Optimal placement of electrical vehicle charging stations

Abstract

A method for determining an optimal placement of an electric vehicle charging station includes receiving electric vehicle (EV) user data, climate data, and power grid data for a region, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data, calculating probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region, determining an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region, and providing the optimal location for the EV charging station.

Description

OPTIMAL PLACEMENT OF ELECTRICAL VEHICLE CHARGING STATIONSBACKGROUND

[0001] Electric vehicles (EVs) include an electric motor that is typically driven by a charge stored in a battery as opposed to an internal combustion engine that is driven by the combustion of fossil fuel. The EV batteries can be large traction battery packs that require recharging, which can be accomplished by plugging the electric motor into a wall outlet or an EV charging station.

[0002] There is significant research ongoing into the optimal site locations of EV charging stations. Current considerations of placing EV charging stations can include factors such as location accessibility, number of EVs that can access the charging station at one time, number of EVs that pass the location of the EV charging station, etc. However, when the EV charging station obtains power from solar panels and / or other renewable energy sources placed at the charging station, additional factors should be considered.BRIEF SUMMARY

[0003] Methods and systems for determining an optimal placement of an electric vehicle charging station are provided herein. Advantageously, by analyzing additional factors related to the feasibility of different locations within a region with respect to renewable energy resources and environmental impact along with current considerations of placing EV charging stations, optimal locations for new EV charging stations can be determined. The optimal placement of EV charging stations allows for low environmental impact along with energy reliability even when the power grid may not be reliable within that region.

[0004] A method for determining an optimal placement of an electric vehicle charging station includes receiving electric vehicle (EV) user data, climate data, and power grid data for a region, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data, calculating probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region, determining an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region, and providing the optimal location for the EV charging station.

[0005] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 illustrates a representational diagram of an operating environment for an optimal EV charging station location system.

[0007] Figure 2 illustrates a method for determining an optimal placement of an electric vehicle charging station.

[0008] Figure 3 illustrates a specific process flow for determining an optimal placement of an electric vehicle charging station.

[0009] Figure 4 illustrates components of a computing device that may be used in certain embodiments described herein.DETAILED DESCRIPTION

[0010] Methods and systems for determining an optimal placement of an electric vehicle charging station are provided herein. Advantageously, by analyzing additional factors related to the feasibility of different locations within a region with respect to renewable energy resources and environmental impact along with current considerations of placing EV charging stations, optimal locations for new EV charging stations can be determined. The optimal placement of EV charging stations allows for low environmental impact along with energy reliability even when the power grid may not be reliable within that region.

[0011] Figure 1 illustrates a representational diagram of an operating environment for an optimal EV charging station location system. Referring to Figure 1, an example operating environment 100 includes an optimal EV charging station location (OEVCSL) system 102, an optimal EV charging system location (OEVCSL) storage 104, and a plurality of data sources 106. The plurality of data sources includes, but is not limited to, an EV user data source 108, a climate data source 110, and a power grid data source 112. In some cases, the OEVCSL storage 104 is part of the OEVCSL system 102. In some cases, the OEVCSL storage 104 is external from the OEVCSL system 102.

[0012] Figure 2 illustrates a method for determining an optimal placement of an electric vehicle charging station. Referring to Figures 1 and 2, a method 200 for determining an optimal placement of an electric vehicle charging station includes receiving, by the OEVCSL system102, (202) electric vehicle (EV) user data, climate data, and power grid data for a region. The EV user data, climate data, and power grid data for the region is received by the OEVCSL storage 104 and then received (202) by the OEVCSL system 102. In some cases in which the OEVCSL storage 104 is part of the OEVCSL system 102, the EV user data, climate data, and power grid data for the region is received by the OEVCSL system 102 and stored in the OEVCSL storage 104. The EV user data is sent by the EV user data source 108. The climate data is sent by the climate data source 110. The power grid data is sent by the power grid data source 112. In some cases, the EV user data, climate data, and power grid data for the region is collected in real-time.

