Information processing device, information processing method, and information processing program

Abstract

Properly evaluate the substitution of the target object with a battery-powered alternative. [Solution] An information processing device that evaluates replacing an object that operates using means other than a storage battery with an alternative that operates using a storage battery, and includes: an objective function generation unit that acquires object operating state information from an object state memory unit that stores object operating state information that represents changes in the object's past operating state; an objective function generation unit that uses the operating state of the alternative as a decision variable and generates an objective function having a parameter term that represents the degree of deviation between the object's operating state and the operating state of the alternative; a constraint condition generation unit that generates constraint conditions related to the remaining capacity of the storage battery that allows the alternative to operate; an optimization unit that identifies the value of the decision variable that optimizes the value of the objective function under the constraint conditions; and an output unit that outputs an evaluation result based on the optimization result.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Toward achieving the goal of zero greenhouse gas emissions by 2050, there has been a growing trend to migrate existing business systems to new systems using drive battery technology, which has seen remarkable advances in recent years. In particular, the transportation industry is accelerating its transition to electric vehicles (EVs) (hereafter referred to as "EVization"). In addition, the integration of drones into logistics networks has also been actively considered in recent years. However, due to the many challenges in both cost and technology involved in the introduction of EVs, it is more realistic to gradually replace existing systems. However, compared to engine-powered systems, drive battery technology faces several obstacles, such as the time required for energy charging and the need to charge or replace batteries only at specific locations. Therefore, when migrating from existing vehicles to vehicles using drive battery technology, it is effective to conduct a simulation of the replacement with a vehicle using drive battery technology in advance, based on the operational performance of the existing vehicle.

[0003] On the other hand, annealing has been attracting attention as a fast solution method for combinatorial optimization problems to improve the productivity of social systems. Annealing is a computational technology targeted at mathematical optimization problems, and it is believed that there is growing demand for its use in real-world problems such as transportation systems, delivery, and route determination.

[0004] An example of a technique related to the above is the technique described in Patent Document 1. Patent Document 1 discloses a charging plan creation device, a charging system, a charging plan creation method, and a charging plan creation program that improve the accuracy of charging plans. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2022-118575 Summary of the Invention [Problem to be solved by the invention]

[0006] However, with the technology disclosed in Patent Document 1, it is possible to set a maximum charging power for vehicles with operation plans, such as buses and trucks, so that the remaining battery power will not run out. However, the plan itself is designed with EVs in mind, and when assessing the feasibility of converting to EVs, it is not possible to evaluate the inconsistencies that arise when replacing (substituting) existing mobile vehicles with EVs.

[0007] The present invention has been made in consideration of the above circumstances, and its purpose is to provide an information processing device, an information processing method, and an information processing program that can appropriately evaluate the replacement of a target object with an alternative that runs on a storage battery. [Means for solving the problem]

[0008] One aspect of the present invention for solving the above problem is an information processing device that evaluates the replacement of an object that operates using means other than a storage battery with an alternative that operates using a storage battery, and is equipped with: a processor and memory, and acquires object operating state information from an object state memory unit that stores object operating state information that represents changes in the object's past operating state, an objective function generation unit that uses the operating state of the alternative as a decision variable and generates an objective function having a parameter term that represents the degree of deviation between the operating state of the object and the operating state of the alternative, a constraint condition generation unit that generates constraint conditions related to the remaining capacity of the storage battery that allows the alternative to operate, an optimization unit that identifies the value of a decision variable that optimizes the value of the objective function under the constraint conditions, and an output unit that outputs an evaluation result based on the result of the optimization. [Effects of the Invention]

