Method and system for determining optimal position and size of electric vehicle charging station

Abstract

The present disclosure relates to a method and system for determining an optimal position and an optimal size of an electric vehicle charging station (EVCS). The method comprises: receiving, by an input unit [202], at least a name of a geographic area; receiving, by the processing unit [204], geographic data associated with the geographic area; then identifying, by a processing unit [204], at least a list of potential charging station locations and a list of point of interest locations, at least for determining, via a data fusion module, updated geographic data associated with the geographic area; then, based on at least one of the geographic data and the updated geographic data, determining a demand center associated with the geographic area; a candidate location associated with the demand center is then identified, and then an optimal location and size of the EVCS is determined based on the candidate location and the EVCS parameters using an optimization technique.

Description

Technical Field

[0001] This disclosure generally relates to the field of charging station planning systems within a geographic area. More specifically, this disclosure relates to methods and systems for determining the optimal location and optimal size of an EVCS (Electric Vehicle Charging Station) based on one or more EVCS parameters. Background Technology

[0002] The following description of related technologies is intended to provide background information relevant to the field of this disclosure. This section may contain aspects that may be related to various features of this disclosure. However, it should be understood that this section is intended only to enhance the reader's understanding of this disclosure and is not intended as an admission of prior art.

[0003] The global push for a sustainable and greener future has led to significant increases in the adoption of electric vehicles (EVs) as an environmentally friendly alternative to traditional fossil fuel-powered vehicles. EVs offer numerous environmental benefits, such as reduced greenhouse gas emissions and air pollution. However, for EVs to truly become a viable alternative to conventional vehicles, the challenge of providing a sufficient number of electric vehicle charging stations (EVCSs) in strategic locations must be addressed. The placement and size of these charging stations are crucial for promoting widespread EV adoption and ensuring a seamless and positive user experience.

[0004] One of the major obstacles to the rapid adoption of EVs is range anxiety—the fear of running out of power and being stranded. This anxiety can be alleviated by ensuring adequate charging infrastructure, assuring users that convenient charging points can be found wherever they go. A robust charging station network encourages greater EV adoption because people have confidence in the availability of charging facilities for daily commutes and long-distance travel. Furthermore, the transition from fossil fuel vehicles to EVs largely depends on the availability of a reliable charging network to make electric mobility attractive and accessible to the masses.

[0005] To achieve the goal of promoting EVs instead of fossil fuel vehicles, the following issues need to be addressed:

[0006] • Centralized Strategic Planning: A centralized strategic planning approach is crucial to maximizing the effectiveness of charging station placement. This requires meticulous analysis and optimization of locations to ensure comprehensive coverage of high-demand areas.

[0007] • Demand Forecasting and Spatiotemporal Analysis: Advanced data analytics and demand forecasting models help identify areas with high EV usage and charging demand. These insights help determine the optimal distribution of charging stations.

[0008] • Balancing highways and urban areas: To facilitate long-distance travel, charging stations must be strategically placed along highways; however, due to higher population density and more frequent daily commutes in urban areas, denser coverage is required.

[0009] Accessibility and convenience: Charging stations should be located in easily accessible locations, such as shopping malls, office buildings, residential areas and public parking lots, to improve convenience and encourage frequent use.

[0010] • Scalable capacity: The capacity of charging stations should be scalable to accommodate the increasing number of EVs in the future, ensuring that the infrastructure remains efficient and affordable in the long term.

[0011] Integration with the power grid and energy management: Careful consideration should be given to integrating charging stations with existing power grids and energy management systems to optimize power distribution and load balancing.

[0012] In summary, the growth and widespread adoption of electric vehicles are inextricably linked to the availability of a sufficient number of electric vehicle charging stations. Strategic planning, data-driven optimization, and consideration of renewable energy integration are key elements for successfully building a robust charging infrastructure. As policymakers, governments, and private stakeholders invest in building reliable and convenient charging networks, the transition from fossil fuel vehicles to EVs will be facilitated, leading to a cleaner and more sustainable transportation future for everyone.

[0013] Furthermore, various solutions have been developed in the past to determine the optimal location and size of electric vehicle charging stations (EVCSs) within a region. However, these prior methods have significant drawbacks that hinder their effectiveness. A key issue is that existing solutions rely on charging data from existing EVCSs in other regions to estimate charging demand in the target region. This dependence on data from irrelevant sources can lead to inaccurate predictions. Additionally, these prior solutions utilize probabilistic prediction methods to estimate EV charging demand, which are neither precise nor reliable. Another limitation of existing solutions is their reliance on customer data and charging history from existing EVCSs, making them less universal and applicable to a wider range of scenarios. Moreover, previous solutions typically estimate EV charging demand by fitting a Gaussian function to charging history data from existing EVCSs, leading to discrepancies in results, especially in regions utilizing different charging patterns. Furthermore, the optimization formulas used in existing solutions result in low compatibility and efficiency compared to previously known solutions; for example, some previous solutions estimate demand by sensing traffic information through traffic sensors, or some previously known solutions model demand estimation based on vehicle flow in different regions; these solutions introduce inaccuracies and limitations into their estimations. These limitations highlight the need for an innovative and improved approach to address the challenge of determining the optimal location and size of EVCS.

[0014] Therefore, there is an urgent need in the art to determine the optimal location and size of an EVCS based on one or more EVCS parameters so that the EVCS can be placed within a geographical area, which is the problem that this disclosure aims to solve. Summary of the Invention

[0015] Some of the objectives of this disclosure (at least one embodiment disclosed herein satisfies) are listed below.

[0016] One object of this disclosure is to provide a system and method that helps determine at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCSs) for placement within a geographic area.

[0017] Another object of this disclosure is to provide a solution that determines updated geographic data related to a geographic region based on a geographic dataset and at least one of a list of potential charging station locations and a list of points of interest locations, wherein the updated geographic data includes at least updated road network data, an updated list of electric vehicle charging station data, updated population data, and updated infrastructure data.

[0018] Another object of this disclosure is to provide a solution for determining a list of demand centers, including the locations of electric vehicle (EV) charging centers and estimated EV charging center demand values ​​associated with geographic regions, based on at least one of a geographic dataset and an updated geographic dataset.

[0019] Another object of this disclosure is to provide a system and method for identifying a set of candidate locations associated with at least one demand center in a list of demand centers, based on existing infrastructure data associated with a geographic dataset.

[0020] Another object of this disclosure is to provide a solution that determines at least one optimal location and optimal size of one or more EVCSs based on at least one parameter in a candidate location set and an EVCS parameter set, by using one or more optimization techniques, so as to place one or more EVCSs within a geographic area.

[0021] Summarize

[0022] This section is intended to present certain aspects of the disclosed methods and systems in a simplified form, rather than to identify key advantages or features of this disclosure.

[0023] One aspect of this disclosure relates to a system for determining at least one optimal location and optimal size for one or more electric vehicle charging stations (EVCS). The system includes an input unit configured to receive at least the name of a geographic region. Furthermore, the system includes a processing unit configured to receive a set of geographic data associated with the geographic region from a storage unit. Further, the processing unit is configured to identify at least a list of potential charging station locations and a list of points of interest locations based on the geographic data set. The processing unit is also configured to determine an updated set of geographic data associated with the geographic region via a data fusion module, based on the geographic data set and at least one of the potential charging station location list and the point of interest location list. The processing unit is further configured to determine a list of demand centers associated with the geographic region based on at least one of the geographic data set and the updated geographic data set, wherein each demand center in the demand center list includes at least one of an EV charging center location and an estimated EV charging center demand value. Furthermore, the processing unit is configured to identify a set of candidate locations associated with at least one demand center in the demand center list, based on existing infrastructure data associated with the geographic dataset, wherein each candidate location in the set is associated with a set of EVCS parameters. Subsequently, the processing unit is configured to use one or more optimization techniques to determine at least one optimal location and an optimal size for one or more EVCSs, based on the set of candidate locations and at least one parameter in the set of EVCS parameters.

[0024] Another aspect of this disclosure relates to a method for determining at least one optimal location and optimal size for one or more electric vehicle charging stations (EVCSs). The method further includes receiving at least the name of a geographic region via an input unit. Additionally, the method includes receiving a set of geographic data associated with the geographic region from a storage unit via a processing unit. The method further includes identifying at least a list of potential charging station locations and a list of points of interest locations based on the geographic data set via the processing unit. The method further includes determining an updated set of geographic data associated with the geographic region via a data fusion module via the processing unit, based on the geographic data set and at least one of the potential charging station location list and the point of interest location list. Furthermore, the method includes determining a list of demand centers associated with the geographic region via the processing unit based on at least one of the geographic data set and the updated geographic data set, wherein each demand center in the demand center list includes at least one of an EV charging center location and an estimated EV charging center demand value. The method further includes identifying a set of candidate locations associated with at least one demand center in the demand center list via the processing unit based on existing infrastructure data associated with the geographic data set, wherein each candidate location in the candidate location set is associated with a set of EVCS parameters. The method further includes using one or more optimization techniques by a processing unit to determine at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCSs) based on at least one parameter in the candidate location set and the EVCS parameter set. Attached Figure Description

[0025] The accompanying drawings, which are incorporated herein and form part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems, wherein similar reference numerals in the different drawings refer to the same parts. Components in the drawings are not necessarily drawn to scale, but the focus is on clearly illustrating the principles of this disclosure. Some drawings may use block diagrams to indicate components and do not represent the internal circuitry of each component. Those skilled in the art will understand that such disclosures include disclosures of electrical components, electronic components, or circuits commonly used to implement such components.

