1. A method for selecting an optimal merchant site for establishing an Electric Vehicle (EV) charging infrastructure, the method comprising: receiving cost data associated with the EV charging infrastructure; estimating a plurality of EV demand data corresponding to a plurality of merchant sites present within a region, wherein each EV demand data is estimated based on customer classification data and merchant dwell time data obtained for each merchant site, and wherein the customer classification data indicates a footfall count of customers comprising at least one of EV customers and non-EV customers at each merchant site, and wherein the merchant dwell time data indicates amount of time spent by the at least one of the EV customers and the nonEV customers at each merchant site; estimating yearly yield data for each merchant site based on the cost data and the EV demand data estimated for each merchant site; and ranking the plurality of merchant sites based on the corresponding yearly yield data estimated for each merchant site such that the optimal merchant site is selected among the plurality of merchant sites for establishing the EV charging infrastructure.

2. The method as claimed in claim 1, wherein for estimating the EV demand data, the method further comprises: receiving geospatial demand data comprising at least one of: power grid data, EV registration data, traffic data, parking data, competitor’s charging facility data; and estimating the EV demand data based on the geospatial demand data, the customer classification data, and the merchant dwell time data.

3. The method as claimed in claim 1, wherein for obtaining the customer classification data, the method comprises: receiving a plurality of customer classification parameters comprising transaction data performed by the customers, merchant name, merchant type, merchant location data, frequent merchant visit data, number of yearly renewable purchase data; training a classification learning model to classify the customers, based on the plurality of customer classification parameters, into the at least one of the EV customers and the nonEV customers; and 24 generating a visit frequency map of each of the EV customers at each merchant site.

4. The method as claimed in claim 3, wherein after receiving the plurality of customer classification parameters comprising the transaction data, the method further comprises calculating maximum distance data indicating a maximum distance being travelled by the customers using the transaction data.

5. The method as claimed in claim 1, wherein for obtaining the merchant dwell time data, the method further comprises: receiving the merchant location data and merchant transaction data, wherein the merchant location data comprises at least one of: building size data, parking space data, merchant class data, and wherein the merchant transaction data comprises at least one of: average transaction volume and average transaction amount; creating one or more merchant clusters of the plurality of the merchant sites present within the region based on at least one of: the merchant location data and the merchant transaction data, wherein each merchant site of the plurality of the merchant sites belong to a merchant type; ranking the one or more clusters of the plurality of merchant sites based on received inputs; training dwell time learning model to learn about dwell time for the one or more clusters of the plurality of merchant sites; and implementing the trained dwell time learning model to generate remaining dwell time maps for remaining merchant sites of the plurality of merchant sites in the region.

6. The method as claimed in claim 1, wherein the cost data comprises fixed cost data for establishing the EV charging infrastructure and operational cost data for operating the EV charging infrastructure.

7. The method as claimed in claim 1, wherein the EV demand data comprises at least one of: the merchant transaction data, merchant business type, toll transaction data, and partner charger.

8. A system for selecting an optimal merchant site for establishing an Electric Vehicle (EV) charging infrastructure, the system comprises: 25 a memory unit; a plurality of processing units, wherein the plurality of processing units in conjunction with the memory unit is configured to: receive cost data associated with the EV charging infrastructure; estimate a plurality of EV demand data corresponding to a plurality of merchant sites present within a region, wherein each EV demand data is estimated based on customer classification data and merchant dwell time data obtained for each merchant site, and wherein the customer classification data indicates a footfall count of customers comprising at least one of EV customers and non-EV customers at each merchant site, and wherein the merchant dwell time data indicates amount of time spent by the at least one of the EV customers and the non-EV customers at each merchant site; estimate yearly yield data for each merchant site based on the cost data and the EV demand data estimated for each merchant site; and rank the plurality of merchant sites based on the corresponding yearly yield data estimated for each merchant site such that the optimal merchant site is selected among the plurality of merchant sites for establishing the EV charging infrastructure.