[0009] According to the present invention, it is possible to appropriately evaluate the replacement of a target object with an alternative that runs on a storage battery. Configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing an example of a configuration of an information processing device according to a first embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of object operating state information. [Figure 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Figure 4] FIG. 2 is a processing flow diagram illustrating an outline of processing performed by the information processing device according to the first embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of an operating state vector. [Figure 6] FIG. 10 is a diagram illustrating an example of a method for expressing an exclusive OR vector. [Figure 7] FIG. 10 is a diagram illustrating an example of a solution vector. [Figure 8] FIG. 10 is a block diagram showing an example of input and output data of an information processing device according to a second embodiment. [Figure 9] FIG. 10 is a block diagram showing an example of the configuration of an information processing device according to a second embodiment. [Figure 10] FIG. 10 is a diagram illustrating a functional configuration of an evaluation optimization model generation unit according to the second embodiment. [Figure 11] FIG. 10 is a processing flow diagram illustrating an outline of processing performed by an information processing device according to a second embodiment. [Figure 12] FIG. 10 is a process flow diagram illustrating details of a route charging spot calculation process. [Figure 13] FIG. 10 is a diagram illustrating an example of a substitution variable vector. [Figure 14] FIG. 10 is a diagram showing an example of a display form of an SoC. [Figure 15] FIG. 10 is a block diagram showing an example of the configuration of an information processing device according to a third embodiment. [Figure 16]FIG. 11 is a diagram illustrating an example of processing performed by an information processing device according to a third embodiment. [Figure 17] FIG. 11 is a processing flow diagram illustrating an outline of processing performed by an information processing device according to a third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. The following description and drawings are examples for explaining the present invention, and some omissions and simplifications have been made as appropriate for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural. In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings. In the following explanation, various types of information may be described using expressions such as "table," "list," and "queue," but the various types of information may also be expressed using data structures other than these. To indicate that the information is not dependent on the data structure, "XX table," "XX list," etc. may be referred to as "XX information." When describing identification information, expressions such as "identification information," "identifier," "name," "ID," and "number" are used, but these are interchangeable. When there are multiple components with the same or similar functions, they may be described using the same reference numeral with different subscripts. However, when there is no need to distinguish between these multiple components, the subscripts may be omitted. Furthermore, in the following description, processing performed by executing a program may be described, but the program is executed by a processor (e.g., a CPU or a GPU) to perform the specified processing while appropriately using storage resources (e.g., a memory) and / or interface devices (e.g., a communication port), and therefore the subject of the processing may be the processor. Similarly, the subject of the processing performed by executing a program may be a controller, device, system, computer, or node having a processor. The subject of the processing performed by executing a program may be any computing unit, and may include a dedicated circuit (e.g., an FPGA or an ASIC) that performs a specific processing. A program may be installed on a device such as a computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. If the program source is a program distribution server, the program distribution server may include a processor and storage resources for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. Also, in the following description, two or more programs may be realized as one program, and one program may be realized as two or more programs.

[0012] [First embodiment] First, an information processing device, an information processing method, and an information processing program according to a first embodiment will be described.

[0013] <Overall overview of information processing equipment> 1 is a block diagram showing an example of the configuration of an information processing device 1 according to the first embodiment. The information processing device 1 may be a single physical computer, or each component may be implemented on a separate physical computer. Alternatively, instead of a computer system including one or more physical computers, the information processing device 1 may be implemented on another type of system, for example, a system (e.g., a cloud computing system) implemented on a group of physical computing resources (e.g., a cloud platform).

[0014] The information processing device 1 performs an optimization calculation to simulate a substitution evaluation in which an action (which may be not only business but also personal or private) performed by the object to be evaluated during the evaluation period specified by input is performed using a substitute that runs on a storage battery. In other words, the information processing device 1 performs an evaluation in which an object that runs on a means other than a storage battery is replaced with a substitute that runs on a storage battery. The substitute may be anything that runs on a storage battery, such as an EV or a drone.

[0015] The information processing device 1 is connected to an external input device 2, an external output device 3, and an object state storage unit 4.

[0016] Information is input to the information processing device 1 via an external input device 2. The external input device 2 includes, for example, an input interface, and receives input data 20 from a user via the input interface. The external input device 2 outputs the received input data 20 to a time slot variable generation unit 8, which will be described later. The input data 20 includes at least an evaluation period 21 and a time axis interval 22 of the evaluation period.

[0017] The external output device 3 includes, for example, an output interface, and can display the alternative evaluation result 30 calculated by the information processing device 1 via the output interface.