[0026] Figure 1 An example block diagram is shown, depicting an example network architecture diagram according to an example embodiment of the present disclosure

[100] .

[0027] Figure 2 An exemplary block diagram of a system

[200] for determining at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS) according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 3A flowchart illustrating an exemplary method for determining at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS) according to an exemplary embodiment of the present disclosure

[300] .

[0029] Figure 4 An exemplary flowchart

[400] is shown for determining a list of demand centers associated with a geographic region according to an exemplary embodiment of the present disclosure.

[0030] The above will become clearer from the following more detailed description of this disclosure. Detailed Implementation

[0031] In the following description, various specific details are set forth for ease of explanation in order to provide a full understanding of embodiments of this disclosure. However, it will be apparent that embodiments of this disclosure can be practiced without these specific details. Several features described below can be used independently of each other or in any combination with other features. A single feature may not solve any of the problems described above, or may only solve some of the problems described above. Any feature described herein may not completely solve some of the problems described above. Example embodiments of this disclosure will be described below, as illustrated in the accompanying drawings, wherein the same reference numerals denote the same parts in different drawings.

[0032] The following description provides exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of this disclosure. Rather, the following description of exemplary embodiments will provide useful instructions for those skilled in the art to implement the exemplary embodiments. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the spirit and scope of this disclosure.

[0033] In this document, the terms “electric vehicle charging station,” “EVCS,” “charging station,” and “vehicle charging station” are used interchangeably and all refer to an electric vehicle charging station. It should be noted that these terms are used interchangeably only for ease of reading and understanding and should not be construed as limiting the scope of this disclosure. These terms are intended to convey the same concept and are not intended to be distinguished. The content disclosed herein covers all aspects and variations relating to electric vehicle charging stations, regardless of the specific terminology used.

[0034] It should be noted that, for the purpose of describing this invention, the terms "mobile device," "user equipment," "user apparatus," "communication apparatus," "apparatus," and similar terms are used interchangeably. These terms are not intended to limit the scope of the invention or imply any particular functionality or limitation with respect to the described embodiments. Their use is solely for convenience and clarity of description. This invention is not limited to any particular type of apparatus or device, and it should be understood that other equivalent terms or variations thereof may be used interchangeably without departing from the scope of the invention as defined herein.

[0035] Specific details are set forth in the following description to provide a thorough understanding of the embodiments. However, those skilled in the art will understand that the embodiments can be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form to avoid obscuring the embodiments with unnecessary details. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without repetitive details to avoid obscuring the embodiments.

[0036] Furthermore, it should be noted that the various embodiments can be described as processes, which can be depicted as flowcharts, flow diagrams, data flow diagrams, structural diagrams, or block diagrams. While flowcharts can describe operations as a sequential process, many operations can be performed in parallel or simultaneously. Moreover, the order of operations can be rearranged. The process terminates when all operations are completed, but there may be additional steps not included in the accompanying drawings.

[0037] The terms “exemplary” and / or “illustrator” are used herein to mean as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited to these examples. Furthermore, any aspect or design described herein as “exemplary” and / or “illustrator” does not necessarily imply superiority over other aspects or designs, nor does it exclude equivalent exemplary structures and techniques known to those skilled in the art. Additionally, when terms such as “comprising,” “having,” “including,” etc., are used in the specification or claims, these terms are intended to indicate inclusiveness in a manner similar to the open transitional term “comprising,” without excluding any additional or other elements.

[0038] Furthermore, the user equipment may also include a "processor" or "processing unit," where a processor refers to any logic circuitry used to process instructions. The processor can be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor, multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), any other type of integrated circuit, etc. The processor can perform signal-encoded data processing, input / output processing, and / or any other functions that enable the system to work according to this disclosure. More specifically, the processor is a hardware processor. The proposed invention offers a novel and non-obvious solution for determining the optimal location and size of electric vehicle charging stations (EVCSs) in any target city, overcoming the limitations of existing techniques in the field. Unlike most existing methods, which focus on different optimization problem formulations and city-specific details, the novel solution disclosed herein aims to build a robust, city-agnostic system for EVCS location and size optimization. This solution achieves this goal through three innovative components. First, a unique mechanism extracts city-specific data from multiple sources and transforms it into a uniform format for downstream tasks. Secondly, a novel approach utilizes this city-specific information to project potential EV charging demand in terms of location and intensity. Finally, a mixed-integer linear programming (MILP)-based optimizer takes the city-specific data and projected EV charging demand as input to generate optimal locations and sizes for new EVCSs, thereby minimizing overall costs and complying with various business and regulatory constraints. By significantly reducing the construction and operation costs of EVCS infrastructure, the solution provided in this disclosure offers mobility solution providers an effective means to minimize the expenses associated with new EV charging stations. Furthermore, the solution disclosed herein has the potential to enhance and complement existing EV ecosystem management solutions, namely the interconnected network of various components, technologies, and services supporting the adoption, operation, and maintenance of electric vehicles (EVs).

[0039] In the following, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement the solutions provided by the present disclosure.

[0040] See Figure 1 , Figure 1 An exemplary block diagram is shown, depicting an exemplary network architecture diagram according to an exemplary embodiment of the present disclosure

[100] . As... Figure 1As shown, the exemplary network architecture diagram

[100] includes at least one user equipment (UE)

[102] connected to at least one network server

[104] via at least one network

[106] . In one implementation, the network server

[104] further includes a system

[200] configured to implement the features of the present invention. Furthermore, in one implementation, the system

[200] may reside partially in the network server

[104] or the user equipment

[102] , or may be connected to both the network server

[104] and the user equipment

[102] to implement the features of this disclosure in a manner readily apparent to those skilled in the art.

[0041] In addition, Figure 1 The present invention only shows a single user device (or user unit)

[102] and a single network server

[104] . However, multiple such user devices

[102] and / or network servers

[104] may exist, or any number of such user devices

[102] and / or network servers

[104] may exist, as will be apparent to those skilled in the art or necessary to implement the features of this disclosure. Furthermore, in the implementation of the system

[200] residing in the network server

[104] , based on the features of this disclosure, the system

[200] determines the optimal location and optimal size for placing electric vehicle charging stations (EVCS) in the geographic area by receiving the name of the geographic area from the user device

[102] at the network server

[104] . Then, a set of geographic data for that geographic area is determined. Next, potential charging station locations and points of interest are identified. Subsequently, using a data fusion module, updated geographic data for that geographic area is generated by combining information from the potential charging station locations and points of interest. Subsequently, based on at least one of the geographic datasets and updated geographic data, a list of demand centers for the geographic region is determined. This list includes EV charging center locations and estimated EV charging center demand values. Then, using existing infrastructure data, a set of candidate locations associated with the demand centers is identified, where each candidate location is linked to a set of electric vehicle charging station (EVCS) parameters. Finally, using one or more optimization techniques, based on the candidate location set and at least one parameter from the EVCS parameter set, the optimal locations and optimal sizes of one or more EVCSs are determined for placing the one or more EVCSs in the geographic region.

[0042] See Figure 2An exemplary block diagram of a system

[200] according to an exemplary embodiment of the present invention is shown, the system being used to determine at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS). The system

[200] includes at least one input unit

[202] , at least one processing unit

[204] , and at least one storage unit

[206] . Furthermore, unless otherwise stated below, all components / units of the system

[200] are assumed to be interconnected. Additionally, in Figure 2 Only a few units are shown in the diagram; however, system

[200] may include multiple such units or system

[200] may include any number of the units required to implement the features of this disclosure. Furthermore, in one implementation, system

[200] may exist in, for example, Figure 1 The features of the present invention are implemented in the network server

[104] shown. The system

[200] may be part of the network server

[104] , or may be independent of the network server

[104] but communicate with it.

[0043] The system

[200] is configured to determine at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCSs) by means of interconnection between the components / units of the system

[200] , so as to place one or more electric vehicle charging stations (EVCSs) within a geographic area.

[0044] To determine at least one optimal location and optimal size of one or more Electric Vehicle Charging Stations (EVCSs) for placing them within a geographic area, the input unit

[202] of the system

[200] is configured to receive at least the name of the geographic area. In one implementation of this solution, the input unit

[202] may receive the name of the geographic area based on user input provided by the user. In another implementation of this solution, the input unit

[202] receiving the name of the geographic area may further include automatically detecting the name of the geographic area based on one or more predefined actions, such as receiving the latitude and longitude of the geographic area from the user, or receiving a PIN code associated with the geographic area from the user.

