Patent Application
20160343011
The present invention relates to an electricity-demand prediction device, an electricity supply system, an electricity-demand prediction method, and a program that predict the amount of electricity demand at a charging facility.
Priority is claimed on Japanese Patent Application No. 2014-038747, filed on Feb. 28, 2014, the contents of which are incorporated herein by reference.
In recent years, an electric car having a battery mounted therein or hybrid cars have become widespread, and accordingly, electricity demand at charging facilities has increased. Accordingly, a distribution planning technique for controlling a total amount of electrical energy to be generated according to a prediction result of electricity demand and an amount of electrical energy to be supplied according to areas and time periods has been used.
In order to predict electricity demand, generally, a technique of performing prediction by constructing a prediction model using a statistical method based on previous electricity demand records, time information, calendar information indicating days of the week, holidays or the like has been used, for example (for example, see Patent Literature 1).
Furthermore, in a case where electricity demand is predicted in a specific area, a technique of statistically analyzing group behavior trends in the specific area and modeling the group behavior trends has been used.
[PTL 1] Japanese Unexamined Patent Application Publication No. 2012-115066
However, for example, in a case where group behavior trends in a specific area are statistically analyzed, in order to construct models for reproducing features of all group behavior trends in the specific area with high accuracy, it is necessary to provide a large amount of record data (instructional data). On the other hand, since the number of probe cars (vehicles having a function of acquiring detailed traveling data) may be limited, it may not be possible to acquire a considerable amount of record data. Thus, it is difficult to reproduce group behavior trends in a specific area with high accuracy.
In order to solve the above-mentioned problems, an object of the invention is to provide an electricity-demand prediction device, an electricity supply system, an electricity-demand prediction method, and a program capable of performing electricity demand prediction with high accuracy based on limited record data.
According to a first aspect of the invention, there is provided an electricity-demand prediction device (100) including: a data reception unit (101) that receives an input of vehicle probe data (D1) in which a traveling state of a specific vehicle (probe cars 201, 202, and so on) is recorded; an individual model generation unit (112) that generates an individual model (M1, M2, and so on) indicating a correlation between a record value of factor information indicating a decision-making factor for charging of the specific vehicle at a specific charging facility (301, 302, and so on) and a record value indicating electricity demand for the specific vehicle at the specific charging facility, with respect to the specific vehicle or a user of the specific vehicle, based on the received vehicle probe data (D1); and a demand prediction computation unit (113) that calculates a predicted value of electricity demand for the specific vehicle at the specific charging facility based on the generated individual model.
According to such an electricity-demand prediction device, individual models are generated according to users of electric cars, and a prediction process in which a decision-making feature in charging for each of the users is reflected is performed. Accordingly, it is possible to perform electricity demand prediction with high accuracy based on decisions of the users.
According to a second aspect of the invention, the individual model generation unit includes at least an operating rate, a presence proportion in a predetermined area, and a charging rate of a battery as the factor information.
According to such an electricity-demand prediction device, it is possible to acquire information indicating whether a user is driving a vehicle, which location the vehicle is present at, and which level a charging rate of a battery has decreased to, as the factor information which serves as the decision-making factor for charging.
Furthermore, according to a third aspect of the invention, the individual model generation unit extracts usage rate record data (D20) indicating usage rates of the specific vehicle at the specific charging facility according to time periods, as the record value of the electricity demand based on the received vehicle probe data.
According to such an electricity-demand prediction device, it is possible to predict a rate at which a specific charging facility will be in a specific time period as a predicted value of electricity demand.
Furthermore, according to a fourth aspect of the invention, the individual model generation unit constructs a lifestyle model (N1, N2, and so on) that includes a set of the plurality of individual models having similar correlations, and the demand prediction computation unit calculates, based on a distribution rate of a population corresponding to the lifestyle model for activists who are active in a specific area, a predicted value of electricity demand at each charging facility that belongs to the specific area.
According to such an electricity-demand prediction device, it is possible to predict usage rates of charging facilities according to the lifestyle models, and to adjust weights depending on distribution rates of population who belongs to the respective lifestyles at a specific area, with respect to the prediction result. Accordingly, it is possible to enhance the accuracy of electricity demand prediction in the entire area.
Furthermore, according to a fifth aspect of the invention, the data reception unit further receives an input of charging facility data which is information acquired from each charging facility, in which information relating to charging performed in the charging facility is recorded, and the individual model generation unit generates the individual model based on the charging facility data.
According to such an electricity-demand prediction device, it is possible to construct an individual model based on a variety of information relating to charging acquired at each charging facility in addition to vehicle probe data acquired from a specific vehicle. Thus, it is possible to generate an individual model in which decision-making in charging for individual users is reflected with high accuracy, to thereby enhance the accuracy of prediction.
Furthermore, according to a sixth aspect of the invention, there is provided an electricity supply system (1) including: a plurality of probe cars (201, 202, and so on) configured to record a traveling state of a host vehicle; and an electricity supply management device (400) that adjusts an electricity supply for each charging facility according to a prediction result of the above-described electricity-demand prediction device.