[0013] In some cases, the EV user data includes traffic data, EV battery data, and / or user driving habit data. In some cases, the climate data includes satellite data and / or weather data. Although the EV user data source 108, the climate data source 110, and the power grid data source 112 may be a singular source and / or entity, in some cases, each of these sources and / or entities may include multiple sources and / or entities, as explained in detail below.

[0014] The EV user data source 108 can include cameras (e.g., public and / or private cameras) scanning a number of license plates, road sensors counting the number of vehicles over a period of time, and / or smartphones or computing systems in vehicles that are tracked via Global Positioning System (GPS). This EV user data can be considered traffic data and can be accessed via an application programming interface (API) of the OEVCSL system 102. The EV user data source 108 can further include EV operating systems that provide the state of charge and battery life of the batteries in the EV. This EV user data can be considered can be considered EV battery data and can be accessed via an API of the OEVCSL system 102 and / or collected from the manufacturer of the EV. The EV user data source 108 can further include smartphones or computing systems in vehicles that track the details of each journey taken by a user of the vehicle, including departure time and date, route, time at waypoints, and / or arrival time. This EV user data can be considered user driving habit data and can be accessed via an API of the OEVCSL system 102 and / or collected from the manufacturer of the vehicle.

[0015] The climate data source 110 can include satellite data from satellites that include thermal infrared sensors that collect surface temperature data. This climate data can be considered satellite data and can be accessed via an API of the OEVCSL system 102. The climate data source 110 can further include almanacs, historical and real-time weather data collections, and other known sources of weather data. This climate data can be consideredweather data and can be accessed via an API of the OEVCSL system 102. In some cases, the weather data includes time-stamped data on temperature, wind, and precipitation within the region and / or locations within the region.

[0016] The method 200 for determining, by the OEVCSL system 102, an optimal placement of an EV charging station further includes determining (204) EV charging conditions for the region based on the EV user data, the climate data, and the power grid.

[0017] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes creating a sunlight heatmap of a plurality locations within the region based on the satellite data. The sunlight heatmap is useful to determine whether solar panels are viable for a particular location within the region based on the amount of sunlight received at that location. The sunlight heatmap can include sun exposure (count map) levels for each potential EV charging station site along a given road within the region, which enables identification of optimal locations for building the EV charging station (for maximum energy generation efficiency) as well as placement of solar panels for the EV charging station. For example, the placement of solar panels for the EV charging station may be on a roof, wall, and / or other structure associated with the EV charging station and / or in an area of the location of the EV charging station that, directly or indirectly, abuts the EV charging station itself. The sunlight heatmap also captures information of how shadows cast from buildings, trees, and other structures impede sunlight to a location. In some cases, the sunlight heatmap can be used to determine whether a location for the EV charging station has the potential to be energy independent of power from a power grid. For example, the EV charging station can capture all of the necessary power and / or energy from solar panels and / or other renewable energy resources (e.g., wind turbines and / or hydroelectric power) and not require any additional power and / or energy from a traditional power grid.

[0018] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes determining a high-traffic condition for each of the one or more specific locations within the region based on the traffic data. By analyzing the traffic data, patterns of EV and internal combustion engine vehicle movement can be used to determine an optimal location(s) for the EV charging station that includes high-traffic, ensuring convenient access for EV owners along a route they normally travel. In some cases, the traffic data only includes EV traffic data.

[0019] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes determining battery life and condition for individual EVs based on EV battery data. This determination ensures thatan EV charging station(s) is placed in a location(s) that can be reached by the EV (based on how far the EV can be driven before charging) as well as how long it will take to charge the battery of the EV (which can help determine how many chargers are required at the charging station).

[0020] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes determining individual EV users driving habits based on the user driving habit data. The driving habit data can be used to estimate the life of the battery and the time to reach the destination of the EV user. This data can include a set of coefficients or a distribution representing the EV user’s propensity to undertake certain types of journeys at different times of the day, week, month, and / or year. This data can further include a set of coefficients or a distribution representing the EV user’s propensity to undertake certain types of journeys under different conditions, such as weather conditions. This determination can be made using multivariate regression and / or a neural network such as an autoencoder for an efficient representation.