9. The system as claimed in claim 7, wherein to estimate the EV demand data, the plurality of processing units in conjunction with the memory unit is further configured to: receive geospatial demand data comprising at least one of: power grid data, EV registration data, traffic data, parking data, competitor’s charging facility data; and estimate the EV demand data based on the geospatial demand data, the customer classification data, and the merchant dwell time data.

10. The system as claimed in claim 7, wherein to obtain the customer classification data, the plurality of processing units in conjunction with the memory unit is further configured to: receive a plurality of customer classification parameters comprising transaction data performed by the customers, merchant name, merchant type, merchant location data, frequent merchant visit data, number of yearly renewable purchase data; train a classification learning model to classify the customers, based on the plurality of customer classification parameters, into the at least one of the EV customers and the non-EV customers; and generate a visit frequency map of each of the EV customers at each merchant site. 26

11. The system as claimed in claim 10, wherein after receiving the plurality of customer classification parameters comprising the transaction data, the plurality of processing units in conjunction with the memory unit is further configured to calculate maximum distance data indicating a maximum distance being travelled by the customers using the transaction data.

12. The system as claimed in claim 7, wherein to obtain the merchant dwell time data, the plurality of processing units in conjunction with the memory unit is further configured to: receive the merchant location data and merchant transaction data, wherein the merchant location data comprises at least one of: building size data, parking space data, merchant class data, and wherein the merchant transaction data comprises at least one of: average transaction volume and average transaction amount; create one or more merchant clusters of the plurality of the merchant sites present within the region based on at least one of: the merchant location data and the merchant transaction data, wherein each merchant site of the plurality of the merchant sites belong to a merchant type; rank the one or more clusters of the plurality of merchant sites based on received inputs; train dwell time learning model to learn about dwell time for the one or more clusters of the plurality of merchant sites; and implement the trained dwell time learning model to generate remaining dwell time maps for remaining merchant sites of the plurality of merchant sites in the region.

13. The system as claimed in claim 7, wherein the cost data comprises fixed cost data to establish the EV charging infrastructure and operational cost data for operating the EV charging infrastructure.

14. The system as claimed in claim 7, wherein the EV demand data comprises at least one of: the merchant transaction data, merchant business type, toll transaction data, and partner charger.