According to such an electricity supply system, since the electricity supply management device adjusts an electricity supply for each charging facility according to a highly accurate prediction result of the electricity-demand prediction device, it is possible to perform an electricity supply service management with higher efficiency.
Furthermore, according to a seventh aspect of the invention, there is provided an electricity-demand prediction method including the steps of: receiving an input of vehicle probe data in which a traveling state of a specific vehicle is recorded; generating an individual model indicating a correlation between a record value of factor information indicating a decision-making factor for charging of the specific vehicle at a specific charging facility and a record value indicating electricity demand for the specific vehicle at the specific charging facility, with respect to the specific vehicle or a user of the specific vehicle, based on the received vehicle probe data; and calculating a predicted value of electricity demand for the specific vehicle at the specific charging facility based on the generated individual model.
According to such an electricity-demand prediction method, individual models are generated according to users of electric cars, and a prediction process in which a decision-making feature in charging for each of the users is reflected is performed. Accordingly, it is possible to perform electricity demand prediction with high accuracy based on decisions of the users.
Furthermore, according to an eighth aspect of the invention, there is provided a program that causes a computer of an electricity-demand prediction device to function as: individual model generation means for generating, based on vehicle probe data in which a traveling state of a specific vehicle is recorded, an individual model indicating a correlation between a record value of factor information indicating a decision-making factor for charging of the specific vehicle at a specific charging facility and a record value indicating electricity demand for the specific vehicle at the specific charging facility, with respect to the specific vehicle or a user of the specific vehicle; and demand prediction computation means for calculating a predicted value of electricity demand for the specific vehicle at the specific charging facility based on the generated individual model.
According to such a program, the individual model generation means generates individual models according to users of electric cars, and performs a prediction process in which a decision-making feature in charging for each of the users is reflected. Accordingly, it is possible to perform electricity demand prediction with high accuracy based on decisions of the users.
According to the above-described electricity-demand prediction device, the electricity supply system, the electricity-demand prediction method, and the program, it is possible to perform electricity demand prediction with higher accuracy based on limited record data.
Hereinafter, an electricity supply system according to a first embodiment will be described.
The electricity supply system according to the first embodiment generates individual models obtained by modeling behaviors of individual users that use probe cars using vehicle probe data obtained from the probe cars. Further, the electricity supply system performs, using an individual model in which a feature of each individual user who represents activists (group) who are active in a specific area (for example, in a city) is reflected, prediction of electricity demand at each of charging facilities (in this embodiment, a “usage rate” of each charging facility) in the specific area. Here, the “activists” include residents who live in the specific area, and in addition, include entire people who perform various activities in the area for the purpose of commuting to work, commuting to school, pleasure trip, or the like.
(Overall Configuration)
An electricity supply system 1 according to the first embodiment includes an electricity-demand prediction device 100, plural probe cars 201, 202, and so on, plural charging facilities 301, 302, and so on, and an electricity supply management device 400.
The electricity supply system 1 provides electricity supply service for an electric car in a specific area (for example, in a city T1). Specifically, the electricity supply system 1 provides electricity for battery charging to an electric car that travels in the city T1 through the charging facilities 301, 302, and so on provided in respective locations of the city T1.
The electricity-demand prediction device 100 receives inputs of plural pieces of vehicle probe data D1 (which will be described later) from the respective probe cars 201, 202, and so on, and performs prediction of electricity demand (usage rates according to time periods) in each of the charging facilities 301, 302, and so on based on the vehicle probe data D1.
The probe cars 201, 202, and so on are electric cars used by specific users among residents who belong to the city T1. Each of the probe cars 201, 202, and so on is provided with an exclusive on-board device (not shown), and is able to record a traveling state of each of the probe cars 201, 202, and so on at a predetermined time interval. For example, each of the probe cars 201, 202, and so on is able to record operating state information indicating whether each of the probe cars 201, 202, and so on is being operated, vehicle position information (for example, latitude and longitude information obtained using a global positioning system (GPS)) for specifying each position, and state of charge (SOC) information indicating a charging rate [%] (remaining capacity) of a battery mounted therein, at a predetermined time interval (for example, every hour), as traveling states of each probe car.
Contents of the traveling states capable of being acquired by the probe cars 201, 202, and so on are not limited to the above-described information, and traveling distance information, speed and acceleration information acquired through speed and acceleration sensors mounted therein, or the like may be recorded. In addition, a variety of information during stop and during charging of the probe cars 201, 202, and so on may be recorded. Further, the probe cars 201, 202, and so on are not limited to a configuration in which respective traveling states are acquired “at a predetermined time interval”, and may have a configuration in which respective traveling states are recorded when a specific event which is arbitrarily determined occurs. Specifically, for example, the probe cars 201, 202, and so on may record, at every predetermined traveling distance, or in every predetermined vehicle state change (change from a traveling state to a vehicle stop state, ON and OFF switching of a main power source, and ON and OFF switching of a headlight), respective traveling states at time points corresponding thereto.
