fleet in a multiple time slot horizon and meet the required battery level when PHEVs plug out. We adopt summation of PHEVs' expenditure in a finite number of time slots as our objective function, which is a quadratic optimization problem. A model predictive control based (MPC-based) PHEV charging and regulation algorithm is proposed to schedule the charging and regulation processes. Through the numerical experiments, we obtain the optimal charging and frequency regulation sequences for each PHEV, the effect of price prediction error on PHEV's cost as well as the impact of penalty factor to plug-out State of Charge (SOC). It is also shown that by taking the optimal control sequences, the PHEV owner can reduce his cost and depart with desired SOC.

The adoption of plug-in hybrid electric vehicles (PHEV) as a means of transportation over conventionally fueled vehicles introduces new challenges to the existing infrastructure of the electrical transmission and distribution system. PHEV battery charging can represent a significant power demand that has the potential to overload electrical distribution components. This study examines the impacts of PHEV charging on household service transformers, distribution conductors and voltage levels of a Central California residential distribution system. The system is simulated using ETAP power system analysis software. Transformers are the most vulnerable to overloads, especially if PHEV charging occurs in clusters. Main feeder conductors will be overloaded if a large amount of high power, quick charging occurs. Branch conductors will not be affected by PHEV charging. Based on current PHEV market projections for the region this study shows that significant equipment overloads are not likely to occur until well after 2017.

The combination of high oil costs, concerns about oil security and availability, and air quality issues related to vehicle emissions are driving interest in plug-in hybrid electric vehicles (PHEVs). PHEVs are similar to conventional hybrid electric vehicles, but feature a larger battery and plug-in charger that allows electricity from the grid to replace a portion of the petroleum-fueled drive energy. PHEVs may derive a substantial fraction of their miles from grid-derived electricity, but without the range restrictions of pure battery electric vehicles. As of early 2007, production of PHEVs is essentially limited to demonstration vehicles and prototypes. However, the technology has received considerable attention from the media, national security interests, environmental organizations, and the electric power industry. The use of PHEVs would represent a significant potential shift in the use of electricity and the operation of electric power systems. Electrification of the transportation sector could increase generation capacity and transmission and distribution (T&D) requirements, especially if vehicles are charged during periods of high demand. This study is designed to evaluate several of these PHEV-charging impacts on utility system operations within the Xcel Energy Colorado service territory.

Routing a mix of conventional, plug-in hybrid, and electric vehicles

The rising concerns over global climate change and depleting fossil fuel reserves are two of the main reasons for the ongoing efforts towards the electrification of the transportation sector. While greenhouse gases (GHGs) emissions from other sectors are generally falling, emissions from the road transport have increased over the past few decades, with both full electric vehicles (FEVs) and plug-in hybrid electric vehicles (PHEVs) being recognized as potential alternatives to combat climate change and reduce GHG emissions. However, wide-spread integration of FEVs and PHEVs will substantially increase the load on the power system which will eventually affect the reliability of existing power systems. In this paper, a probabilistic model for integrating FEVs and PHEVs with existing power grids is proposed that incorporates important FEV and PHEV characteristics, such as battery capacity, charge depleting distance, and charging rates. In addition, user behavior is taken into account through time of recharging, arrival and departure times, and daily miles driven. Furthermore, different charging strategies, i.e., opportunistic charging and controlled charging with and without vehicle-to-grid (V2G) scheme have been considered to evaluate the impact of FEVs and PHEVs on the composite power system. IEEE-RTS-79 system is used to examine the proposed probabilistic technique considering different FEV and PHEV penetration levels as well as charging strategies. Simulation results show that even a relatively low penetration level of FEVs or PHEVs might have a significant impact on the system reliability unless a proper charging and/or discharging schemes are utilized.

Author(s): Muehlegger, Erich; Rapson, David | Abstract: This research project explores the plug-in electric vehicle (PEV) market, including both Battery Electric Vehicles (BEVs) and Plug-in Hybrid Electric Vehicles (PHEVs), and the sociodemographic characteristics of purchasing households. The authors use detailed micro-level data on PEV purchase records to answer two primary research questions. Their results confirm that low-income households exhibit a lower share of PEV purchases than they do for conventional, internal combustion engine (ICE) vehicles. Households with annual income less than $50,000 comprise 33 percent of ICE purchases and only 14 percent of PEVS. By comparison, high-income households earning more than $150,000 annually comprise only 12 percent of ICE purchases and 35 percent of PEV purchases over their sample period. Similarly, unsurprising patterns can be seen across ethnicities. For example, non-Hispanic Whites represent 41 percent of ICE purchases but 55 percent of PEV purchases, as compared to Hispanics (38 percent of ICE and 10 percent of PEVs) and African Americans (3 percent of ICEs and 2 percent of PEVS). These differences naturally raise questions about barriers to PEV adoption among low-income and minority ethnic populations. By comparing outcomes in the ICE, hybrid, and PEV markets across income and ethnic groups, the authors are able to test whether price discrimination and barriers to market access are higher in PEV markets for low-income and minority ethnic groups. The authors find that, overall, they are not, although there are mixed results for the used PEV market. In general, non-white, low-income populations face higher prices in the used PEV market, relative to a baseline, than they do in the new PEV market. While some people travel farther to buy used PEVs than they do to buy used ICE vehicles, there is not a pattern that would indicate systematic discrimination (e.g. Hispanics travel farther to buy used PHEVs but less far to buy used BEVs). While the authors admit that their empirical approach cannot control for all potential vehicle composition effects, the authors view their results as being most consistent with a market that provides access to all ethnicities and income groups.View the NCST Project Webpage