TECHNICAL FIELD
[001] The present invention generally relates to the field of Electric Vehicles (EVs) and more
particularly relates to providing a method and system for facilitating optimal site
selection for placing the EV charging infrastructure.
5 BACKGROUND
[002] The following description includes information that may be useful in understanding
the present invention. It is not an admission that any of the information provided herein
is prior art or relevant to the presently claimed invention, or that any publication
specifically or implicitly referenced is prior art.
10
[003] Electric vehicles (EVs) are crucial for combating climate change by reducing
greenhouse gas emissions from transportation. They offer sustainable mobility,
decreasing reliance on fossil fuels and improving air quality in urban areas. EVs also
drive innovation, fostering advancements in battery technology and renewable energy
15 integration for a cleaner, greener future. As a result, they are experiencing a rapid rise
due to advancements in battery technology, government incentives, and growing
environmental concerns. Their popularity is driven by lower operating costs, reduced
emissions, and increased charging infrastructure. Now, naturally, the widespread
adoption of EVs necessitates the development of robust charging infrastructure. Public
20 charging stations, fast-charging networks, and home charging solutions are essential
to alleviate range anxiety and facilitate convenient EV usage. Investment in
infrastructure expansion is crucial for accelerating the transition to sustainable
transportation and ensuring seamless integration of EVs into daily life.
25 [004] To accommodate the ever-increasing rise in EVs, selecting appropriate charging
infrastructure sites is imperative which, in turn, may pose several challenges. Factors
such as accessibility, proximity to power sources, zoning regulations, and demand
patterns must be carefully considered. Balancing coverage in urban and rural areas
while optimizing for convenience and cost-effectiveness requires thorough planning
30 and coordination among stakeholders. Additionally, addressing concerns regarding
land use, environmental impact, and community engagement is crucial for successful
deployment. In the existing scenario, selection of charging infrastructure sites typically
involves a combination of factors such as population density, transportation corridors,
existing infrastructure (such as electrical grids), proximity to major highways or
3
thoroughfares, and areas with high EV adoption rates. Additionally, considerations for
convenient access, parking availability, and potential partnerships with businesses or
municipalities play a role in site selection. Advanced data analytics and modelling
techniques may also be employed to forecast demand and optimize site placement for
5 maximum utilization and user convenience. Finally, stakeholder engagement and
feedback are important for ensuring that charging infrastructure meets the needs of the
community and promotes widespread EV adoption.
[005] However, several challenges are associated with existing site selection techniques for
10 charging infrastructure such as limited data on EV usage patterns, future demand
projections, and demographic trends can hinder accurate site selection. Integrating
charging stations with existing electrical grids and infrastructure may be complex and
costly, especially in areas with outdated systems. Further, ensuring equitable access to
charging infrastructure across urban, suburban, and rural areas while balancing
15 demand fluctuations and congestion may be challenging as well. Then the high upfront
costs for installation, maintenance, and operation of charging stations may deter
investment, particularly in less densely populated areas with lower projected usage.
The utmost challenge is posed when selected site fails to prioritize user convenience,
safety, and accessibility to encourage EV adoption and usage. These factors require
20 careful consideration of factors such as parking availability and proximity to amenities.
Further, anticipating future advancements in EV technology and changes in
transportation habits requires flexibility in site selection to adapt to evolving needs and
preferences.
25 [006] There is therefore a need for a method and system to overcome the challenges
associated with the existing technologies and to facilitate robust and effective optimal
site selection techniques for placing the EV charging infrastructure.
SUMMARY
30 [007] The present disclosure overcomes one or more shortcomings of the prior art and
provides additional advantages. Embodiments and aspects of the disclosure described
in detail herein are considered a part of the claimed disclosure.