The charging facilities 301, 302, and so on are installed at respective locations in the city T1. Users of electric cars perform charging of the electric cars in the charging facilities 301, 302, and so on installed at the respective locations. In this embodiment, as shown in
The electricity supply management device 400 makes a distribution plan so that electricity necessary for charging can be supplied from each of the charging facilities 301, 302, and so on, based on a prediction result of electricity demand (usage rates according to time periods with respect to each of the charging facilities 301, 302, and so on) by using the electricity-demand prediction device 100, in reflection of the prediction result.
(Functional Configuration of Electricity-Demand Prediction Device)
As shown in
The data reception unit 101 is a communication module that receives an input of the vehicle probe data D1 from each of the probe cars 201, 202, and so on. Here, the on-vehicle device of each of the probe cars 201, 202, and so on automatically outputs the acquired vehicle probe data D1 to the data reception unit 101 through predetermined communication means. Instead of a configuration in which each on-vehicle device automatically transmits the vehicle probe data D1 to the data reception unit 101, a user (manager) of the electricity supply system 1 may manually perform a process of transmitting the vehicle probe data D1 to the data reception unit 101 from each on-vehicle device.
The data output unit 102 is a communication module that outputs usage rate prediction data D20F obtained through a calculation process (which will be described later) of the CPU 110 to the electricity supply management device 400.
The CPU 110 is a versatile CPU that performs the entire processes of the electricity-demand prediction device 100. The CPU 110 is operated according to an exclusive program read in a storage area to realize functions as a data accumulation unit 111, an individual model generation unit 112, and a demand prediction computation unit 113. Details of the respective functions will be described later.
The probe data storage unit 120 is a storage area in which the acquired vehicle probe data D1 is stored through a process of the CPU 110 (data accumulation unit 111 (which will be described later)).
The individual model storage unit 121 is a storage area in which individual models of the probe cars 201, 202, and so on, generated by the CPU 110 (the individual model generation unit 112 (which will be described later)) are respectively stored.
The above-described probe data storage unit 120 and individual model storage unit 121 may have a configuration in which storage is performed in a single storage device.
As described above, the CPU 110 according to this embodiment includes functions as the data accumulation unit 111, the individual model generation unit 112, and the demand prediction computation unit 113.
The data accumulation unit 111 successively stores the vehicle probe data D1 input through the data reception unit 101 in the probe data storage unit 120. The content of the vehicle probe data D1 stored by the data accumulation unit 111 will be described later.
The individual model generation unit 112 performs a process of generating individual models M1, M2, and so on corresponding to the probe cars 201, 202, and so on (users P1, P2, and so on), based on previous vehicle probe data D1 accumulated in the probe data storage unit 120. Here, the “individual models” are simulation models in which features (particularly, decision-making features in charging) in usage of the probe cars 201, 202, and so on, of the respective users, are reflected. The individual model generation unit 112 stores the generated individual models M1, M2, and so on in the individual model storage unit 121.
Further, as shown in
The demand prediction computation unit 113 calculates predicted values (usage rate prediction data D20F) of usage rates according to respective time periods in each of the charging facilities 301, 302, and so on, based on the individual models M1, M2, and so on stored in the individual model storage unit 121 and newly input vehicle probe data D1.
(Function of Data Accumulation Unit)
As described above, the data accumulation unit 111 successively stores and accumulates the vehicle probe data D1 acquired in the respective probe cars 201, 202, and so on in the probe data storage unit 120. For example, the data accumulation unit 111 stores the vehicle probe data D1 in the form of a configuration as shown in
In the probe data storage unit 120, one or more pieces of vehicle probe data D1 which are previously acquired by each of the probe cars 201, 202, and so on are stored. It is preferable that plural sets of a variety of information over previous several months to several years are stored and accumulated as the vehicle probe data D1, for example.
Further, a configuration of the vehicle probe data D1 stored in the probe data storage unit 120 is not limited to the configuration shown in
(Function of Individual Model Generation Unit)
The factor information extraction unit 112a of the individual model generation unit 112 extracts factor record data D10 which is a record value of factor information with reference to the vehicle probe data D1 (
(Time Period Operating Rate Data)
The factor information extraction unit 112a extracts the time period operating rate data D11 which belongs to the factor record data D10 from the vehicle probe data D1 stored in the probe data storage unit 120. Here, as shown in
In
The factor information extraction unit 112a extracts the time period operating rate data D11 with respect to other users P2, P3, and so on (the probe cars 202, 203, and so on), in a similar way.
(Time Period Activity Area Data)
The factor information extraction unit 112a extracts the time period action area data D12 which belongs to the factor record data D10 from the vehicle probe data D1 stored in the probe data storage unit 120. Here, as shown in
(SOC Data According to Time Periods)
The factor information extraction unit 112a further extracts time period SOC data D13 or the like which belongs to the factor record data D10 from the vehicle probe data D1 stored in the probe data storage unit 120. Here, the time period SOC data D13 is information obtained by recording SOCs [%] of users (probe cars 201, 202, and so on) according to time periods through a predetermined sensor, as shown in
Further, the factor information extraction unit 112a may further extract the factor record data D10 other than the above-described data. For example, the factor information extraction unit 112a may specify which one of the charging facilities 301, 302, and so on charging is performed through, with reference to vehicle positions and SOCs according to time periods in the vehicle probe data D1, and may acquire charger usage location data D14 indicating statistics of the charging facilities 301, 302, and so on used by the users P1, P2, and so on (see
Further, although not shown in
The individual model generation unit 112 according to the first embodiment extracts the factor record data D10 that includes previous record values of plural pieces of factor information, as described above.