Microscopic series plug-in hybrid electric vehicle energy consumption model: Model development and validation

Plug-in hybrid electric vehicle (PHEV) presents the new trend of clean energy vehicle development due to their advantage of all electric driving, allowable external charging, lower emissions, and lower petroleum fuel consumption, comparing to the maturing HEV. Applications of advanced plug-in hybrid powertrain system technology to different type of vehicles lead to the need to identify the key characteristics of these different vehicular applications, and to develop more systematic and effective powertrain design methods. In this work two different types of PHEV powertrain architecture were investigated: a) pre- trans series-parallel multi-regime plug-in hybrid electric commercial vehicle (SPMR-PHEV), and b) post-trans parallel plug-in hybrid electric formula racing car. Model-based design (MBD) methods were used for powertrain system modelling of the two PHEV applications. With the powertrain system models developed using MATLAB Simulink and dSPACE Automotive Simulation Models (ASM), the powertrain configurations, control strategies and key features were investigated. The simulation results on standard driving cycles for each model using different rule-based control strategies were compared. The differences and key features of two types of vehicle in design and calibration were presented and analyzed.

As the penetration level of plug-in hybrid electric vehicles (PHEVs) increases, the stress on the distribution system will become more pronounced. In this paper, we concentrate on PHEV charging in public infrastructures, such as shared parking lots in commercial office campuses and shopping malls. In such clustered scenarios, PHEV charging demand can vary significantly and stochastically with time, and the overall system performance is a result of a trade-off between the peak load on the distribution system and the consumer specified charging deadlines that are met successfully. However, unlike distributed residential charging, those scenarios can benefit from centralized algorithms to schedule the charging of vehicles. This paper considers the design of such scheduling algorithms. We show that through proper design of the scheduling algorithms, the parking lot owner can balance distribution system load with quality of charging service.

Nowadays the shortfall of petroleum and natural gas are believed as one of the most serious issues world-wide. Besides, car owners globally, in general, spend more money at the petroleum and gas station than they have done forever before. The most realistic way out to the transportation industry oil consumption crisis difficulties lies in commercially plug in hybrid electric vehicles (PHEVs). Electric Vehicles (EVs) and PHEVs fulfill a significant role to reduce greenhouse gases and necessity on oil. This paper evaluates the battery performance of PHEV in a vehicle to grid approach, which gives an inexpensive explanation for designing a unified power quality conditioner using PHEV charging station

Cost-effectiveness of plug-in hybrid electric vehicle battery capacity and charging infrastructure investment for reducing US gasoline consumption

Concern for the environment and energy security is changing the way we think about energy. Grid-enabled passenger vehicles, like electric vehicles (EV) and plug-in hybrid electric vehicles (PHEV) can help address environmental and energy issues. Automakers have recognized that electric drive vehicles are critical to the future of the industry. However, some challenges exist to greater adoption: the perception of cost, EV range, access to charging, potential impacts to the grid, and lack of public awareness about the availability and practicality of these vehicles. Although the current initial price for EV's is higher, their operating costs are lower. Policies that reduce the total cost of ownership of EVs and PHEVs, compared to conventional internal combustion engine (ICE) vehicles, will lead to faster market penetration. Greater access to charging infrastructure will also accelerate public adoption. Smart grid technology will optimize the vehicle integration with the grid, allowing intelligent and efficient use of energy. By coordinating efforts and using a systems perspective, the advantages of EVs and PHEVs can be achieved using the least resources. This paper analyzes these factors, their rate of acceleration and how they may synergistically align for the electrification of vehicles.

Charging performance of Plug-in Hybrid Electric Vehicles (PHEVs) under various charging approaches brings new challenges for the distribution grid, such as feeder overloading and increment of loss. In this paper, the impact of charging PHEVs on the load profile is evaluated considering Demand Response (DR) programs in order to minimize the impact of charging PHEVs on load profile. In the proposed DR strategy, all consumers can determine and control their loads. Also, the proposed DR strategy can satisfy the function of reducing peak with regard to different PHEV penetration, while preserving consumer comfort levels. For performing DR programs, time of use and real time pricing models are used to evaluate the impacts of charging of PHEVs on distribution system operations. A 33-node test feeder has been studied to assess different penetration schemes of PHEVs including 11.3%, 35% and 45% PHEV penetration in residential loads. Moreover, uncertainties associated with PHEV charging performances are handled with Monte Carlo simulation. Results validate that the amount of peak loss, and Peak to Average Ratio (PAR) increase owing to PHEVs penetration growth. Also, the results illustrate that scheduling for the operation of PHEVs with DR program reduces the distribution losses and PAR.