4
[008] In one embodiment of the present disclosure, a method for selecting an optimal
merchant site for establishing an Electric Vehicle (EV) charging infrastructure has
been disclosed. The method comprises receiving cost data associated with the EV
charging infrastructure and estimating a plurality of EV demand data corresponding to
5 a plurality of merchant sites present within a region, wherein each EV demand data is
estimated based on customer classification data and merchant dwell time data obtained
for each merchant site, and wherein the customer classification data indicates a footfall
count of customers comprising at least one of EV customers and non-EV customers at
each merchant site, and wherein the merchant dwell time data indicates amount of time
10 spent by the at least one of the EV customers and the non-EV customers at each
merchant site. It further comprises estimating yearly yield data for each merchant site
based on the cost data and the EV demand data estimated for each merchant site.
Furthermore, it also comprises ranking the plurality of merchant sites based on the
corresponding yearly yield data estimated for each merchant site such that the optimal
15 merchant site is selected among the plurality of merchant sites for establishing the EV
charging infrastructure.
[009] In yet another non-limiting embodiment of the present disclosure, for estimating the
EV demand data, the method further comprises receiving geospatial demand data
20 comprising at least one of: power grid data, EV registration data, traffic data, parking
data, competitor’s charging facility data; and estimating the EV demand data based on
the geospatial demand data, the customer classification data, and the merchant dwell
time data.
25 [0010] In yet another non-limiting embodiment of the present disclosure, for obtaining the
customer classification data, the method comprises receiving a plurality of customer
classification parameters comprising transaction data performed by the customers,
merchant name, merchant type, merchant location data, frequent merchant visit data,
number of yearly renewable purchase data. It further comprises training a classification
30 learning model to classify the customers, based on the plurality of customer
classification parameters, into the at least one of the EV customers and the non-EV
customers and thereafter generating a visit frequency map of each of the EV customers
at each merchant site.
5
[0011] In yet another non-limiting embodiment of the present disclosure, after receiving the
plurality of customer classification parameters comprising the transaction data, the
method further comprises calculating maximum distance data indicating a maximum
distance being travelled by the customers using the transaction data.
5
[0012] In yet another non-limiting embodiment of the present disclosure, for obtaining the
merchant dwell time data, the method further comprises receiving the merchant
location data and merchant transaction data, wherein the merchant location data
comprises at least one of: building size data, parking space data, merchant class data,
10 and wherein the merchant transaction data comprises at least one of: average
transaction volume and average transaction amount. Subsequently, it discloses
creating one or more merchant clusters of the plurality of the merchant sites present
within the region based on at least one of: the merchant location data and the merchant
transaction data, wherein each merchant site of the plurality of the merchant sites
15 belong to a merchant type and ranking the one or more clusters of the plurality of
merchant sites based on received inputs. It further comprises training dwell time
learning model to learn about dwell time for the one or more clusters of the plurality
of merchant sites and thereafter implementing the trained dwell time learning model
to generate remaining dwell time maps for remaining merchant sites of the plurality of
20 merchant sites in the region.
[0013] In yet another non-limiting embodiment of the present disclosure, the cost data
comprises fixed cost data for establishing the EV charging infrastructure and
operational cost data for operating the EV charging infrastructure.
25
[0014] In yet another non-limiting embodiment of the present disclosure, the EV demand data
comprises at least one of: the merchant transaction data, merchant business type, toll
transaction data, and partner charger.
30 [0015] In yet another embodiment of the present disclosure, a system for for selecting an
optimal merchant site for establishing an Electric Vehicle (EV) charging infrastructure
has been disclosed. The system comprises a memory unit and a plurality of processing
units, wherein the plurality of processing units in conjunction with the memory unit is