(Usage Rate Record Data)
Next, the individual model generation unit 112 extracts a record value (electricity demand record data) of electricity demand at each of the charging facilities 301, 302, and so on, with reference to the previous vehicle probe data D1 (
Here, the usage rate record data D20 is statistic data indicating frequencies (usage rates) at which the users P1, P2, and so on use the charging facilities 301, 302, and so on according to days of the week and time periods, based on the vehicle prove data D1 which is previously accumulated (see
Specifically, the electricity demand information extraction unit 112b extracts information about whether each of the charging facilities 301, 302, and so on is being used on each day of the week and in each time period based on vehicle position information or time period SOC information in the vehicle probe data D1 (
(Construction of Individual Models)
Next, a function of a model construction unit 112c that generates individual models based on the factor record data D10 and the usage rate record data D20 described above will be described with reference to
The model construction unit 112c receives inputs of plural sets of factor record data D10 and usage rate record data D20 extracted from the vehicle probe data D1 of each of the probe cars 201, 202, and so on, accumulated in the probe data storage unit 120, and generates individual models M1, M2, and so on indicating correlations between the factor record data D10 and the usage rate record data D20 according to the users P1, P2, and so on (that is, according to the probe cars 201, 202, and so on).
Specifically, for example, the model construction unit 112c sets respective pieces of the factor record data D10 (the time period operating rate data D11, the time period action area data D12, and so on (
Next, the model construction unit 112c generates the individual model M1 indicating the correlations of the responses y1, y2, and so on with respect to the factors x1, x2, and so on. The individual model M1 corresponds to the user P1 (probe car 201). As shown in
y
1
=a
11
x
1
+b
11
x
2
+c
11
x
3
+d
11
x
4
+ . . . (1)
Here, coefficients a11, b11, and so on relating to the factors x1, x2, and so on in Expression (1) represent factor loads of the factors x1, x2, and so on. That is, a factor having a larger coefficient (factor load) has a stronger correlation with the response y1 (that is, usage rate), while a factor having a smaller coefficient (factor load) has a weaker correlation with the response y1.
For example, in a case where the factor x1 is the time period operating rate data D11 and a value of the coefficient all is large, this means that a usage rate (response y1) at which the user p1 uses the charging facility 301 is in a strong causal relationship with a time period operating rate (factor x1). That is, this shows a feature of the user P1 indicating that “the user P1 approximately reliably performs charging in the charging facility 301 whenever the user P1 operates the probe car”.
Similarly, in a case where the factor x2 is the time period action area data D12 and a value of the coefficient b11 is small, this means that the causal relationship between the usage rate (response y1) at which the user P1 uses the charging facility 301 and a time period activity area (factor x2) is not recognized. That is, this shows a feature of the user P1 indicating that “the user P1 approximately necessarily uses the charging facility 301 in charging no matter which location an activity area to which the user P1 initially belongs is present at”.
In this way, the individual model generation unit 112 according to this embodiment derives a bundle of expressions indicating the correlations between known factors x1, x2, and so on (factor record data D10) and known responses y1, y2, and so on (usage rate record data D20) which are previously acquired, and generates the individual model M1 in which a decision-making feature in charging relating to the user P1 is reflected.
As a method of deriving expressions (for example, the above-described Expression (1)) indicating respective correlations between known factors x1, x2, and so on and known responses y1, y2, and so on, for example, a simulation model construction method based on a support vector machine (SVM) or a neural network (NN), or the like which is a known model construction method may be used. More simply, a general least-squares method may be used. Furthermore, Expression (1) indicating the correlations is only an example, and alternatively, a more complicated expression (secondary function, exponential function, logarithmic function, or the like) indicating correlations may be used.
As shown in
In the following description, a function indicating the correlations between the response y1 relating to the charging facility 301 installed in the area Al and the factors x1, x2, and so on relating to the users P1 (probe car 201) is expressed as Expression (2) (see
y
1
=f
A1P1(x1, x2, x3, x4 . . . ) (2)
(Function of Demand Prediction Computation Unit)
The demand prediction computation unit 113 calculates electricity demand prediction data indicating predicted values of electricity demand at each of the charging facilities 301, 302, and so on with respect to the users P1, P2, and so on (probe cars 201, 202, and so on), based on the respective individual models M1, M2, and so on which are stored in advance in the individual model storage unit 121. Specifically, the predicted values of the electricity demand in this embodiment refers to predicted values of usage rates in predetermined time periods in each of the charging facilities 301, 302, and so on. Further, the demand prediction computation unit 113 calculates usage rate prediction data D20F (electricity demand prediction data) indicating the predicted values of the usage rates.