[0045] In addition, the processing unit

[204] is connected to at least the input unit

[202] , and the processing unit

[204] is configured to receive a set of geographic data associated with the geographic region from the storage unit

[206] , wherein the set of geographic data includes at least road network data, a list of existing electric vehicle charging stations, population data, and existing infrastructure data.

[0046] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) and a database defined for such data sources to receive road network data. In another exemplary implementation of the solution, the processing unit

[204] may receive road network data in a predefined road network data format (such as a graphic format, etc.).

[0047] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as a public charging map data source and / or via a private charging map data source) to receive an existing electric vehicle charging station data list via a database (such as a public charging map API database). In another exemplary implementation of this disclosure, the processing unit

[204] may receive the existing electric vehicle charging station data list based on a query mechanism, wherein the processing unit

[204] may use the centroid of a geographic region and / or the centroid of a portion of a geographic region within a geographic region to query the geographical locations of existing electric vehicle charging stations located within a specified radius of a geographic region and / or within a portion of a geographic region (e.g., within a 30 km radius of the geographic region). In another exemplary implementation of the solution, the processing unit

[204] may receive the existing electric vehicle charging station data list in a predefined format (such as a standard file format).

[0048] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as public API data sources and / or via private API data sources) and a database defined for such data sources to receive population data. In another exemplary implementation of the solution, the processing unit

[204] may receive population data in a predefined road network data format (such as an integer format).

[0049] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) and a database defined for such data sources to receive existing infrastructure data. In another exemplary implementation of the solution, the processing unit

[204] may receive existing infrastructure data in a predefined road network data format (such as a standard file format). The term "existing infrastructure data" as used in this disclosure may include, but is not limited to, data relating to existing building structures (such as schools, shopping malls, parking lots, vacant lots, and other similar features) within a specified geographic area.

[0050] It should be noted that the terms “public charging map data source,” “private charging map data source,” “public API data source,” “public charging map API database,” and “integer format” used herein are for illustrative purposes only. These examples are provided to enhance understanding and should not be construed as limiting the scope of this disclosure. Furthermore, the solutions disclosed herein are not limited to the exemplary data sources, databases, or predefined formats mentioned. Rather, it covers the use of any other data sources, databases, or predefined formats capable of achieving similar functionality or serving the same purpose. Moreover, those skilled in the art will readily understand that various alternative data sources, databases, and formats exist for implementing this disclosure, and these alternatives are fully included within the scope of this disclosure, even if they may not be explicitly described in this specification. Therefore, any references to a particular data source, database, or format in this disclosure are for illustrative purposes only and should not be construed as limiting the scope of this disclosure. This disclosure is intended to cover all modifications, substitutions, or equivalents falling within the scope of the claims, whether or not such alternatives are explicitly mentioned in this specification.

[0051] In addition, the processing unit

[204] is configured to identify at least a list of potential charging station locations and a list of points of interest locations based on the geographic data set.

[0052] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as public street map data sources and / or private street map data sources) and a database defined for such data sources to identify a list of potential charging station locations. In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of potential charging station locations based on existing infrastructure data it receives. Furthermore, in order to identify a list of potential charging station locations based on existing infrastructure data, at least one piece of infrastructure data may be used as an initial potential charging station location based on one or more potential charging location parameters. For example, based on one or more potential charging location parameters, infrastructure data such as data indicating details of public parking lots may be used as an initial potential charging station location. For example, public parking lots are good candidate locations for potential EV charging stations because they are places where electric vehicles typically spend a lot of time idle and are hotspots of human activity within a geographic area. In another exemplary implementation of the solution, the processing unit

[204] may receive a list of potential charging station locations in a predefined format (such as a standard file format).

[0053] Furthermore, in another exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) to identify a list of points of interest locations using a database defined for such data sources. In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of points of interest locations based on existing infrastructure data it receives. In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of points of interest locations by using at least one piece of infrastructure data from the existing infrastructure data as initial potential point of interest locations based on one or more potential point of interest parameters. For example, infrastructure data such as data indicating the location of convenience facilities (e.g., shopping malls, offices, clubhouses) may be used as initial potential point of interest locations based on one or more potential point of interest parameters (i.e., pedestrian flow value parameters, vehicle idle parking time parameters, population density parameters, or any other parameters obvious to those skilled in the art). In an exemplary scenario, the shopping mall associated with the geographic area may include more foot traffic values ​​than a predefined threshold. For example, based on at least the potential point of interest parameter (i.e., ABC shopping mall includes 2000 foot traffic values, where the predefined threshold is 1000), ABC shopping mall is used as the initial potential point of interest location. In another exemplary implementation of this solution, the processing unit

[204] may receive the list of point of interest locations in a predefined format (such as a standard file format).

[0054] Furthermore, the processing unit

[204] is configured to determine, via a data fusion module, an updated set of geographic data associated with the geographic region based on a geographic dataset and at least one of a list of potential charging station locations and a list of points of interest locations, wherein the updated geographic dataset includes at least updated road network data, an updated list of electric vehicle charging station data, updated population data, and updated infrastructure data. Those skilled in the art will understand that, as used herein, the term "updated set of geographic data associated with the geographic region" refers to updated geographic data that can be determined by using the data fusion module in combination with at least various information sources, including geographic data and one or more additional data related to the list of potential charging station locations and the list of points of interest locations. Furthermore, as used herein, the term "updated road network data" refers to information about road infrastructure within the geographic region. This data is derived or updated through the processes described in this disclosure and may include detailed information such as road layout, traffic patterns, road types, and other relevant road-related information.

[0055] Furthermore, those skilled in the art will understand that the term "updated electric vehicle charging station data list" as used herein refers to a collection of information about electric vehicle charging stations existing within a geographic area. This data is updated or enhanced as part of a data fusion process and includes detailed information such as the location of charging stations, geographic area, charging protocols, and other relevant attributes. Additionally, the term "updated population data" as used herein refers to the population residing in or frequently visiting the geographic area. This data is updated based on a data fusion process and may include detailed information such as population size, demographic data, population density, and other relevant demographic characteristics. Furthermore, the term "updated infrastructure data" as used herein includes information about various types of infrastructure within a geographic area, such as buildings, schools, shopping malls, parking lots, vacant land, and other related structures. This data is updated or improved through the processes outlined in this specification.

[0056] Furthermore, it should be noted that terms used in this disclosure, such as “updated geographic data,” “updated road network data,” “updated list of electric vehicle charging stations,” “updated population data,” and “updated infrastructure data,” should not be construed or understood as limiting the scope of this disclosure. Additionally, it should be noted that the intent of using these terms is limited to describing and illustrating the technical aspects and embodiments of this disclosure. Their purpose is not to limit the broader scope, application, or potential variations of this disclosure in any way.

[0057] Furthermore, the processing unit

[204] is configured to determine a list of demand centers associated with a geographic region based on at least one of the geographic dataset and the updated geographic dataset, wherein each demand center in the list of demand centers includes at least one of an EV charging center location and an estimated EV charging center demand value.

[0058] In one implementation of this solution, in order to determine a list of demand centers associated with a geographic region, the processing unit

[204] is configured to retrieve at least road network data and population data associated with the geographic region from the storage unit

[206] .

[0059] In addition, the processing unit

[204] is configured to determine the set of electric vehicle (EV) charging center locations based at least on road network data and population data.

[0060] In addition, the processing unit

[204] is configured to retrieve population data associated with each EV charging center location in the EV charging center location set from the storage unit

[206] .

[0061] Furthermore, the processing unit

[204] is configured to determine an estimated EV charging center demand value associated with each EV charging center location, based at least on the set of EV charging center locations and population data associated with each EV charging center location. In one implementation of this solution, the processing unit

[204] determines the estimated EV charging center demand value associated with each EV charging center location based on one or more demand projection techniques, such as centrality-based EV demand projection techniques and / or clustering-based EV demand projection techniques.

[0062] In an exemplary implementation of this solution, to determine the estimated EV charging center demand value associated with a geographic region via a centrality-based EV demand forecasting technique, this solution identifies one or more central nodes in updated road network data of the geographic region via a predefined analysis method (e.g., a graph centrality analysis method). Each of the one or more central nodes refers to a location that can be used to determine a list of demand centers within the geographic region. Furthermore, in the exemplary graph centrality analysis method, updated road network data can be used to find one or more potential areas that may be activity hotspots within the geographic region. Additionally, the graph centrality analysis method can identify nodes that are important and / or central relative to one or more nodes in the road network graph. For example, one or more of the following two exemplary graph centrality measurement methods can be used to implement this solution:

[0063] 1. A method for measuring degree centrality, wherein the term "degree centrality" defines the importance of a node based on its degree. The higher the degree, the more critical the node becomes in the graph.