[0021] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes estimating a traffic condition for each of the one or more specific locations within the region based on the weather data. For example, weather conditions, such as rain, snow, storms, etc. impact traffic conditions and the time to reach the EV charging station and / or final destination of the EV user. Therefore, by analyzing the affect of the weather on the traffic condition, estimates of the traffic condition(s) and impact on EV charging behavior ofEV users over a future period oftime (e.g., minutes, hours, days, and / or months) can be determined.

[0022] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes determining destinations for individual EV users based on the user driving habits. The destination for an EV user may or may not be known, depending on whether the EV user inputs their destination into a system (e.g., GPS via voice interface and / or typing the destination into a keyboard and / or interface). If the destination is not known, the OEVCSL system 102 can estimate the most likely destinations and distance to be traveled based on the EV user’s driving habit data.

[0023] In some cases, determining (204) the EV charging conditions for the region based on the EV user data, the climate data, and the power grid includes estimating energy availability for the one or more specific locations within the region based on the power grid data. For example, this step can include investigating the status of the power grid in the region, including peak demand times and load fluctuations throughout the day. This step can alsoinclude the use of demand response programs, analyzing electricity consumption patterns by locations within the region, distinguishing areas with high demand and potential for EV adoption, and / or monitoring of large energy users.

[0024] In some cases, any of the above variations of the determining (204) step can be used in conjunction and / or in addition to any and / or all of the above variations of the determining (204) step. In some cases, the results of the determining (204) step are stored in the OEVCSL storage 104 for further use.

[0025] The method 200 for determining, by the OEVCSL system 102, an optimal placement of an EV charging station further includes calculating (206) probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region. In some cases, calculating (206) probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region is performed by a convolution neural network. In some cases, the convolution neural network is pre-trained by the OEVCSL system 102 and updated periodically as needed (e.g., every week, but this is dependent on recurrent validation of performance in the OEVCSL system 102).

[0026] As an example of calculating (206) probability distributions for the plurality of EV charging parameters for the one or more specific locations within the region based on the determined EV charging conditions for the region, consider the previously described sunlight heatmap. The sunlight heatmap may be used to calculate (206) probability distributions, at a specific location, that determine energy independence (e.g., energy independence from reliance on an externa power grid) as a percentage of time that the placement of solar panels at a specific location can be used to provide enough power for the EV charging station and / or a percentage of the power for the EV charging station that the placement of solar panels at a specific location can provide.

[0027] The method 200 for determining, by the OEVCSL system 102, an optimal placement of an EV charging station further includes determining (208) an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region. The outputs of the calculating (206) step are used in the determining (208) step. For example, the outputs of the calculating (206) step are used in the simulation(s) in order to identify an optimal set of actions for an actor for an actor (e.g., EV user and / or system planner) to determine the optimal location of the EV charging station. Each simulation combines the plurality of EV charging parameters for the one or more corresponding specificlocations within the region. In some cases, the EV charging parameters include energy independence, environmental impact, scalable charging location design capability, and / or wireless EV charging unit capability. In some cases, the simulation for each of the one or more specific locations within the region determines an individual rating for each of energy independence, environmental impact, scalable charging location design capability, and / or wireless EV charging unit capability and uses those individual ratings to determine the optimal location for the EV charging station.

[0028] In some cases, these individual ratings for each of the EV charging parameters can be summed to determine the optimal location. In some cases, these individual ratings for each of the EV charging parameters can be weighted according to preference and / or importance, which may be tied to the geographical area of the region itself. In some cases, minimum thresholds for one or more of the ratings may be used to disqualify locations of the one or more specific locations within the region. In some cases, the individual ratings for each of the EV charging parameters can be used in a combination of any of the ways described above. In some cases, the simulation for each of the one or more specific locations within the region are performed using a Monte Carlo simulation method.

