SYSTEM AND METHOD FOR ESTIMATING ELECTRIC VEHICLE CHARGING STATION DEMAND AT SPECIFIC POINTS OF INTEREST

1 . A method for predicting charging station demand at a point of interest (POI), comprising:

determining a percentage of visitors to the POI that are electric vehicle (EV) drivers;

determining a first percentage of the EV drivers that visit the POI that qualify as essential drivers;

determining a second percentage of the EV drivers that visit the POI that qualify as opportunistic drivers;

feeding input data to an inference engine, wherein the input data includes:

the first percentage;

the second percentage;

a first charge rate for opportunistic drivers,

a second charge rate for essential drivers,

a number of visitors to the POI,

based on the input data, the inference engine generating output data that includes at least one of:

a predicted number of EV visits to the POI,

for each type of a plurality of types of chargers, a proposed number of chargers to install at the POI,

a predicted number of charging sessions at the POI,

a predicted mean dwell time for each EV driver at each type of charger of the plurality of types of chargers;

a predicted amount of energy used at the POI; or

a predicted power draw at the POI; and

generating a display, on a display device of a computing device, that is based on the output data;

wherein the method is performed by one or more computing devices.

2 . The method of claim 1 wherein determining a percentage of visitors to the POI that are EV drivers is performed using a Bass model.

3 . The method of claim 1 wherein:

the input data includes number of people visiting the POI at each hour of a day; and

the output data includes the predicted number of EV visits to the POI for each hour of a day.

4 . The method of claim 1 wherein the output data includes a predicted power draw at the POI, and the predicted power draw is at least one of:

a predicted total power draw for each hour of the day for the entire POI;

a predicted total power draw for each hour of the day for each type of charger at the POI; or

a predicted max amount of power draw at a peak of a day for the entire POI.

5 . The method of claim 1 wherein the output data includes a predicted amount of energy used at the POI, and the predicted amount of energy used includes at least one of:

a predicted amount of energy used over each hour of a day for the POI; or

a predicted amount of energy used, at the POI, over each hour of a day for each type of charger of the plurality of types of chargers.

6 . The method of claim 1 wherein the output data includes a predicted number of charging sessions at the POI, and the predicted number of charging sessions includes at least one of:

a predicted total number of sessions per day, at the POI, for each type of charger of the plurality of types of chargers;

a predicted number of sessions, at the POI, per each hour, for each type of charger of the plurality of types of chargers; or

a predicted number of sessions, at the POI, at a peak hour for each type of charger of the plurality of types of chargers.

7 . The method of claim 1 wherein determining the first percentage and the second percentage is performed based on combining distributions of:

average distance a set of EV drivers travel;

access to charging stations;

duration at which the set of EV drivers are able to charge; and

what level of charge constitutes a satisfying charge to the set of EV drivers.

8 . The method of claim 1 further comprising generating a prediction of additional visitors to the POI that result from the addition of charging stations at the POI.

9 . The method of claim 8 wherein the prediction of additional visitors to the POI is determined based, at least in part, on:

amount of EV adoption in an area that includes the POI; and

availability of EV charging stations of various types in immediate vicinity of the POI.

10 . The method of claim 1 further comprising generating a prediction of additional annual spend at the POI that result from the addition of charging stations at the POI.

11 . The method of claim 10 wherein the prediction of additional annual spend is determined based, at least in part, on:

a predicted likelihood that EV drivers are to make a purchase at the POI, and

an average purchase per visit at the POI.

12 . One or more computing devices configured to:

determine a percentage of visitors to the POI that are electric vehicle (EV) drivers;

determine a first percentage of the EV drivers that visit the POI that qualify as essential drivers;

determine a second percentage of the EV drivers that visit the POI that qualify as opportunistic drivers;

feed input data to an inference engine, wherein the input data includes:

the first percentage;

the second percentage;

a first charge rate for opportunistic drivers,

a second charge rate for essential drivers,

a number of visitors to the POI,

based on the input data, cause the inference engine to generate output data that includes at least one of:

a predicted number of EV visits to the POI,

for each type of a plurality of types of chargers, a proposed number of chargers to install at the POI,

a predicted number of charging sessions at the POI,

a predicted mean dwell time for each EV driver at each type of charger of the plurality of types of chargers;

a predicted amount of energy used at the POI; or

a predicted power draw at the POI; and

generate a display, on a display device of a computing device, that is based on the output data.

13 . The one or more computing devices of claim 12 , wherein determining the percentage of visitors to the POI that are EV drivers is configured to be performed using a Bass model.

14 . The one or more computing devices of claim 12 , wherein:

the input data includes number of people visiting the POI at each hour of a day; and

the output data includes the predicted number of EV visits to the POI for each hour of a day.

15 . The one or more computing devices of claim 12 , wherein the output data includes a predicted power draw at the POI, and the predicted power draw is at least one of:

a predicted total power draw for each hour of the day for the entire POI;

a predicted total power draw for each hour of the day for each type of charger at the POI; or

a predicted max amount of power draw at a peak of a day for the entire POI.

16 . The one or more computing devices of claim 12 , wherein the output data includes a predicted amount of energy used at the POI, and the predicted amount of energy used includes at least one of:

a predicted amount of energy used over each hour of a day for the POI; or

a predicted amount of energy used, at the POI, over each hour of a day for each type of charger of the plurality of types of chargers.

17 . A non-transitory computer readable medium comprising instructions executable by a processor to:

determine a percentage of visitors to the POI that are electric vehicle (EV) drivers;

determine a first percentage of the EV drivers that visit the POI that qualify as essential drivers;

determine a second percentage of the EV drivers that visit the POI that qualify as opportunistic drivers;

feed input data to an inference engine, wherein the input data includes:

the first percentage;

the second percentage;

a first charge rate for opportunistic drivers,

a second charge rate for essential drivers,

a number of visitors to the POI,

based on the input data, cause the inference engine to generate output data that includes at least one of:

a predicted number of EV visits to the POI,

for each type of a plurality of types of chargers, a proposed number of chargers to install at the POI,

a predicted number of charging sessions at the POI,

a predicted mean dwell time for each EV driver at each type of charger of the plurality of types of chargers;

a predicted amount of energy used at the POI; or

a predicted power draw at the POI; and

generate a display, on a display device of a computing device, that is based on the output data.

18 . The non-transitory computer readable medium of claim 17 , wherein the instructions, when executed by the processor, cause determining the percentage of visitors to the POI that are EV drivers to be performed using a Bass model.

19 . The non-transitory computer readable medium of claim 17 , wherein:

the input data includes number of people visiting the POI at each hour of a day; and

the output data includes the predicted number of EV visits to the POI for each hour of a day.

20 . The non-transitory computer readable medium of claim 17 , wherein the output data includes a predicted power draw at the POI, and the predicted power draw is at least one of:

a predicted total power draw for each hour of the day for the entire POI;

a predicted total power draw for each hour of the day for each type of charger at the POI; or

a predicted max amount of power draw at a peak of a day for the entire POI.