[0064] 2. A method for measuring betweenness centrality, wherein the term "betweenness centrality" is defined based on the number of times any node appears in the shortest paths between other nodes, thus defining its importance. Furthermore, the method measures the percentage of shortest paths in a road network and determines the position of a particular node within that network.

[0065] Furthermore, in another implementation of this solution, the centrality-based EV demand forecasting technology can also determine electric vehicle (EV) projections, i.e., the projected number of EVs in the future. To determine EV projections via this technology, the centrality-based EV demand forecasting technology can calculate the top K1 nodes from one or more nodes, where the top K1 road network nodes, i.e., the top K1 central nodes, can be based on user input and at least one of the centrality scores associated with each of the one or more nodes. The locations of the top K1 nodes can then be used to determine a list of demand centers. In an exemplary implementation of this solution, one or more central nodes may be very close to each other, and may overrepresent geographical areas in terms of EV charging center locations. To eliminate this overrepresentation, the solution can implement a distance heuristic algorithm to ensure that each demand center in the demand center list is at least a predefined distance apart from each other.

[0066] In an exemplary implementation of this solution, to determine a list of demand centers associated with a geographic region via a cluster-based EV demand forecasting technique, the cluster-based EV demand forecasting technique may use one or more predefined techniques, such as k-means or k-means++, to determine one or more clusters of updated road network data associated with the geographic region based on geodetic distance. In one implementation, the one or more clusters may be used to estimate the location of EV charging centers and EV charging center demand values ​​within the geographic region. In an exemplary implementation, unsupervised machine learning techniques, such as k-means clustering or hierarchical agglomerative clustering, may be used to determine one or more clusters of updated road network data and / or one or more clusters of updated infrastructure data nodes (e.g., labeled "buildings" or "facilities" in an Open Street Map (OSM)). In one implementation, for each demand center in the list of demand centers associated with the geographic region, the one or more clusters may be based on geodetic (latitude, longitude) distance approximations, also known as geospatial clustering.

[0067] Furthermore, in another implementation of this solution, the cluster-based EV demand forecasting technology can also determine the electric vehicle (EV) forecast, i.e., the expected number of EVs in the future. To determine the EV forecast via this technology, the cluster-based EV demand forecasting technology can determine K² clusters from one or more clusters after performing geospatial clustering. In one implementation, K² clusters can be determined from one or more clusters based on user input. In another implementation, the K² clusters can be used to forecast EV charging center demand values ​​via a fusion module, which can be further used to determine the locations of EV charging centers.

[0068] In an exemplary implementation of this solution, a combination of centrality-based EV demand forecasting and clustering-based EV demand forecasting techniques can be used to determine a merged list of demand centers associated with a geographic region. In this implementation, the processing unit

[204] can use a combination of K2 clusters determined from one or more clusters via clustering-based EV demand forecasting techniques and the top K1 central nodes calculated from one or more nodes via centrality-based EV demand forecasting techniques to determine a list of demand centers associated with a geographic region.

[0069] In one implementation, the disclosed solution may assume that the location of EV charging centers is the centroid of one or more clusters of updated road network data and / or the centroid of clusters of updated infrastructure data nodes (e.g., labeled "buildings" or "facilities" in a public / private street map). Furthermore, updated population data associated with a geographic region is assigned to each individual cluster within the one or more clusters based on the number of centroid nodes in each cluster. The cluster-specific population can then be processed via a machine learning (ML) model to determine the EV charging center demand value within each cluster. For example, according to this disclosure:

[0070] For each cluster ,calculate = Clustering The number of nodes in the internal "central" road network.

[0071] For each cluster The population of each cluster is calculated as follows: :

[0072]

[0073] in = The total number of "central" road network nodes within a geographical region.

[0074] • This population It is used as a feature in the ML model to predict the demand value corresponding to cluster c.

[0075] • The location of the demand center of each cluster is assumed to be the centroid of all road network nodes in that cluster.

[0076] In the exemplary ML-based prediction model shown below, the EV charging center demand value for cluster c ( This represents the annual EV charging center demand (kWh / year) within the cluster. Furthermore, the population of each cluster is estimated as a portion of the total population of the geographic area based on one or more population projection techniques, which are readily apparent to those skilled in the art according to this disclosure. The EV charging center demand depends on various factors, such as EV penetration rate, EV availability, and other socioeconomic factors specific to the region under consideration. This solution proposes a data-driven approach via an ML-based prediction model to estimate and refine the EV charging center demand using ground-value data from the field. Further, in an exemplary scenario, to achieve the above, the ML-based prediction model utilizes the following socioeconomic characteristics... Estimate each cluster The requirements in:

[0077] = [clustered population ( ), the number of "center" nodes in the cluster ( (e.g., the number of Points of Interest (POI) nodes in the cluster, the average age of the population in the cluster, the average income of the population in the cluster, the number of registered vehicles in the cluster, etc.)

[0078] Clustered population ( ) and the number of "center" nodes within the cluster ( The first cluster is a manually designed feature used to predict EV charging center demand. Other cluster-specific socioeconomic features, such as average income and the number of registered vehicles, can be extracted through the data retrieval module of the ML-based predictive model or from publicly available government data repositories or open-source resources. The target variable is the annual demand for EV charging centers. This was obtained from the field by aggregating the annual EV charging center demand values ​​of all existing EV charging stations located within this cluster. Target geographic area Feature matrix It is obtained by appending the feature vectors of all clusters in the target geographic region together, as follows:

[0079]

[0080] Therefore, the characteristic matrix there will be Okay. Similarly, geographical regions. Target vector The target variable is obtained by clustering all the target geographic regions. The target vector is obtained by appending these elements together, as shown below. There will also be OK.

[0081]

[0082] The entire training data is derived from various cities within the same geographical region. Summarize separately and To create a matrix that is large enough. (have (row) and its corresponding target vector (There are also (Line), details are as follows:

[0083]

[0084]

[0085] Standard ML-based predictive models, such as linear / nonlinear regression models, decision tree models, and neural network models, can be summarized based on this. right The data is used for training to predict the demand for EV charging centers in each cluster within a geographic region of interest. .

[0086] Furthermore, the processing unit

[204] is configured to determine a list of demand centers based on a set of EV charging center locations and an estimated EV charging center demand value associated with each EV charging center location. In a preferred exemplary implementation of this disclosure, a combination of centrality-based EV demand forecasting techniques and clustering-based EV demand forecasting techniques may be used to determine a list of demand centers associated with a geographic region.

[0087] In addition, the processing unit

[204] is configured to identify a set of candidate locations associated with at least one demand center in the demand center list based on existing infrastructure data associated with the geographic data set, wherein each candidate location in the set of candidate locations is associated with a set of electric vehicle charging station (EVCS) parameters, wherein the EVCS parameter set includes at least EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters.

[0088] It is important to note that the term "EVCS deployment cost parameter" refers to a numerical value or set of values ​​associated with each candidate location in the candidate location set. Furthermore, it represents the estimated or actual cost required to establish an electric vehicle charging station at a specific candidate location. This parameter considers various expenses such as equipment procurement, installation, licensing, labor, grid connection, and any other relevant costs associated with deploying EVCS infrastructure. Similarly, it is important to note that the term "EVCS access parameter" refers to a characteristic or set of characteristics associated with each candidate location in the candidate location set. Furthermore, it indicates the accessibility or availability of the location for potential electric vehicle users. Factors that may be considered in this parameter include proximity to main roads, highways, city centers, public transport hubs, or other relevant access points that could attract electric vehicle owners to use the charging station. Similarly, it is important to note that the term "EVCS infrastructure size parameter" refers to a numerical value or set of values ​​associated with each candidate location in the candidate location set. Furthermore, it represents the physical size or capacity of the electric vehicle charging station that can be accommodated at a specified location. This parameter considers the number of charging points or charging piles that can be installed, the available space for expansion, and other relevant factors related to the size and scalability of the EVCS infrastructure. Similarly, it is important to note that the term "EVCS charging demand type parameter" refers to a classification or categorization associated with each candidate location in the candidate location set. It describes the specific type or level of expected charging demand at that location. This parameter may include names such as slow charging, fast charging, rapid charging, or ultra-fast charging based on the expected charging requirements of electric vehicles at a given location.

[0089] In one implementation of the described solution, each candidate location is associated with a unique combination of these EVCS parameters, including EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters. These parameters play a crucial role in determining the feasibility and suitability of establishing an electric vehicle charging station at a particular location, taking into account existing infrastructure data and geographic information associated with the set of candidate locations and demand centers. It is important to note that the terminology definitions provided in this disclosure are for illustrative and clarifying purposes only. These definitions are intended to aid in a better understanding of this disclosure and its components. However, it should be clearly understood that these definitions are not intended to impose limitations or restrictions on the scope of this disclosure. Those skilled in the art will readily recognize that the terms used herein may have broader interpretations within the context of this disclosure. The definitions provided should not be construed as limiting this disclosure to a particular implementation or configuration. Rather, they serve as illustrative examples to aid understanding. Furthermore, the scope of this disclosure should be determined by the claims appended to this disclosure. Any variation, alteration, or modification of the terminology used herein that is obvious to those skilled in the art is expressly considered to fall within the scope of this disclosure as defined in the claims. Therefore, this disclosure is not limited to the precise meanings assigned to the terms herein. It should be understood that different interpretations or embodiments may be apparent to those skilled in the art, and such variations are contained within the spirit and scope of the claimed disclosure.