Specifically, first, the demand prediction computation unit 113 receives an input of the vehicle probe data D1 of the user P1 (probe car 201) which is recently acquired, and acquires the factor record data D10 (factors x1, x2, and so on) based on the recent vehicle probe data D1 (see
Then, the demand prediction computation unit 113 inputs the factor record data D10 (factors x1, x2, and so on) to the individual model M1 corresponding to the user P1, and calculates its outputs (responses y1, y2, and so on). More specifically, the demand prediction computation unit 113 substitutes values of the respective factors x1, x2, and so on in respective functions (Expression (2) or the like) included in the individual model M1 to calculate the responses y1, y2, and so on which are solutions of the respective functions.
Here, the calculated responses y1, y2, and so on are values calculated based on the individual model M1 in which the feature of the user P1 is reflected, and represents future usage rates (individual usage rate prediction data D20f) of the charging facilities 301, 302, and so on, of the user P1.
Similarly, the demand prediction computation unit 113 calculates the individual usage rate prediction data D20f of each of the users P2, P3, and so on based on the individual models M2, M3, and so on which are generated in advance (see
If the individual usage rate prediction data D20f for the entirety of the users P1, P2, and so on is calculated, the demand prediction computation unit 113 totals the entire individual usage rate prediction data D20f for each of the charging facilities 301, 302, and so on, and calculates a predicted value of a usage rate of each of the charging facilities 301, 302, and so on in each time period. For example, in a case where it is predicted that rates at which the respective users P1, P2, and so on use the charging facility 301 in a certain time period are y11, y21, and so on, the demand prediction computation unit 113 may calculate a predicted value y1 of a usage rate at the time period of the charging facility 301 as Y1=y11+y21+Y31+. . . . The demand prediction computation unit 113 similarly calculates predicted values Y2, Y3, and so on of usage rates of the other charging facilities 302, 303, and so on at the same time period (see
The demand prediction computation unit 113 acquires the usage rate prediction data D20F in which change in a usage rate in the near future (for example, within 24 hours from a current time point) for each of the charging facilities 301, 302, and so on is predicted, through the above-described processes (see
The demand prediction computation unit 113 outputs the usage rate prediction data D20F (electricity demand prediction data) for each of the charging facilities 301, 302, and so on acquired in this way to the electricity supply management device 400 through the data output unit 102. The electricity supply management device 400 makes a distribution plan with respect to each of the charging facilities 301, 302, and so on, based on a prediction result (usage rate prediction data D20F) of electricity demand for each of the charging facilities 301, 302, and so on, in reflection of the prediction result. For example, in a time period at which it is predicted that the usage rate of the charging facility 301 is high, the electricity supply management device 400 makes a distribution plan so that electricity supply suitable for its electricity demand is performed in the time period. Thus, the electricity supply system 1 can appropriately generate and supply necessary electricity depending on the electricity demand at each of the charging facilities 301, 302, and so on which is predicted in advance, and thus, it is possible to efficiently perform an electricity supply service management.
In the above-described embodiment, the electricity-demand prediction device 100 applies the prediction result in which the decision-making features (individual models) of the selected users P1, P2, and so on are reflected as they are, as a prediction result for all residents in the city T1. In this case, the users P1, P2, and so on of the probe cars 201, 202, and so on may be randomly selected from all residents in the city T1 which is a prediction target area. With such a configuration, it is possible to approximate features of a group of the users P1, P2, and so on who own the probe cars 201, 202, and so on as features of all residents in the city T1.
(Effects)
Since a charging time period or a charging location varies according to a traveling situation or preference of each individual user, it is difficult to accurately predict electricity demand by a simulation method in the related art. However, according to the electricity supply system 1 according to the above-described first embodiment, the electricity-demand prediction device 100 generates individual models according to users of electric cars, and performs simulation analysis in which a decision-making feature in charging for each of the users is reflected. Accordingly, a lifestyle, a sense of values, or the like of each user is reflected in the simulation analysis, and thus, it is possible to perform electricity demand prediction based on user's decision with high accuracy.
Further, the electricity-demand prediction device 100 generates plural individual models in which a decision-making feature of each user is reflected as described above, and approximates groups of the plural individuals as all resident groups in a city to predict electricity demand. Accordingly, it is possible to construct a simulation model with a small amount of data compared with the amount of record data necessary for directly modeling behavior trends of all resident groups.
In addition, in order to construct a simulation model with high accuracy, it is necessary to select a factor having a strong causal relationship with output (solution) to perform model construction. However, for example, in a case where behavior trends of all resident groups in the city T1 are used as a target of model construction, it is difficult to find which factor has a strong causal relationship with respect to the behavior trends of all resident groups. Accordingly, there is a limit to enhancing the accuracy of a model for reproducing the behavior trends of the group.
On the other hand, the electricity-demand prediction device 100 according to this embodiment models decision-making in charging at an individual level, and then, enlarges the model to be used for behavior trends at a group level. Here, it is possible to easily predict what information (that is, factor information) serves as an individual decision-making factor. For example, information about an operating state (whether or not a vehicle is being operated), a vehicle's position (whether or not a vehicle is close to a charging facility), an SOC (whether or not the SOC is small), or the like may be a strong decision-making factor in charging. Accordingly, in construction of individual models, it is possible to select a factor having a strong causal relationship to construct a simulation model, and thus, it is possible to further enhance the accuracy of prediction.