[0029] Energy independence of EV charging stations includes simulating the ability for each location to produce energy. This involves producing energy by integrating renewable energy resources, such as solar panels and / or wind turbines, into the EV charging station. Therefore, the EV charging stations can have the ability to operate independently of the power grid. Furthermore, energy independence can include storing of excess energy in batteries (and the location of those batteries within the EV charging station) so that EVs can be charged even when the renewable energy sources are not producing energy (e.g., the sun is not shining for solar panels and / or the wind is not moving for wind turbines). In some cases, the energy produced by the solar panels and / or other renewable energy source(s) can be used to directly provide power to EVs and / or to store in batteries at the EV charging station that are later used to charge EVs. In some cases, energy independence includes whether a location for the EV charging station has the potential to be energy independent of power from a power grid (e.g., an external energy source outside of the EV charging station). For example, the EV charging station can capture all of the necessary power and / or energy from solar panels and / or other renewable energy resources and not require any additional power and / or energy from a traditional power grid. In some cases, energy independence may not be feasible 100% of the time in a location within a region; accordingly, an EV charging station may still require access to the power grid for some energy at certain times. It should be understood that a first locationwithin the region that provides more energy independence from the power grid (even if not complete energy independence) than a second location will receive a “better” and / or “higher” energy independence rating than the second location.

[0030] Environmental impact of EV charging stations includes simulating the environmental impact of an EV charging station at a specific location. By accompanying satellite data with advanced data from environmental sensors, the OEVCSL system 102 monitors numerous parameters such as air quality, soil health, and / or noise levels. By gathering this real-time data, objective evaluation metrics of the environmental impact of placing an EV charging station in a specific location are produced. The design of EV charging stations can also be altered to minimize the ecological footprint on the surrounding environment, including lowering unnecessary energy consumption, choice of materials to build the EV charging station, and / or selecting locations that do not disrupt natural habitats and / or ecosystems. For example, a location directly abutting a river may have more of an environmental impact than a location that is not near a water source. Therefore, if all other things are equal, the location that is not near the water source may be selected as the optimal location for the EV charging station. The environmental impact can also take into account other information, such as but not limited to, historical buildings, schools, and other existing infrastructure that cannot be destroyed / altered for an EV charging station.

[0031] Scalable charging location design of EV charging stations includes simulating the ability to use interchangeable components so that as technology advances, that components can be changed out for newer technology, as well as the ability to expand the charging station by adding more chargers as more drivers switch to EVs. Furthermore, the more modular the design and the specific location in which the EV charging station is placed, the easier these changes and / or additions can be made without interrupting the entire EV charging station.

[0032] Wireless EV charging units can be important for several reasons, including but not limited to, accessibility for EV users with mobility challenges and reduction and / or elimination of cords and bulky chargers that are subject to damage and may not be aesthetically pleasing. Including the feasibility of adding wireless EV charging units to a simulation for a specific location within the region further enhances the determination of the optimal EV charging station.

[0033] The method 200 for determining, by the OEVCSL system 102, an optimal placement of an EV charging station further includes providing (210) the optimal location for the EV charging station. For example, the optimal location can be provided (210) to a source of the request. In some cases, the source of the request can be a city, municipality, and / or othergovernmental entity. In some cases, the source of the request can be an electrical utility provider (e.g., a power company). In some cases, the source of the request can be an EV manufacturer. In some cases, the source of the request can be a private business. In any case, the optimal location for the EV charging station can be provided (210) through an app, an email, text, and / or other form of electronic communication and / or in a display of the OEVCSL system 102.

[0034] Figure 3 illustrates a specific process flow for determining an optimal placement of an electric vehicle charging station. Referring to Figure 3, a specific process flow 300 for determining an optimal placement of an electric vehicle charging station includes data collection 302 by a data collection platform and / or module. The data collection 302 can include one or more of EV traffic data 304, satellite data 306, power grid data 308, EV battery data 310, user driving habit data 312, and weather data 314. The data collected is then stored in data storage 316.