configured to receive cost data associated with the EV charging infrastructure and
35 estimate a plurality of EV demand data corresponding to a plurality of merchant sites
6
present within a region, wherein each EV demand data is estimated based on customer
classification data and merchant dwell time data obtained for each merchant site, and
wherein the customer classification data indicates a footfall count of customers
comprising at least one of EV customers and non-EV customers at each merchant site,
5 and wherein the merchant dwell time data indicates amount of time spent by the at
least one of the EV customers and the non-EV customers at each merchant site. The
system is further configured to estimate yearly yield data for each merchant site based
on the cost data and the EV demand data estimated for each merchant site and rank the
plurality of merchant sites based on the corresponding yearly yield data estimated for
10 each merchant site such that the optimal merchant site is selected among the plurality
of merchant sites for establishing the EV charging infrastructure.
[0016] In yet another embodiment of the present disclosure, to estimate the EV demand data,
the plurality of processing units in conjunction with the memory unit is further
15 configured to receive geospatial demand data comprising at least one of: power grid
data, EV registration data, traffic data, parking data, competitor’s charging facility data
and estimate the EV demand data based on the geospatial demand data, the customer
classification data, and the merchant dwell time data.
20 [0017] In yet another embodiment of the present disclosure, to obtain the customer
classification data, the plurality of processing units in conjunction with the memory
unit is further configured to receive a plurality of customer classification parameters
comprising transaction data performed by the customers, merchant name, merchant
type, merchant location data, frequent merchant visit data, number of yearly renewable
25 purchase data. Further, it has been configured to train a classification learning model
to classify the customers, based on the plurality of customer classification parameters,
into the at least one of the EV customers and the non-EV customers and generate a
visit frequency map of each of the EV customers at each merchant site.
30 [0018] In yet another embodiment of the present disclosure, after receiving the plurality of
customer classification parameters comprising the transaction data, the plurality of
processing units in conjunction with the memory unit is further configured to calculate
maximum distance data indicating a maximum distance being travelled by the
customers using the transaction data.
7
[0019] In yet another embodiment of the present disclosure, to obtain the merchant dwell time
data, the plurality of processing units in conjunction with the memory unit is further
configured to receive the merchant location data and merchant transaction data,
wherein the merchant location data comprises at least one of: building size data,
5 parking space data, merchant class data, and wherein the merchant transaction data
comprises at least one of: average transaction volume and average transaction amount.
The system is further configured to create one or more merchant clusters of the
plurality of the merchant sites present within the region based on at least one of: the
merchant location data and the merchant transaction data, wherein each merchant site
10 of the plurality of the merchant sites belong to a merchant type and rank the one or
more clusters of the plurality of merchant sites based on received inputs. Furthermore,
it has been configured to train dwell time learning model to learn about dwell time for
the one or more clusters of the plurality of merchant sites and implement the trained
dwell time learning model to generate remaining dwell time maps for remaining
15 merchant sites of the plurality of merchant sites in the region.
[0020] In yet another embodiment of the present disclosure, the cost data comprises fixed cost
data to establish the EV charging infrastructure and operational cost data for operating
the EV charging infrastructure.
20
[0021] In yet another embodiment of the present disclosure, the EV demand data comprises
at least one of: the merchant transaction data, merchant business type, toll transaction
data, and partner charger.
25 [0022] The foregoing summary is illustrative only and is not intended to be in any way
limiting. In addition to the illustrative aspects, embodiments, and features described
above, further aspects, embodiments, and features will become apparent by reference
to the drawings and the following detailed description.