As described above, according to the electricity supply system 1 according to the first embodiment, it is possible to perform electricity demand prediction with high accuracy based on limited record data.
The configuration of the electricity supply system 1 is not limited to the above-described configuration, and for example, may be modified as follows.
The individual model generation unit 112 according to the first embodiment derives a bundle of functions of Expressions (1), (2), or the like based on the vehicle probe data D1 which is previously accumulated, with respect to correlations between the factor record data D10 (factors x1, x2, and so on) and the usage rate record data D20 (responses y1, y2, and so on), to construct individual models.
As a modification example thereof, for example, the individual model generation unit 112 may generate individual models M1′, M2′, and so on of the users P1, P2, and so on based on decision tree learning. For example, as shown in
For example, in a decision tree model shown in
In this way, the decision-making results (corresponding to the responses y1, y2, and so on) derived according to whether or not the plural conditions (corresponding to the factors x1, x2, and so on) which are the decision-making factors are satisfied are modeled.
With such a configuration, it is possible to easily write decision-making in charging for each of the users P1, P2, and so on, and to clarify what factor each of the users P1, P2, and so on leads to a decision for charging based on. Thus, it is possible to easily perform adjustment of electricity demand at each of the charging facilities 301, 302, and so on in installation of a new charging facility, in provision of service therein, or the like, for example.
In the above-described electricity supply system 1, a configuration in which usage rates according to time periods are predicted as electricity demand at each of the charging facilities 301, 302, and so on is described, but other embodiments are not limited to this configuration. For example, in an electricity supply system according to another embodiment, an amount of supplied electrical energy [kW] according to time periods at the charging facilities 301, 302, and so on may be used as prediction target information. Specifically, the electricity demand information extraction unit 112b of the individual model generation unit 112 may select record data (electricity supply record data) of the “amount of supplied electrical energy” at each of the charging facilities 301, 302, and so on with respect to the responses y1, y2, and so on which are prediction targets, to thereby acquire electricity supply prediction data which is a prediction result of the amount of supplied electrical energy.
Next, an electricity supply system according to a second embodiment will be described.
In the electricity supply system according to the first embodiment, a configuration in which the prediction result in which the respective decision-making features (individual models) of the selected users P1, P2, and so on are reflected are applied as they are as the prediction result for all residents in the city T1 is described.
On the other hand, in the electricity supply system according to the second embodiment, similar individual models among plural individual models are grouped according to lifestyles, and a prediction result for all residents in the city T1 is corrected based on the ratio of the number of residents who match each lifestyle.
In
As shown in
The resident data storage unit 122 stores resident data in which information relating to individuals of the residents of the city T1 (for example, age, gender, residential area, job and place of work, commuting by car or not, and the like) is recorded. Furthermore, the resident data storage unit 122 stores in advance whether or not the residents are the users (users P1, P2, and so on) of the probe cars 201, 202, and so on.
The lifestyle model generation unit 112d of the individual model generation unit 112 according to this embodiment generates plural sets of individual models having similar correlations (functions of Expressions (1), (2), or the like) among the individual models M1, M2, and so on generated by the model construction unit 112c.
Specifically, the lifestyle model generation unit 112d compares factor loads (respective coefficients all, b11, and so on in Expression (1)) of the individual models M1, M2, and so on to calculate a difference degree thereof. The difference degree may be calculated by the sum of errors for each factor load, for example. In a case where the calculated difference degree is smaller than a predetermined threshold value which is given in advance, the lifestyle model generation unit 112d determines that there are similar correlations. In this way, the lifestyle model generation unit 112d generates lifestyle models N1, N2, and so on that include sets of individual models having similar correlations among the individual models M1, M2, and so on (see
Furthermore, the lifestyle model generation unit 112d calculates functions indicating correlations between the factors x1, x2, and so on and the responses y1, y2, and so on with respect to each of the lifestyle models N1, N2, and so on. Specifically, the lifestyle model generation unit 112d calculates an average of each bundle (Expressions (1), (2), or the like, see
A method of calculating the functions of the lifestyle models N1, N2, and so on is not limited to the above-described method (average of individual models), and for example, a method of selecting a central value of functions that forms the individual models M1 and M2 may be used.
Then, the lifestyle model generation unit 112d refers to resident data with respect to the users P1, P4, P5, and so on corresponding to each of the individual models M1, M4, M5, and so on (see
The lifestyle model generation unit 112d performs the same process with respect to the other lifestyle models N2, N3, and so on. The lifestyle model generation unit 112d may also perform association of common data indicating “housewife group” with respect to a set of individual models having a similarity of “a high operating rate during the day on weekdays”, for example.