[0090] Subsequently, the processing unit

[204] is configured to determine at least one optimal location and the optimal size of one or more EVCSs using one or more optimization techniques based on at least one parameter in the candidate location set and the EVCS parameter set.

[0091] In one implementation, this solution aims to maximize the utilization of one or more EVCSs, minimize the EVCS deployment cost parameter associated with each of the one or more EVCSs, and ensure equitable access for one or more EV users to one or more EVCSs. In one implementation, to achieve the above, this solution can utilize a mixed-integer linear programming (MILP) model, taking into account the spatial distribution of demand associated with one or more EVCSs, points of interest, and existing EV charging station data, to determine the most efficient size and placement of one or more EVCSs. In one implementation, the solution receives a set of candidate locations as input to determine one or more EVCSs. In other words, in one example, this solution considers all nodes marked "parking" in a geographic area as the set of candidate locations, and the problem is formulated as follows:

[0092] ·Target:

[0093] o To minimize:

[0094] ■ EVCS deployment costs associated with each of the one or more EVCSs, operating costs associated with each of the one or more EVCSs, and charger costs associated with each of the one or more EVCSs.

[0095] ■ The “accessibility” cost required to extract EV charging center demand values ​​from the list of demand centers associated with each of one or more EVCSs.

[0096] ·constraint:

[0097] o Demand constraints:

[0098] ■ Each installed EVCS must meet the requirements of existing EV charging centers.

[0099] o Distance constraint:

[0100] ■ One or more EVCS should be installed:

[0101] • At least α kilometers away from any existing EVCS (user input)

[0102] • Within at least β kilometers (user input) of each point of interest location in the list of point of interest locations

[0103] • They are at least γ kilometers apart (user input)

[0104] o Supply constraints:

[0105] ■ The supply to each EVCS must not exceed the known charging capacity.

[0106] ■ The number of “fast” and “slow” chargers selected should not exceed the known limits.

[0107] To achieve its goal, the MILP model may perform one or more of the following steps:

[0108] - Determine the objective function as -

[0109]

[0110] Among them, one or more decision variables are -

[0111] – Potential charging stations (binary; corresponding to the extracted potential charging station locations)

[0112] – No. Each station serves the annual demand of the i-th demand center.

[0113] – No. The number of slow chargers in a potential charging station

[0114] – No. The number of fast chargers in potential charging stations

[0115] One or more of the inputs are -

[0116] = Annual equivalent of EVCS deployment cost + Annual operating cost

[0117] * EVCS deployment costs include electricity and civil engineering costs.

[0118] * Operating costs associated with each of the one or more EVCSs include maintenance fees, land lease fees, and promotional expenses.

[0119] – Cost per kilometer of driving an EV

[0120] – From the i-th demand center to the i-th The distance between charging stations (the location of the demand center used to calculate this distance is obtained through the process described)

[0121] – Annual equivalent cost of a single slow charger

[0122] – Annual equivalent cost of a single fast charger

[0123] - Define one or more constraints -

[0124] One or more of the requirement constraints are:

[0125] • Demand Center The demand of the place It should be fully distributed to the activated ( =1) Charging station:

[0126] •

[0127] • for For all j = 0, they must be zero. To ensure this, the following inequality can be added:

[0128] •

[0129] One or more of the supply constraints are -

[0130] • Each station When activated, a sufficient number of chargers should be included to meet the requirements.

[0131] •

[0132] Station activation hours = 12 hours (assuming)

[0133] Charging time (in hours) for slow chargers [e.g., 8 hours for the "ABC AC-001" charger]

[0134] Charging time (in hours) for fast chargers [e.g., 0.8 hours for an "AAA" charger]

[0135] • Boundary constraints: for =0 The value must be zero. To ensure this, and to ensure that the parameters are within known upper and lower limits, the following can be included:

[0136] •

[0137] •

[0138] •

[0139] •

[0140] —The upper and lower limits for the number of slow chargers

[0141] —The upper and lower limits for the number of fast chargers

[0142] Among them, one or more distance constraints are -

[0143] • Each station j, upon activation, should have sufficient distance from the nearest existing charging station, where the nearest existing charging station is defined as -

[0144] • ( (User input) where e is the nearest existing charging station.

[0145] • Each station j, upon activation, should be sufficiently close to the nearest point of interest, where the nearest point of interest is defined as -

[0146] • ( (User input) For recent points of interest.

[0147] • Any pair of activated charging stations Sufficient distance between them:

[0148] • ( (User input)

[0149] •

[0150] •

[0151] •

[0152] Now, see Figure 3 An exemplary method flowchart

[300] according to an exemplary embodiment of the present invention is shown for determining at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS). In one implementation, the method

[300] is performed by a system

[200] . Furthermore, in one implementation, the system

[200] may reside in a user equipment

[102] to implement the features of the invention. Similarly, as Figure 3 As shown, the method

[300] begins with step

[302] .

[0153] In step

[304] , the method

[300] disclosed herein includes receiving at least the name of a geographic region via the input unit

[202] . In one implementation of this solution, the input unit

[202] may receive the name of the geographic region based on user input provided by the user. In another implementation of this solution, the input unit

[202] receiving the name of the geographic region may further include automatically detecting the name of the geographic region based on one or more predefined actions, such as receiving the latitude and longitude of the geographic region from the user, or receiving a PIN code of the region associated with the geographic region from the user.

[0154] Next, in step

[306] , the method

[300] disclosed herein includes receiving a set of geographic data associated with the geographic region from the storage unit

[206] via the processing unit

[204] , wherein the set of geographic data includes at least road network data, a list of existing electric vehicle charging stations, population data, and existing infrastructure data.

[0155] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) and a database defined for such data sources to receive road network data. In another exemplary implementation of the solution, the processing unit

[204] may receive road network data in a predefined road network data format (such as a graphic format, etc.).

[0156] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may receive an existing electric vehicle charging station data list via a database (such as a public charging map data source and / or via a private charging map data source) using one or more data sources. In another exemplary implementation of this disclosure, the processing unit

[204] may receive the existing electric vehicle charging station data list based on a query mechanism, wherein the processing unit

[204] may query the geographical locations of existing electric vehicle charging stations located within a specified radius of the geographical region and / or within a portion of the geographical region (e.g., within a 30 km radius of the geographical region) using the centroid of the geographical region and / or the centroid of a portion of the geographical region within the geographical region. In another exemplary implementation of the solution, the processing unit

[204] may receive the existing electric vehicle charging station data list in a predefined format (such as a standard file format).

[0157] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as public API data sources and / or via private API data sources) and a database defined for such data sources to receive population data. In another exemplary implementation of the solution, the processing unit

[204] may receive population data in a predefined road network data format (such as an integer format).

[0158] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) and a database defined for such data sources to receive existing infrastructure data. In another exemplary implementation of the solution, the processing unit

[204] may receive existing infrastructure data in a predefined road network data format (such as a standard file format). The term "existing infrastructure data" as used in this disclosure may include, but is not limited to, data relating to existing building structures (such as schools, shopping malls, parking lots, vacant lots, and other similar features) within a specified geographic area.

[0159] It should be noted that the terms “public charging map data source,” “private charging map data source,” “public API data source,” “public charging map API database,” and “integer format” used herein are for illustrative purposes only. These examples are provided to enhance understanding and should not be construed as limiting the scope of this disclosure. Furthermore, the solutions disclosed herein are not limited to the exemplary data sources, databases, or predefined formats mentioned. Rather, it covers the use of any other data sources, databases, or predefined formats capable of achieving similar functionality or serving the same purpose. Moreover, those skilled in the art will readily understand that various alternative data sources, databases, and formats exist for implementing this disclosure, and these alternatives are fully included within the scope of this disclosure, even if they may not be explicitly described in this specification. Therefore, any references to a particular data source, database, or format in this disclosure are for illustrative purposes only and should not be construed as limiting the scope of this disclosure. This disclosure is intended to cover all modifications, substitutions, or equivalents falling within the scope of the claims, whether or not such alternatives are explicitly mentioned in this specification.

[0160] Next, in step

[308] , the method

[300] disclosed herein includes, by processing unit

[204] , identifying at least a list of potential charging station locations and a list of points of interest locations based on the geographic dataset.