WE CLAIM:
1. A method for selecting an optimal merchant site for establishing an Electric Vehicle (EV)
charging infrastructure, the method comprising:
receiving cost data associated with the EV charging infrastructure;
estimating a plurality of EV demand data corresponding to a plurality of merchant sites
present within a region, wherein each EV demand data is estimated based on customer
classification data and merchant dwell time data obtained for each merchant site, and wherein
the customer classification data indicates a footfall count of customers comprising at least one
of EV customers and non-EV customers at each merchant site, and wherein the merchant dwell
time data indicates amount of time spent by the at least one of the EV customers and the nonEV customers at each merchant site;
estimating yearly yield data for each merchant site based on the cost data and the EV
demand data estimated for each merchant site; and
ranking the plurality of merchant sites based on the corresponding yearly yield data
estimated for each merchant site such that the optimal merchant site is selected among the
plurality of merchant sites for establishing the EV charging infrastructure.
2. The method as claimed in claim 1, wherein for estimating the EV demand data, the method
further comprises:
receiving geospatial demand data comprising at least one of: power grid data, EV
registration data, traffic data, parking data, competitor’s charging facility data; and
estimating the EV demand data based on the geospatial demand data, the customer
classification data, and the merchant dwell time data.
3. The method as claimed in claim 1, wherein for obtaining the customer classification data, the
method comprises:
receiving a plurality of customer classification parameters comprising transaction data
performed by the customers, merchant name, merchant type, merchant location data, frequent
merchant visit data, number of yearly renewable purchase data;
training a classification learning model to classify the customers, based on the plurality
of customer classification parameters, into the at least one of the EV customers and the nonEV customers; and
24
generating a visit frequency map of each of the EV customers at each merchant site.
4. The method as claimed in claim 3, wherein after receiving the plurality of customer
classification parameters comprising the transaction data, the method further comprises
calculating maximum distance data indicating a maximum distance being travelled by the
customers using the transaction data.
5. The method as claimed in claim 1, wherein for obtaining the merchant dwell time data, the
method further comprises:
receiving the merchant location data and merchant transaction data, wherein the
merchant location data comprises at least one of: building size data, parking space data,
merchant class data, and wherein the merchant transaction data comprises at least one of:
average transaction volume and average transaction amount;
creating one or more merchant clusters of the plurality of the merchant sites present
within the region based on at least one of: the merchant location data and the merchant
transaction data, wherein each merchant site of the plurality of the merchant sites belong to a
merchant type;
ranking the one or more clusters of the plurality of merchant sites based on received
inputs;
training dwell time learning model to learn about dwell time for the one or more
clusters of the plurality of merchant sites; and
implementing the trained dwell time learning model to generate remaining dwell time
maps for remaining merchant sites of the plurality of merchant sites in the region.
6. The method as claimed in claim 1, wherein the cost data comprises fixed cost data for
establishing the EV charging infrastructure and operational cost data for operating the EV
charging infrastructure.
7. The method as claimed in claim 1, wherein the EV demand data comprises at least one of:
the merchant transaction data, merchant business type, toll transaction data, and partner
charger.
8. A system for selecting an optimal merchant site for establishing an Electric Vehicle (EV)
charging infrastructure, the system comprises:
25
a memory unit;
a plurality of processing units, wherein the plurality of processing units in conjunction
with the memory unit is configured to:
receive cost data associated with the EV charging infrastructure;
estimate a plurality of EV demand data corresponding to a plurality of merchant
sites present within a region, wherein each EV demand data is estimated based on
customer classification data and merchant dwell time data obtained for each merchant
site, and wherein the customer classification data indicates a footfall count of customers
comprising at least one of EV customers and non-EV customers at each merchant site,
and wherein the merchant dwell time data indicates amount of time spent by the at least
one of the EV customers and the non-EV customers at each merchant site;
estimate yearly yield data for each merchant site based on the cost data and the
EV demand data estimated for each merchant site; and
rank the plurality of merchant sites based on the corresponding yearly yield
data estimated for each merchant site such that the optimal merchant site is selected
among the plurality of merchant sites for establishing the EV charging infrastructure.
9. The system as claimed in claim 7, wherein to estimate the EV demand data, the plurality of
processing units in conjunction with the memory unit is further configured to:
receive geospatial demand data comprising at least one of: power grid data, EV
registration data, traffic data, parking data, competitor’s charging facility data; and
estimate the EV demand data based on the geospatial demand data, the customer
classification data, and the merchant dwell time data.
10. The system as claimed in claim 7, wherein to obtain the customer classification data, the
plurality of processing units in conjunction with the memory unit is further configured to:
receive a plurality of customer classification parameters comprising transaction data
performed by the customers, merchant name, merchant type, merchant location data, frequent
merchant visit data, number of yearly renewable purchase data;
train a classification learning model to classify the customers, based on the plurality of
customer classification parameters, into the at least one of the EV customers and the non-EV
customers; and
generate a visit frequency map of each of the EV customers at each merchant site.
26
11. The system as claimed in claim 10, wherein after receiving the plurality of customer
classification parameters comprising the transaction data, the plurality of processing units
in conjunction with the memory unit is further configured to calculate maximum distance
data indicating a maximum distance being travelled by the customers using the transaction
data.
12. The system as claimed in claim 7, wherein to obtain the merchant dwell time data, the
plurality of processing units in conjunction with the memory unit is further configured to:
receive the merchant location data and merchant transaction data, wherein the merchant
location data comprises at least one of: building size data, parking space data, merchant class
data, and wherein the merchant transaction data comprises at least one of: average transaction
volume and average transaction amount;
create one or more merchant clusters of the plurality of the merchant sites present within
the region based on at least one of: the merchant location data and the merchant transaction
data, wherein each merchant site of the plurality of the merchant sites belong to a merchant
type;
rank the one or more clusters of the plurality of merchant sites based on received
inputs;
train dwell time learning model to learn about dwell time for the one or more clusters
of the plurality of merchant sites; and
implement the trained dwell time learning model to generate remaining dwell time
maps for remaining merchant sites of the plurality of merchant sites in the region.
13. The system as claimed in claim 7, wherein the cost data comprises fixed cost data to establish
the EV charging infrastructure and operational cost data for operating the EV charging
infrastructure.
14. The system as claimed in claim 7, wherein the EV demand data comprises at least one of: the
merchant transaction data, merchant business type, toll transaction data, and partner charger.