A demand prediction computation unit 113 according to this embodiment calculates usage rate prediction data of each of the lifestyle models N1, N2, and so on generated by the lifestyle model generation unit 112d. This calculation may be performed by the same process as the process (
The demand prediction result adjustment unit 113a of the demand prediction computation unit 113 according to this embodiment calculates distribution rate data according to lifestyles in the city T1 with reference to resident data stored in the resident data storage unit 122. Here,
In a case where usage rates of the charging facility 301 at a certain time period in the lifestyle models N1, N2, and so on are predicted as y11, y21, and so on, the demand prediction result adjustment unit 113a calculates a predicted value Y1 of the usage rates of the charging facility 301 in the time period according to Expression (3).
Y
1
+α·y
11
+β·y
21
+γ·y
31 + . . . (3)
Here, coefficients α, β, γ, and so on in Expression (3) represent distribution rates according to populations that belong to the lifestyle models N1, N2, N3, and so on in the city T1 (see
With such a configuration, since the demand prediction result adjustment unit 113a performs weighting (multiplication of the coefficients α, β, and γ) according to population distribution rates in the city T1 with respect to individual usage rate prediction data D20f (responses y11, y12, and so on) calculated according to the lifestyle models N1, N2, and so on and sums up the results, it is possible to further enhance the accuracy of electricity demand prediction in the entire city T1.
(Effects)
According to the electricity supply system 1 according to the above-described second embodiment, the electricity-demand prediction device 100 generates the lifestyle models N1, N2, and so on by grouping the generated individual models M1, M2, and so on according to common lifestyles. Furthermore, usage rates of charging facilities are predicted according to the lifestyle models N1, N2, and so on, and weighting depending on distribution rates of populations who belong to the respective lifestyles is performed for the respective prediction results. Accordingly, it is possible to enhance the accuracy of electricity demand prediction compared with a case where behavior trends of the users P1, P2, and so on who own the probe cars 201, 202, and so on are approximated as they are as behavior trends of all groups which are prediction targets.
Hereinbefore, according to the electricity supply system according to the second embodiment, it is possible to perform electricity demand prediction with high accuracy based on limited record data.
The above-described electricity supply system according to the second embodiment may be modified as follows.
A resident data storage unit 122 of an electricity-demand prediction device 100 according to this modification example stores resident data on residents who belong to a city T2, in addition to the city T1. In addition, as shown in
With such a configuration, it is possible to predict electricity demand with respect to the city T2 where data acquisition of the probe cars 201, 202, and so on is not performed, using the lifestyle models N1, N2, and so on constructed with respect to the city T1. Accordingly, it is possible to reduce efforts of prediction compared with a case where data is newly acquired in a different area to construct individual models.
Next, an electricity supply system according to a third embodiment will be described.
In the electricity supply system according to the third embodiment, charging facilities 301, 302, and so on are configured to be able to acquire information relating to charging (charging facility data D2).
(Electricity-Demand Prediction Device)
Each of the charging facilities 301, 302, and so on may record information relating to charging, and may output the recorded charging facility data D2 to the electricity-demand prediction device 100. In the charging facility data D2, information such as an occupancy rate of a charging device in each of the charging facilities 301, 302, and so on, a vehicle ID for specifying a vehicle that uses each facility, the amount of charged electric power, a charging method (fast charging or not, for example), usage fee, the presence or absence of added value (usability of point service, for example) is recorded.
A data accumulation unit 111 according to this embodiment receives both of vehicle probe data D1 and charging facility data D2 through a data reception unit 101, and stores the result in a probe data storage unit 120. Further, an individual model generation unit 112 generates individual models M1, M2, and so on (or lifestyle models N1, N2, and so on) based on both of the vehicle probe data D1 and the charging facility data D2 accumulated in the probe data storage unit 120. The generated individual models M1, M2, and so on are obtained in consideration of time period congestion levels, usage fee, the presence or absence of added value, or the like in each of the charging facilities 301, 302, and so on as decision-making factors in charging. Accordingly, the individual model generation unit 112 can generate individual models in which decision-making in charging for individual users is reflected with high accuracy.
(Effects)
Hereinbefore, according to the electricity supply system according to the third embodiment, the electricity-demand prediction device 100 constructs the individual models M1, M2, and so on based on the charging facility data D2 acquired from the charging facilities 301, 302, and so on, in addition to the vehicle probe data D1 acquired from the probe cars 201, 202, and so on. Thus, it is possible to generate individual models in which decision-making in charging for individual users is reflected with high accuracy, and to further enhance the accuracy of prediction.
A configuration in which the electricity-demand prediction device 100 according to the above-described third embodiment generates the individual models M1, M2, and so on based on both of the vehicle probe data D1 and the charging facility data D2 is described, but the electricity-demand prediction device 100 according to another embodiment may generate individual models only based on the charging facility data D2. For example, the factor information extraction unit 112a may check vehicle IDs of vehicles for which charging is performed, recorded with respect to each of the plural charging facilities 301, 302, and so on, to thereby generate individual models in which decision-making in charging for individual users associated with the vehicle IDs is reflected. Thus, it is possible to arrange a collection operation of the vehicle probe data D1 using the probe cars 201, 202, and so on, to thereby reduce efforts necessary for prediction.