[0161] In an exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as public street map data sources and / or private street map data sources) and a database defined for such data sources to identify a list of potential charging station locations. In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of potential charging station locations based on existing infrastructure data received by the processing unit

[204] . Furthermore, in order to identify a list of potential charging station locations based on existing infrastructure data, at least one piece of infrastructure data may be used as an initial potential charging station location based on one or more potential charging location parameters. For example, infrastructure data such as data indicating details of public parking lots may be used as an initial potential charging station location based on one or more potential charging location parameters. For example, public parking lots are good candidate locations for potential EV charging stations because they are places where electric vehicles typically spend a lot of idle time and are hotspots of human activity within a geographic area. In another exemplary implementation of the solution, the processing unit

[204] may receive a list of potential charging station locations in a predefined format (such as a standard file format).

[0162] Furthermore, in another exemplary implementation of the solution disclosed herein, the processing unit

[204] may use one or more data sources (such as via a public street map data source and / or via a private street map data source) to identify a list of points of interest locations using a database defined for such data sources. In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of points of interest locations based on existing infrastructure data received by the processing unit

[204] . In another exemplary implementation of this disclosure, the processing unit

[204] may identify a list of points of interest locations by using at least one piece of infrastructure data from the existing infrastructure data as initial potential point of interest locations based on one or more potential point of interest parameters. For example, infrastructure data such as data indicating the location of convenience facilities (e.g., shopping malls, offices, clubhouses) may be used as initial potential point of interest locations based on one or more potential point of interest parameters (i.e., pedestrian flow value parameters, vehicle idle parking time parameters, population density parameters, or any other parameters obvious to those skilled in the art). In an exemplary scenario, the shopping mall associated with the geographic area may include more foot traffic values ​​than a predefined threshold. For example, based on at least the potential point of interest parameter (i.e., ABC shopping mall includes 2000 foot traffic values, where the predefined threshold is 1000), ABC shopping mall is used as the initial potential point of interest location. In another exemplary implementation of this solution, the processing unit

[204] may receive the list of point of interest locations in a predefined format (such as a standard file format).

[0163] Next, in step

[310] , the method

[300] disclosed herein includes, via a data fusion module and a processing unit

[204] , determining an updated set of geographic data associated with the geographic region based on a geographic dataset and at least one of a list of potential charging station locations and a list of points of interest locations, wherein the updated set of geographic data includes at least updated road network data, an updated list of electric vehicle charging station data, updated population data, and updated infrastructure data. Those skilled in the art will understand that, as used herein, the term “updated set of geographic data associated with the geographic region” means that the method or process for determining the updated geographic data may combine at least various information sources (including geographic data and one or more additional data associated with the list of potential charging station locations and the list of points of interest locations) using the data fusion module. Furthermore, as used herein, the term “updated road network data” refers to information about road infrastructure within the geographic region. This data is derived or updated through the processes described in this disclosure and may include detailed information such as road layout, traffic patterns, road types, and other relevant road-related information.

[0164] Furthermore, those skilled in the art will understand that the term "updated electric vehicle charging station data list" as used herein refers to a collection of information about electric vehicle charging stations existing within a geographic area. This data is updated or enhanced as part of a data fusion process and includes detailed information such as the location of charging stations, geographic area, charging protocols, and other relevant attributes. Additionally, the term "updated population data" as used herein refers to the population residing in or frequently visiting the geographic area. This data is updated based on a data fusion process and may include detailed information such as population size, demographic data, population density, and other relevant demographic characteristics. Furthermore, the term "updated infrastructure data" as used herein includes information about various types of infrastructure within a geographic area, such as buildings, schools, shopping malls, parking lots, vacant land, and other related structures. This data is updated or improved through the processes outlined in this specification.

[0165] Furthermore, it should be noted that terms used in this disclosure, such as “updated geographic data,” “updated road network data,” “updated list of electric vehicle charging stations,” “updated population data,” and “updated infrastructure data,” should not be construed or understood as limiting the scope of this disclosure. Additionally, it should be noted that the intent of using these terms is limited to describing and illustrating the technical aspects and embodiments of this disclosure. Their purpose is not to limit the broader scope, application, or potential variations of this disclosure in any way.

[0166] Next, in step

[312] , the method

[300] disclosed herein includes determining a list of demand centers associated with a geographic region by a processing unit

[204] based on at least one of the geographic dataset and the updated geographic dataset, wherein each demand center in the list of demand centers includes at least one of an EV charging center location and an estimated EV charging center demand value.

[0167] Now for reference Figure 4 The diagram illustrates a method flowchart

[400] according to an exemplary embodiment of the present disclosure for determining a list of demand centers associated with a geographic region. In one implementation of the present disclosure, the method

[400] may be implemented in conjunction with the system

[200] disclosed herein to determine the list of demand centers associated with a geographic region. Furthermore, as... Figure 4 As shown, method

[400] begins with step

[402] .

[0168] In step

[404] , the method

[400] disclosed herein includes retrieving at least road network data associated with the geographic region and population data associated with the geographic region from the storage unit

[206] via the processing unit

[204] .

[0169] Next, in step

[406] , the method

[400] disclosed herein includes determining a set of electric vehicle (EV) charging center locations by a processing unit

[204] based at least on road network data and population data.

[0170] Next, in step

[408] , the method

[400] disclosed herein includes retrieving population data associated with each EV charging center location in the set of EV charging center locations from the storage unit

[206] via the processing unit

[204] .

[0171] Next, in step

[410] , the method

[400] disclosed herein includes determining, by a processing unit

[204] , an estimated EV charging center demand value associated with each EV charging center location, based at least on the set of EV charging center locations and population data associated with each EV charging center location. In one implementation of this solution, the processing unit

[204] determines the estimated EV charging center demand value associated with each EV charging center location based on one or more demand value prediction techniques, such as centrality-based EV demand prediction techniques and / or clustering-based EV demand prediction techniques.

[0172] In an exemplary implementation of this solution, to determine the estimated EV charging center demand value associated with a geographic region via a centrality-based EV demand forecasting technique, this solution identifies one or more central nodes in updated road network data of the geographic region via a predefined analysis method (e.g., a graph centrality analysis method). Each of the one or more central nodes refers to a location that can be used to determine a list of demand centers within the geographic region. Furthermore, in the exemplary graph centrality analysis method, updated road network data can be used to find one or more potential areas that may be activity hotspots within the geographic region. Additionally, the graph centrality analysis method can identify nodes that are important and / or central relative to one or more nodes in the road network graph. For example, one or more of the following two exemplary graph centrality measurement methods can be used to implement this solution:

[0173] 3. A method for measuring degree centrality, wherein the term "degree centrality" defines the importance of a node based on its degree. The higher the degree, the more critical the node becomes in the graph.

[0174] 4. A method for measuring betweenness centrality, wherein the term "betweenness centrality" is defined based on the number of times any node appears in the shortest paths between other nodes, thus defining its importance. Furthermore, the method measures the percentage of shortest paths in a road network and determines the position of a particular node within that network.

[0175] Furthermore, in another implementation of this solution, the centrality-based EV demand forecasting technology can also determine electric vehicle (EV) projections, i.e., the projected number of EVs in the future. To determine EV projections via this technology, the centrality-based EV demand forecasting technology can calculate the top K1 nodes from one or more nodes, where the top K1 road network nodes, i.e., the top K1 central nodes, can be based on user input and at least one of the centrality scores associated with each of the one or more nodes. The locations of the top K1 nodes can then be used to determine a list of demand centers. In an exemplary implementation of this solution, one or more central nodes may be very close to each other, and may overrepresent geographical areas in terms of EV charging center locations. To eliminate this overrepresentation, the solution can implement a distance heuristic algorithm to ensure that each demand center in the demand center list is at least a predefined distance apart from each other.

[0176] In an exemplary implementation of this solution, to determine a list of demand centers associated with a geographic region via a cluster-based EV demand forecasting technique, the cluster-based EV demand forecasting technique may use one or more predefined techniques, such as k-means or k-means++, to determine one or more clusters of updated road network data associated with the geographic region based on geodetic distance. In one implementation, the one or more clusters may be used to estimate the location of EV charging centers and the demand value of EV charging centers in the geographic region. In an exemplary implementation, unsupervised machine learning techniques, such as k-means clustering or hierarchical agglomerative clustering, may be used to determine one or more clusters of updated road network data and / or one or more clusters of updated infrastructure data nodes (e.g., labeled "buildings" or "facilities" in OSM). In one implementation, for each demand center in the list of demand centers associated with the geographic region, the one or more clusters may be based on geodetic (latitude, longitude) distance approximations, also known as geospatial clustering.

[0177] Furthermore, in another implementation of this solution, the cluster-based EV demand forecasting technology can also determine the electric vehicle (EV) forecast, i.e., the expected number of EVs in the future. To determine the EV forecast via this technology, the cluster-based EV demand forecasting technology can determine K² clusters from one or more clusters after performing geospatial clustering. In one implementation, K² clusters can be determined from one or more clusters based on user input. In another implementation, the K² clusters can be used to forecast EV charging center demand values ​​via a fusion module, which can be further used to determine the locations of EV charging centers.