[0035] The specific process flow 300 for determining an optimal placement of an electric vehicle charging station further includes a data integration platform 320 and / or module accessing the data collected from the data storage 316 to perform analysis on the data. The analysis performed on the data collected from the data storage 316 by the data integration platform 320 includes one or more of satellite data analysis 322, power grid data analysis 324, traffic flow data analysis 326, EV battery life data analysis 328, driving habit data analysis 330, weather data analysis 332. The analysis performed on the data collected from the data storage 316 by the data integration platform 320 further includes determining 334 whether a destination for an EV user is known. In cases in which the destination for individual EV users is known, destination data analysis 336 is performed and the intermediate results for all analyses are stored 338. In cases in which the destination for individual EV users is not known, the destination data analysis may be forgone and the intermediate results for all other analyses are stored 338.

[0036] The specific process flow 300 for determining an optimal placement of an electric vehicle charging station further includes simulations 340 for locations within a region using the intermediate results for all analyses. These simulations 340 may be performed by a simulations platform and / or module. The simulations 340 include one or more of an energy independence simulation 342, an environmental impact simulation 344, a scalable charging location design simulation 346, and a wireless charging simulation 348.

[0037] The results of the simulations 340 determine the optimal location of the electric vehicle charging station. In some cases, the determination of the optimal location of the electricvehicle charging station is given to the recommendation system 350. In some cases, the simulations 340 themselves are given to the recommendation system 350 and the recommendation system 350 determines the optimal location of the electric vehicle charging station based on the simulations 340.

[0038] The recommendation system 350 can includes provide the optimal location for the EV charging station 352, for example, to a source of the request. In some cases, the recommendation system 350 can further provide an optimal location to charge a user’s EV 354.The specific process flow 300 for determining an optimal placement of an electric vehicle charging station then finishes 356.

[0039] Figure 4 illustrates components of a computing device that may be used in certain embodiments described herein. Referring to Figure 4, system 400 may represent a computing device such as, but not limited to, a personal computer, a reader, a mobile device, a personal digital assistant, a wearable computer, a smart phone, a tablet, a laptop computer (notebook or netbook), a hybrid computer, or a desktop computer. Accordingly, more or fewer elements described with respect to system 400 may be incorporated to implement a particular computing device.

[0040] System 400 includes a processing system 405 of one or more processors to transform or manipulate data according to the instructions of software 410, such as method 200 of Figure 2 and / or process flow 300 of Figure 3, stored on a storage system 415. Examples of processors of the processing system 405 include general purpose central processing units, application specific processors, and logic devices, as well as any other type of processing device, combinations, or variations thereof. System 400 can include OEVCSL system 102 of Figure 1.

[0041] Processing system 405 can include one or more of any suitable processing devices (“processors”), such as a microprocessor, central processing unit (CPU), graphics processing unit (GPU), field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), logic circuits, and state machines.

[0042] Storage system 415 may comprise any computer readable storage media readable by the processing system 405 and capable of storing software 410. Storage system 415 may include volatile and nonvolatile memories, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. Examples of storage media of storage system 415 include random access memory, read only memory, magnetic disks, optical disks, CDs, DVDs, flash memory, magnetic cassettes, magnetic tape, magneticdisk storage or other magnetic storage devices, or any other suitable storage media. In no case is the storage medium a transitory propagated signal.

[0043] Storage system 415 may be implemented as a single storage device but may also be implemented across multiple storage devices or sub-systems co-located or distributed relative to each other. Storage system 415 may include additional elements, such as a controller, capable of communicating with processing system 405. Storage system 415 can include OEVCSL storage 104 of Figure 1.

[0044] Software 410 may be implemented in program instructions, such as method 200 of Figure 2 and / or process flow 300 of Figure 3, and among other functions may, when executed by system 400 in general or processing system 405 in particular, direct system 400 or the one or more processors of processing system 405 to operate as described herein. In some cases, the Monte Carlo simulation method is implemented on software, such as software 410.In some cases, a neural network, such as a convolution neural network, is implemented as an algorithm running on the system 400. In some cases, a neural network, such as a convolution neural network, is implemented on one or more processors (e.g., processing system 405) executing instructions and / or implemented on hardware (e.g., FPGAs and / or ASICs), where some or all of the neural network operations performed in software, hardware, or a combination thereof.