In all of the electricity supply systems according to the above-described embodiments, the electricity supply management device 400 makes a distribution plan so that necessary minimum electricity suitable for a prediction result can be supplied, based on a prediction result of the electricity-demand prediction device 100, in reflection of the prediction result, to achieve an efficient operation. However, an electricity supply system according to another embodiment may be configured to include a request notification device that notifies each user of an electric car which belongs to the city T1 of a mail for refraining from using a predetermined charging facility at a specific time period according to the received prediction result, and for promoting usage of a predetermined charging facility at another specific time period as necessary. For example, in a case where the demand notification device receives a prediction that electricity demand for the charging facility 301 noticeably increases at a time period of 6 p.m. on a specific day, the demand notification device transmits a mail for requesting users having a high usage rate at the charging facility 301 to refrain from using the charging facility 301 in the time period and to use the charging facility 301 at another time period at which electricity demand is predicted to be low. Thus, each user can follow the request, to thereby make it possible to conveniently perform peak cut (peak shift) in electricity demand.
Further, in this case, individual models may be constructed in consideration of how much influence the presence or absence of reception of the above-described usage refrain notification mail has as a decision-making factor in charging for each of the users P1, P2, and so on. Thus, it is possible to effectively select a delivery destination of the usage refrain notification mail.
Furthermore, in the above-described embodiments, it is assumed that each of the probe cars 201, 202, and so on is owned by each of the users P1, P2, and so on. That is, for example, it is assumed that the individual model M1 derived from the vehicle probe data D1 acquired in the probe car 201 reflects the decision-making feature of the user P1 who is an owner of the probe car 201.
However, in another embodiment, a configuration in which the probe cars 201, 202, and so on do not necessarily correspond to individuals (users P1, P2, and so on) one to one may be used. That is, like a family car or a company car, a configuration in which plural users (for example, user P1 and user P2) share and use a specific probe car 201 may be used. In this case, in the individual model M1 calculated based on the vehicle probe data D1 of the probe car 201, decision-making features in charging for the respective users P1, P2, and so on who share and use the probe car 201 are reflected together.
Furthermore, as described above, in a case where plural users share a specific probe car among the probe cars 201, 202, and so on, a configuration in which the specific probe car among the probe cars 201, 202, and so on dividedly acquires the vehicle probe data D1 for each of the users may also be used. For example, the probe cars 201, 202, and so on may receive identification information for identifying which one of the users P1, P2, and so on a current driver is at the start of driving. In this case, since the individual model M1 is calculated based on the vehicle probe data D1 divided for each of the users P1, P2, and so on, decision-making of each of the users P1, P2, and so on is reflected.
A program for realizing the functions of the electricity-demand prediction device 100 in the above-described embodiments may be recorded on a computer-readable recording medium, and a computer system may read the program recorded on the recording medium for execution, to perform the processes. Here, the “computer system” is configured to include hardware such as an OS or peripheral devices. In addition, the “computer system” is configured to include a WWW system including a home page provision environment (or a display environment). Furthermore, the “computer-readable recording medium” refers to a portable medium such as a flexible disc, a magneto-optical disc, a ROM, or a CD-ROM, or a storage medium such as a hard disk built in a computer system. Here, the “computer-readable recording medium” may include a recording medium that retains a program for a predetermined time, such as a volatile memory (RAM) in a computer system which serves as a server or a client in a case where the program is transmitted through a network such as the Internet or a communication line such as a telephone line.
Further, the program may be transmitted to another computer system from the computer system in which the program is stored in a storage device or the like through a transmission medium, or through transmission waves in the transmission medium. Here, the “transmission medium” that transmits the program refers to a medium that has a function of transmitting information, such as a network (communication network) such as the Internet or a communication line such as a telephone line. In addition, the program may realize a part of the above-described functions. Furthermore, the program may be a so-called differential file (differential program) capable of realizing the above-described functions in combination with a program stored in advance in a computer system.
Hereinbefore, several embodiments of the invention have been described, but the embodiments are only examples, and do not limit the scope of the invention. The embodiments may be performed in other various forms, and may include various omissions, replacements, or modifications in a range without departing from the spirit of the invention. These embodiments and modifications are included in the scope or spirit of the invention, and similarly, are included in the inventions disclosed in claims and equivalents thereof.
According to the above-described embodiments, it is possible to perform electricity demand prediction with high accuracy based on limited record data.
1 Electricity supply system
100 Electricity-demand prediction device
101 Data reception unit
102 Data output unit
110 CPU
111 Data accumulation unit
112 Individual model generation unit
112
a Factor information extraction unit
112
b Electricity demand information extraction unit
112
c Model construction unit
112
d Lifestyle model generation unit
113 Demand prediction computation unit
113
a Demand prediction result adjustment unit
120 Probe data storage unit
121 Individual model storage unit
122 Resident data storage unit
201, 202, . . . Probe car
301, 302, . . . Charging facility
400 Electricity supply management device
| Number | Date | Country | Kind |
|---|---|---|---|
| 2014-038747 | Feb 2014 | JP | national |
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/JP2015/054995 | 2/23/2015 | WO | 00 |