[0178] In an exemplary implementation of this solution, a combination of centrality-based EV demand forecasting and clustering-based EV demand forecasting techniques can be used to determine a merged list of demand centers associated with a geographic region. In this implementation, the processing unit

[204] can use a combination of K2 clusters determined from one or more clusters via clustering-based EV demand forecasting techniques and the top K1 central nodes calculated from one or more nodes via centrality-based EV demand forecasting techniques to determine a list of demand centers associated with a geographic region.

[0179] In one implementation, the disclosed solution may assume that the location of EV charging centers is the centroid of one or more clusters of updated road network data and / or the centroid of clusters of updated infrastructure data nodes (e.g., labeled "buildings" or "facilities" in a public / private street map). Furthermore, updated population data associated with a geographic region is assigned to each individual cluster within the one or more clusters based on the number of centroid nodes in each cluster. The cluster-specific population can then be processed via a machine learning (ML) model to determine the EV charging center demand value within each cluster. For example, according to this disclosure:

[0180] For each cluster ,calculate = Clustering The number of nodes in the internal "central" road network.

[0181] For each cluster The population of each cluster is calculated as follows: :

[0182]

[0183] in = The total number of "central" road network nodes within a geographical region.

[0184] • This population It is used as a feature in the ML model to predict the demand value corresponding to cluster c.

[0185] • The location of the demand center of each cluster is assumed to be the centroid of all road network nodes in that cluster.

[0186] In the exemplary ML-based prediction model shown below, the EV charging center demand value for cluster c ( This represents the annual EV charging center demand (kWh / year) within the cluster. Furthermore, the population of each cluster is estimated as a portion of the total population of the geographic area based on one or more population projection techniques, which are readily apparent to those skilled in the art according to this disclosure. The EV charging center demand depends on various factors, such as EV penetration rate, EV availability, and other socioeconomic factors specific to the region under consideration. This solution proposes a data-driven approach via an ML-based prediction model to estimate and refine the EV charging center demand using ground-value data from the field. Further, in an exemplary scenario, to achieve the above, the ML-based prediction model utilizes the following socioeconomic characteristics... Estimate each cluster The requirements in:

[0187] = [clustered population ( ), the number of "center" nodes in the cluster ( (e.g., the number of Points of Interest (POI) nodes in the cluster, the average age of the population in the cluster, the average income of the population in the cluster, the number of registered vehicles in the cluster, etc.)

[0188] Clustered population ( ) and the number of "center" nodes within the cluster ( The first cluster is a manually designed feature used to predict EV charging center demand. Other cluster-specific socioeconomic features, such as average income and the number of registered vehicles, can be extracted through the data retrieval module of the ML-based predictive model or from publicly available government data repositories or open-source resources. The target variable is the annual demand for EV charging centers. This was obtained from the field by aggregating the annual EV charging center demand values ​​of all existing EV charging stations located within this cluster. Target geographic area Feature matrix It is obtained by appending the feature vectors of all clusters in the target geographic region together, as follows:

[0189]

[0190] Therefore, the characteristic matrix there will be Okay. Similarly, geographical regions. Target vector The target variable is obtained by clustering all the target geographic regions. The target vector is obtained by appending these elements together, as shown below. There will also be OK.

[0191]

[0192] The entire training data is derived from various cities within the same geographical region. Summarize separately and To create a matrix that is large enough. (have (row) and its corresponding target vector (There are also (Line), details are as follows:

[0193]

[0194]

[0195] Standard ML-based predictive models, such as linear / nonlinear regression models, decision tree models, and neural network models, can be summarized based on this. right The data is used for training to predict the demand for EV charging centers in each cluster within a geographic region of interest. .

[0196] Next, in step

[412] , the method

[400] disclosed herein includes determining a list of demand centers by a processing unit

[204] based on a set of EV charging center locations and an estimated EV charging center demand value associated with each EV charging center location. In a preferred exemplary implementation of this disclosure, a combination of centrality-based EV demand forecasting techniques and clustering-based EV demand forecasting techniques may be used to determine the list of demand centers associated with a geographic region.

[0197] Thereafter, method

[400] terminates in step

[414] .

[0198] Refer again Figure 3 Next, in step

[314] , the method

[300] disclosed herein includes, by a processing unit

[204] , identifying a set of candidate locations associated with at least one demand center in a demand center list based on existing infrastructure data associated with a geographic data set, wherein each candidate location in the candidate location set is associated with a set of electric vehicle charging station (EVCS) parameters. Furthermore, in one implementation of this solution, the EVCS parameter set includes at least EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters.

[0199] It is important to note that the term "EVCS deployment cost parameter" refers to a numerical value or set of values ​​associated with each candidate location in the candidate location set. Furthermore, it represents the estimated or actual cost required to establish an electric vehicle charging station at a specific candidate location. This parameter considers various expenses such as equipment procurement, installation, licensing, labor, grid connection, and any other relevant costs associated with deploying EVCS infrastructure. Similarly, it is important to note that the term "EVCS access parameter" refers to a characteristic or set of characteristics associated with each candidate location in the candidate location set. Furthermore, it indicates the accessibility or availability of the location for potential electric vehicle users. Factors that may be considered in this parameter include proximity to main roads, highways, city centers, public transport hubs, or other relevant access points that could attract electric vehicle owners to use the charging station. Similarly, it is important to note that the term "EVCS infrastructure size parameter" refers to a numerical value or set of values ​​associated with each candidate location in the candidate location set. Furthermore, it represents the physical size or capacity of the electric vehicle charging station that can be accommodated at a specified location. This parameter considers the number of charging points or charging piles that can be installed, the available space for expansion, and other relevant factors related to the size and scalability of the EVCS infrastructure. Similarly, it is important to note that the term "EVCS charging demand type parameter" refers to a classification or categorization associated with each candidate location in the candidate location set. It describes the specific type or level of expected charging demand at that location. This parameter may include names such as slow charging, fast charging, rapid charging, or ultra-fast charging based on the expected charging requirements of electric vehicles at a given location.

[0200] In one implementation of the described solution, each candidate location is associated with a unique combination of these EVCS parameters, including EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters. These parameters play a crucial role in determining the feasibility and suitability of establishing an electric vehicle charging station at a particular location, taking into account existing infrastructure data and geographic information associated with the set of candidate locations and demand centers. It is important to note that the terminology definitions provided in this disclosure are for illustrative and clarifying purposes only. These definitions are intended to aid in a better understanding of this disclosure and its components. However, it should be clearly understood that these definitions are not intended to impose limitations or restrictions on the scope of this disclosure. Those skilled in the art will readily recognize that the terms used herein may have broader interpretations within the context of this disclosure. The definitions provided should not be construed as limiting this disclosure to a particular implementation or configuration. Rather, they serve as illustrative examples to aid understanding. Furthermore, the scope of this disclosure should be determined by the claims appended to this disclosure. Any variation, alteration, or modification of the terminology used herein that is obvious to those skilled in the art is expressly considered to fall within the scope of this disclosure as defined in the claims. Therefore, this disclosure is not limited to the precise meanings assigned to the terms herein. It should be understood that different interpretations or embodiments may be apparent to those skilled in the art, and such variations are contained within the spirit and scope of the claimed disclosure.

[0201] Next, in step

[316] , the method

[300] disclosed herein includes using one or more optimization techniques by a processing unit

[204] to determine at least one optimal location of one or more EVCSs and the optimal size of one or more EVCSs based on at least one parameter in a candidate location set and an EVCS parameter set.

[0202] In one implementation of this solution, the aim is to maximize the utilization of one or more EVCSs, minimize the EVCS deployment cost parameter associated with each of the one or more EVCSs, and ensure equitable access for one or more EV users to one or more EVCSs. In one implementation, to achieve the above, this solution can utilize a mixed-integer linear programming (MILP) model, taking into account the spatial distribution of demand associated with one or more EVCSs, points of interest, and existing EV charging station data, to determine the most efficient size and placement of one or more EVCSs. In one implementation, the solution receives a set of candidate locations as input to determine one or more EVCSs. In other words, in one example, this solution considers all nodes marked "parking" in a geographic area as the set of candidate locations, and the problem is formulated as follows:

[0203] ·Target:

[0204] o To minimize:

[0205] ■ EVCS deployment costs associated with each of the one or more EVCSs, operating costs associated with each of the one or more EVCSs, and charger costs associated with each of the one or more EVCSs.

[0206] ■ The “accessibility” cost required to extract EV charging center demand values ​​from the list of demand centers associated with each of one or more EVCSs.

[0207] ·constraint:

[0208] o Demand constraints:

[0209] ■ Each installed EVCS must meet the requirements of existing EV charging centers.

[0210] o Distance constraint:

[0211] ■ One or more EVCS should be installed:

[0212] • At least α kilometers away from any existing EVCS (user input)

[0213] • Within at least β kilometers (user input) of each point of interest location in the list of point of interest locations

[0214] • They are at least γ kilometers apart (user input)

[0215] o Supply constraints:

[0216] ■ The supply to each EVCS must not exceed the known charging capacity.