[0045] The system can further include user interface system 430, which may include input / output (I / O) devices and components that enable communication between a user and the system 400. User interface system 430 can include input devices such as a mouse, track pad, keyboard, a touch device for receiving a touch gesture from a user, a motion input device for detecting non-touch gestures and other motions by a user, a microphone for detecting speech, and other types of input devices and their associated processing elements capable of receiving user input.

[0046] The user interface system 430 may also include user interface software and associated software (e.g., for graphics chips and input devices) executed by the operating system (OS) in support of the various user input and output devices. The associated software assists the OS in communicating user interface hardware events to application programs using defined mechanisms. The user interface system 430 including user interface software may support a graphical user interface, a natural user interface, or any other type of user interface.

[0047] Network interface 440 may include communications connections and devices that allow for communication with other computing systems, over one or more communication networks (not shown). Communication with other computing systems can include requestingand / or receiving information and / or data from, for example, the plurality of data sources 106 of Figure 1. Examples of connections and devices that together allow for inter-system communication may include network interface cards, antennas, power amplifiers, RF circuitry, transceivers, and other communication circuitry. The connections and devices may communicate over communication media (such as metal, glass, air, or any other suitable communication media) to exchange communications with other computing systems or networks of systems.

[0048] Clause 1. A method comprising: receiving electric vehicle (EV) user data, climate data, and power grid data for a region; determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data; calculating probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region; determining an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region; and providing the optimal location for the EV charging station.

[0049] Clause 2. The method of clause 1, wherein the EV user data comprises traffic data, EV battery data, and user driving habit data, wherein the climate data comprises satellite data and weather data.

[0050] Clause 3. The method of clause 1 or 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises creating a sunlight heatmap of the one or more specific locations within the region based on the satellite data.

[0051] Clause 4. The method of any clause 1-3, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining a high-traffic condition for each the one or more specific locations within the region based on the traffic data.

[0052] Clause 5. The method of any clause 1-4, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining battery life and condition for individual EVs based on EV battery data.

[0053] Clause 6. The method of any clause 1-5, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining individual EV users driving habits based on the user driving habit data.

[0054] Clause 7. The method of any clause 1-6, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises estimating a traffic condition for each of the one or more specific locations within the region based on the weather data.

[0055] Clause 8. The method of any clause 1-7, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining destinations for individual EV users based on the user driving habit data.

[0056] Clause 9. The method of any clause 1-8, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises estimating energy availability for the one or more specific locations within the region based on the power grid data.

[0057] Clause 10. The method of any clause 1-9, wherein calculating probability distributions for the plurality of EV charging parameters for the one or more specific locations within the region based on the determined EV charging conditions for the region is performed by a convolution neural network.

[0058] Clause 11. The method of any clause 1-10, wherein the simulation for each of the one or more specific locations within the region determines a rating for energy independence, environmental impact, scalable charging location capability, and wireless EV charging capability.

[0059] Clause 12. The method of any clause 1-11, wherein the simulation for each of the one or more specific locations within the region are performed using a Monte Carlo simulation method.

[0060] Clause 13. The method of any clause 1-12, wherein the optimal location for the EV charging station is energy independent of power from a power grid.

[0061] Clause 14. A system comprising: a processing system; one or more storage media; and instructions stored on the one or more storage media that, when executed by the processing system, direct the processing system to at least: receive electric vehicle (EV) user data, climate data, and power grid data for a region; determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data; calculate probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region; determine an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the pluralityof EV charging parameters for the corresponding one or more specific locations within the region; and provide the optimal location for the EV charging station.

[0062] Clause 15. The system of clause 14, wherein the EV user data comprises traffic data, EV battery data, and user driving habit data, wherein the climate data comprises satellite data and weather data.

[0063] Clause 16. The system of clause 14 or 15, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises creating a sunlight heatmap of the one or more specific locations within the region based on the satellite data.

[0064] Clause 17. The system of any clause 14-16, wherein the instructions that direct the processing system to determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining a high-traffic condition for each of the one or more specific locations within the region based on the traffic data.

