Behavior prediction of a vehicle participating in vehicle-grid integration
A device predicts the future behavior of a vehicle participating in vehicle-grid integration based on past behavior history of the vehicle, and acquires a user input value representing scheduled future behavior of the vehicle. A first integrated error is obtained by integrating an error between the predicted value and an actual value of the vehicle behavior during a predetermined period, and a second integrated error is obtained by integrating an error between the user input value and the actual value during the same period. The device determines that the user input value is a final predicted value of the future behavior of the vehicle when the first integrated error is smaller than the second integrated error, and determines that the predicted value is the final predicted value when the first integrated error is equal to or larger than the second integrated error.
1. A vehicle grid integration control system comprising:
at least one memory that stores at least one program;
at least one processor coupled to the at least one memory, wherein
the at least one processor is configured to:
individually predict behavior of a vehicle engaging in vehicle-grid integration:
calculate a predicted value obtained by statistically predicting future behavior of the vehicle based on past behavior history of the vehicle;
acquire a scheduled value that represents scheduled future behavior of the vehicle from a user who is using the vehicle;
calculate reliability of the predicted value based on an error between the predicted value and an actual value of behavior of the vehicle during a predetermined period in a past;
calculate reliability of the scheduled value based on an error between the scheduled value and the actual value during the predetermined period;
determine, in a case where the scheduled value has higher reliability than the reliability of the predicted value, that the scheduled value is a final predicted value for the future behavior of the vehicle;
determine, in a case where the scheduled value has reliability equal to or less than the reliability of the predicted value, that the predicted value is the final predicted value;
predict a tradeable power amount based on behavior prediction data for the vehicle; and
prepare a charge/discharge plan for the vehicle for satisfying an electric energy adjustment plan, based on the behavior prediction data for the vehicle;
instruct the vehicle to charge/discharge according to the charge/discharge plan; and
send instructions to a car navigation system or an information terminal owned by the user of the vehicle when the vehicle is instructed to charge/discharge electric energy to satisfy the electric energy adjust plan.
2. The vehicle grid integration control system according to claim 1 , wherein the at least one processor is configured to, by executing the at least one program:
determine, in a case where the scheduled value includes a one-off scheduled value that represents a one-off schedule instead of a repeating schedule, the one-off scheduled value as the final predicted value, superseding the predicted value.
3. The vehicle grid integration control system according to claim 2 , wherein the at least one processor is configured to, by executing the at least one program:
determine, in a case where the scheduled value includes a plurality of one-off scheduled values, a latest one-off scheduled value as the final predicted value.
4. The vehicle grid integration control system according to claim 1 , wherein the at least one processor is configured to, by executing the at least one program:
calculate an integrated value of the error between the predicted value and the actual value as a numerical value associated with the reliability of the predicted value; and
calculate an integrated value of the error between the scheduled value and the actual value as a numerical value associated with the reliability of the scheduled value.
5. A behavior prediction method of predicting behavior of a vehicle engaging in vehicle-grid integration, the behavior prediction method comprising:
calculating, by at least one processor, a predicted value obtained by statistically predicting future behavior of the vehicle based on past behavior history of the vehicle;
acquiring, by the at least one processor, a scheduled value that represents scheduled future behavior of the vehicle from a user who is using the vehicle;
calculating, by the at least one processor, reliability of the predicted value based on an error between the predicted value and an actual value of behavior of the vehicle during a predetermined period in a past;
calculating, by the at least one processor, reliability of the scheduled value based on an error between the scheduled value and the actual value during the predetermined period;
determining, by the at least one processor, in a case where the scheduled value has higher reliability than the reliability of the predicted value, the scheduled value as a final predicted value for the future behavior of the vehicle;
determining, by the at least one processor, in a case where the scheduled value has reliability equal to or less than the reliability of the predicted value, the predicted value as the final predicted value;
predicting, by the at least one processor, a tradeable power amount of electric energy that can be exchanged between the vehicle and a power grid based on the predicted future behavior of the vehicle;
preparing, by the at least one processor, a charge/discharge plan for the vehicle for satisfying an electric energy adjustment plan, based on the predicted future behavior of the vehicle; and
instructing, by the at least one processor, the vehicle to charge/discharge according to the charge/discharge plan, wherein the charge/discharge plan is implemented by sending instructions to a vehicle navigation system of the vehicle or an information terminal owned by the user of the vehicle to cause the vehicle to one or both of charge with electric energy and discharge electric energy to satisfy the electric energy adjustment plan.
6. A non-transitory computer-readable medium storing instructions that, when executed on a computer, cause the computer to predict behavior of a vehicle engaging in vehicle-grid integration, the instructions causing the computer to:
calculate a predicted value obtained by statistically predicting future behavior of the vehicle based on past behavior history of the vehicle;
acquire a scheduled value that represents scheduled future behavior of the vehicle from a user who is using the vehicle;
calculate reliability of the predicted value based on an error between the predicted value and an actual value of behavior of the vehicle during a predetermined period in a past;
calculate reliability of the scheduled value based on an error between the scheduled value and the actual value during the predetermined period;
determine, in a case where the scheduled value has higher reliability than the reliability of the predicted value, the scheduled value as a final predicted value for the future behavior of the vehicle;
determine, in a case where the scheduled value has reliability equal to or less than the reliability of the predicted value, the predicted value as the final predicted value;
predict a tradeable power amount of electric energy that can be exchanged between the vehicle and a power grid based on the predicted future behavior of the vehicle;
prepare a charge/discharge plan for the vehicle for satisfying an electric energy adjustment plan, based on the predicted future behavior of the vehicle; and
instruct the vehicle to charge/discharge according to the charge/discharge plan, wherein the charge/discharge plan is implemented by sending instructions to a vehicle navigation system of the vehicle or an information terminal owned by the user of the vehicle to cause the vehicle to one or both of charge with electric energy and discharge electric energy to satisfy the electric energy adjustment plan.