[0217] ■ The number of “fast” and “slow” chargers selected should not exceed the known limits.

[0218] To achieve its goal, the MILP model may perform one or more of the following steps:

[0219] - Determine the objective function as -

[0220]

[0221] Among them, one or more decision variables are -

[0222] – Potential charging stations (binary; corresponding to the extracted potential charging station locations)

[0223] – No. Each station serves the annual demand of the i-th demand center.

[0224] – No. The number of slow chargers in a potential charging station

[0225] – No. The number of fast chargers in each potential charging station

[0226] One or more of the inputs are -

[0227] = Annual equivalent of EVCS deployment cost + Annual operating cost

[0228] * EVCS deployment costs include electricity and civil engineering costs.

[0229] * Operating costs associated with each of the one or more EVCSs include maintenance fees, land lease fees, and promotional expenses.

[0230] – Cost per kilometer of driving an EV

[0231] – From the i-th demand center to the i-th The distance between charging stations (the location of the demand center used to calculate this distance is obtained through the process described)

[0232] – Annual equivalent cost of a single slow charger

[0233] – Annual equivalent cost of a single fast charger

[0234] - Define one or more constraints -

[0235] One or more of the requirement constraints are:

[0236] • Demand Center The demand of the place It should be fully distributed to the activated ( =1) Charging station:

[0237] •

[0238] • for For all j = 0, they must be zero. To ensure this, the following inequality can be added:

[0239] •

[0240] One or more of the supply constraints are -

[0241] • Each station When activated, a sufficient number of chargers should be included to meet the requirements.

[0242] •

[0243] Station activation hours = 12 hours (assuming)

[0244] Charging time (in hours) for slow chargers [e.g., 8 hours for the "ABC AC-001" charger]

[0245] Charging time (in hours) for fast chargers [e.g., 0.8 hours for an "AAA" charger]

[0246] • Boundary constraints: for =0 The value must be zero. To ensure this, and to ensure that the parameters are within known upper and lower limits, the following can be included:

[0247] •

[0248] •

[0249] •

[0250] •

[0251] —The upper and lower limits for the number of slow chargers

[0252] —The upper and lower limits for the number of fast chargers

[0253] Among them, one or more distance constraints are -

[0254] • Each station j, upon activation, should have sufficient distance from the nearest existing charging station, where the nearest existing charging station is defined as -

[0255] • ( (User input) where e is the nearest existing charging station.

[0256] • Each station j, upon activation, should be sufficiently close to the nearest point of interest, where the nearest point of interest is defined as -

[0257] • ( (User input) For recent points of interest.

[0258] • Any pair of activated charging stations Sufficient distance between them:

[0259] • ( (User input)

[0260] •

[0261] •

[0262] •

[0263] Thereafter, method

[300] terminates in step

[318] .

[0264] It is evident from the above disclosure that the solution provided in this disclosure is technically advanced compared to existing known solutions. This solution offers several technical advantages and benefits in the field of optimizing the location and size of electric vehicle charging stations (EVCSs). First, it introduces a robust cross-city framework, ensuring that the model can be effectively applied across different target cities without significant user intervention. This addresses the generalizability issues often faced by previous solutions. Second, the solution utilizes relevant city-specific information and employs a novel approach to predict EV charging demand. Mapping socioeconomic factors to EV charging demand using machine learning algorithms is a novel and technically advanced method. Furthermore, the solution directly predicts annual EV charging demand in different regions of the target city, providing a more accurate estimate compared to predicting EV sales in each region. Additionally, this solution employs a MILP-based optimization formula to find the optimal size and location of new EVCSs while considering various business constraints. This is achieved through the use of a tailored cross-city data source API. Moreover, the solution incorporates advanced techniques such as the Big M method and Reconstructed Linearization (RLT) cut from integer programming to further optimize the optimization process. These technological advancements have collectively enabled efficient, reliable, and scalable systems for determining optimal EVCS location and size, setting them apart from existing technologies in the field.

[0265] While this document has given considerable emphasis to the disclosed embodiments, it should be understood that many embodiments can be formulated and many modifications can be made to these embodiments without departing from the principles of this disclosure. These and other modifications to the embodiments of this disclosure will be apparent to those skilled in the art, and therefore it should be understood that the foregoing descriptions of implementation are illustrative rather than restrictive.

Claims

1. A method for determining at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS), the method comprising: -At least the name of the geographical region is received through the input unit [202]; - The processing unit [204] receives a set of geographic data associated with the geographic region from the storage unit [206]; -The processing unit [204] identifies at least a list of potential charging station locations and a list of points of interest locations based on the geographic data set; - The processing unit [204] determines an updated set of geographic data associated with the geographic region based on the geographic data set and at least one of the potential charging station location list and the point of interest location list via the data fusion module; - The processing unit [204] determines a list of demand centers associated with the geographic region based on at least one of the geographic data set and the updated geographic data set, wherein each demand center in the list of demand centers includes at least one of the location of an electric vehicle (EV) charging center and an estimated EV charging center demand value. - The processing unit [204] identifies a set of candidate locations associated with at least one demand center in the demand center list based on existing infrastructure data associated with the geographic data set, wherein each candidate location in the set of candidate locations is associated with a set of EVCS parameters; and - The processing unit [204] uses one or more optimization techniques to determine at least one optimal location and the optimal size of the one or more EVCSs based on at least one parameter in the candidate location set and the EVCS parameter set.

2. The method according to claim 1, wherein, The geographic dataset includes at least road network data, a list of existing electric vehicle charging stations, population data, and existing infrastructure data.

3. The method according to claim 1, wherein, The updated geographic dataset includes at least updated road network data, an updated list of electric vehicle charging stations, updated population data, and updated infrastructure data.

4. The method of claim 2, wherein determining the list of demand centers associated with the geographic region further comprises: -The processing unit [204] retrieves at least road network data and population data associated with the geographic region from the storage unit [206]. -The processing unit [204] determines a set of EV charging center locations based at least on the road network data and the population data. -The processing unit [204] retrieves population data associated with each EV charging center location in the EV charging center location set from the storage unit [206]. -The processing unit [204] determines, at least based on the set of EV charging center locations and population data associated with each EV charging center location, an estimated EV charging center demand value associated with each EV charging center location, and - The processing unit [204] determines the demand center list based on the set of EV charging center locations and the estimated EV charging center demand value associated with each EV charging center location.

5. The method according to claim 4, wherein, The estimated EV charging center demand value associated with each EV charging center location is determined by the processing unit [204] based on one or more demand value prediction techniques.

6. The method according to claim 1, wherein, The EVCS parameter set includes at least EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters.

7. A system for determining at least one optimal location and optimal size of one or more electric vehicle charging stations (EVCS), said system comprising: - Input unit [202] is configured to receive at least the name of a geographic region; and - The processing unit [204] is configured as follows: • Receive a set of geographic data associated with the geographic region from the storage unit [206]. Based on the aforementioned geographic dataset, at least a list of potential charging station locations and a list of points of interest locations are identified. • Through the data fusion module, based on the geographic data set and at least one of the potential charging station location list and the point of interest location list, an updated geographic data set associated with the geographic region is determined. • Based on at least one of the geographic dataset and the updated geographic dataset, a list of demand centers associated with the geographic region is determined, wherein each demand center in the list includes at least one of electric vehicle (EV) charging center locations and estimated EV charging center demand values. • Based on existing infrastructure data associated with the geographic dataset, identify a set of candidate locations associated with at least one demand center in the demand center list, wherein each candidate location in the set of candidate locations is associated with a set of EVCS parameters, and Using one or more optimization techniques, based on at least one parameter from the candidate location set and the EVCS parameter set, determine at least one optimal location and the optimal size of the one or more EVCS.

8. The system according to claim 7, wherein, The geographic dataset includes at least road network data, a list of existing electric vehicle charging stations, population data, and existing infrastructure data.

9. The system according to claim 7, wherein, The updated geographic dataset includes at least updated road network data, an updated list of electric vehicle charging stations, updated population data, and updated infrastructure data.

10. The system according to claim 8, wherein, In order to determine the list of demand centers associated with the geographic region, the processing unit [204] is configured to: - Retrieve at least road network data and population data associated with the geographic region from the storage unit [206]. - Determine the set of EV charging center locations based at least on the road network data and the population data. - Retrieve population data associated with each EV charging center location in the EV charging center location set from the storage unit [206]. - Based at least on the set of EV charging center locations and the population data associated with each EV charging center location, determine an estimated EV charging center demand value associated with each EV charging center location, and - Determine the demand center list based on the set of EV charging center locations and the estimated EV charging center demand value associated with each EV charging center location.

11. The system according to claim 10, wherein, The estimated EV charging center demand value associated with each EV charging center location is determined by the processing unit [204] based on one or more demand value prediction techniques.

12. The system according to claim 7, wherein, The EVCS parameter set includes at least EVCS deployment cost parameters, EVCS access parameters, EVCS infrastructure size parameters, and EVCS charging demand type parameters.

Images