[0065] Clause 18. The system of any clause 14-17, wherein the simulation for each of the one or more specific locations within the region determines a rating for energy independence, environmental impact, scalable charging location capability, and wireless EV charging capability.

[0066] Clause 19. The system of any clause 14-18, wherein the optimal location for the EV charging station is energy independent of power from a power grid.

[0067] Clause 20. One or more computer readable storage media having instructions stored thereon that, when executed by a processing system, direct the processing system to at least: receive electric vehicle (EV) user data, climate data, and power grid data for a region; determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data; calculate probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region; determine an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region; and provide the optimal location for the EV charging station.

[0068] Although the subj ect matter has been described in language specific to structural features and / or acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as examples of implementing the claims andother equivalent features and acts that would be recognized by one skilled in the art are intended to be within the scope of the claims.

Claims

CLAIMSWhat is claimed is:

1. A method comprising:receiving electric vehicle (EV) user data, climate data, and power grid data for a region;determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data;calculating probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region;determining an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region; andproviding the optimal location for the EV charging station.

2. The method of claim 1, wherein the EV user data comprises traffic data, EV battery data, and user driving habit data, wherein the climate data comprises satellite data and weather data.

3. The method of claim 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises creating a sunlight heatmap of the one or more specific locations within the region based on the satellite data.

4. The method of claim 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining a high-traffic condition for each the one or more specific locations within the region based on the traffic data.

5. The method of claim 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining battery life and condition for individual EVs based on EV battery data.

6. The method of claim 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining individual EV users driving habits based on the user driving habit data.

7. The method of claim 2, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises estimating a traffic condition for each of the one or more specific locations within the region based on the weather data.

8. The method of claim 2, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining destinations for individual EV users based on the user driving habit data.

9. The method of claim 1, determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises estimating energy availability for the one or more specific locations within the region based on the power grid data.

10. The method of claim 1, wherein calculating probability distributions for the plurality of EV charging parameters for the one or more specific locations within the region based on the determined EV charging conditions for the region is performed by a convolution neural network.

11. The method of claim 1, wherein the simulation for each of the one or more specific locations within the region determines a rating for energy independence, environmental impact, scalable charging location capability, and wireless EV charging capability.

12. The method of claim 1, wherein the simulation for each of the one or more specific locations within the region are performed using a Monte Carlo simulation method.

13. The method of claim 1, wherein the optimal location for the EV charging station is energy independent of power from a power grid.

14. A system comprising:a processing system;one or more storage media; andinstructions stored on the one or more storage media that, when executed by the processing system, direct the processing system to at least:receive electric vehicle (EV) user data, climate data, and power grid data for a region;determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data;calculate probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region;determine an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region; andprovide the optimal location for the EV charging station.

15. The system of claim 14, wherein the EV user data comprises traffic data, EV battery data, and user driving habit data, wherein the climate data comprises satellite data and weather data.

16. The system of claim 15, wherein determining EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises creating a sunlight heatmap of the one or more specific locations within the region based on the satellite data.

17. The system of claim 15, wherein the instructions that direct the processing system to determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data comprises determining a high-traffic condition for each of the one or more specific locations within the region based on the traffic data.

18. The system of claim 14, wherein the simulation for each of the one or more specific locations within the region determines a rating for energy independence, environmental impact, scalable charging location capability, and wireless EV charging capability.

19. The system of claim 14, wherein the optimal location for the EV charging station is energy independent of power from a power grid.

20. One or more computer readable storage media having instructions stored thereon that, when executed by a processing system, direct the processing system to at least:receive electric vehicle (EV) user data, climate data, and power grid data for a region;determine EV charging conditions for the region based on the EV user data, the climate data, and the power grid data;calculate probability distributions for a plurality of EV charging parameters for one or more specific locations within the region based on the determined EV charging conditions for the region;determine an optimal location for an EV charging station by performing a simulation for each of the one or more specific locations within the region, each simulation combining the plurality of EV charging parameters for the corresponding one or more specific locations within the region; andprovide the optimal location for the EV charging station.

Images