[0018] The object state storage unit 4 is a database that stores object operating state information 40 that indicates the past changes in the operating state of an object.

[0019] (Object operating status information) FIG. 2 is a diagram showing an example of object operating status information 40. The object operating status information 40 is a record of the past operating status of an object, such as the date and time (e.g., the "date and time (start-end)" column in the table of FIG. 2), the state (e.g., the "status" and "stay duration" columns in the table of FIG. 2), and the location (e.g., the "start latitude" and "start longitude" columns in the table of FIG. 2). For example, the object operating status information 40 is data in a table format having data items such as object ID, date and time (start-end), state, stay duration, start latitude, and start longitude. The object ID is set with identification information that identifies each object. The date and time (start-end) is set with the start date and time and end date and time of the state. The state is set with "Run (running state)" or "Visit (stopped state)" as the state of the object. The stay duration is set with the stay duration (duration) when the object was in the "Visit" state. For example, in the "Visit" state, the object is staying at a business-related visit (e.g., a client's office). The start latitude is set to the latitude at which the object is located at the start of the state. The start longitude is set to the longitude at which the object is located at the start of the state.

[0020] The example shown in FIG. 2 shows the past operational status results of three objects, "object 1" to "object 3." The period of object operational status information 40 stored in object status storage unit 4 needs only to cover evaluation period 21 input from external input device 2, and information for a period longer than evaluation period 21 may be stored. For example, if the evaluation period is from March 1, 2023 to March 3, 2023, it is sufficient that at least that period is included, as shown in the "Year, Month, Date and Time (Start - End)" column in FIG. 2.

[0021] The object state storage unit 4 may be included inside the entity that realizes the information processing device 1, may be external, or may be cloud storage via a network.

[0022] The information processing device 1 also includes functional units, namely, an evaluation optimization model generation unit 5, an optimization unit 6, and a solution processing unit 7.

[0023] The evaluation optimization model generation unit 5 generates a mathematical model of an optimization problem (hereinafter, sometimes referred to as an "evaluation optimization model") that simulates alternative evaluations. The evaluation optimization model may be generated by statements of a computer program, and may be written in, for example, a modeling language for solving optimization problems.

[0024] Here, the optimization problem refers to a problem of finding the values ​​of variables that minimize or maximize the cost, which is the evaluation value, under required constraints. In the simulation of substitution evaluation by the information processing device 1 according to this embodiment, the time axis specified in the input is discretized into time slots with the interval width of the time axis of the evaluation period. The information processing device 1 uses the operating state when using a substitute that runs on a storage battery as a decision variable, and performs optimization calculations to minimize the deviation from the operating state of the object to be evaluated under the constraint that the remaining battery power does not run out.

[0025] When this is expressed as a mathematical model, the optimization problem can be expressed, for example, in the form of the following equations (1-1) to (1-4). Hereinafter, equations (1-1) to (1-4) may be collectively referred to as equation (1).

[0026]

number

[0027] Here, xi,j is a binary decision variable that takes the value 1 if object i is in operation in time slot j, and 0 if not. Equation (1-1) is the objective function, where D is the coefficient of the second-order term and C is the coefficient of the first-order term, and the specific numerical values ​​are given by the degree of deviation between the state of the object and the state of the substitute, the introduction cost of the substitute, the operating state of the object during the evaluation period, etc.

[0028] Equation (1-2) shows an example of a constraint condition for maintaining the battery's remaining battery capacity (State of Charge, SoC) at an appropriate level between L and U. Here, bi,j is a continuous-valued decision variable that takes a real number between 0 and 1 and represents the SoC of object i in time slot j. It requires that SoC remain between L and U for all i and j. Here, continuous variables bi,j are used to simplify the equation, but they do not necessarily have to be continuous as long as they can express SoC. Also, if the substitute moves within a fixed distance or length, it is possible to express it only using xi,j by multiplying it by a coefficient and not using bi,j.

[0029] Equation (1-3) is a constraint that indicates that the variable bi,j can be determined from the set of variables xi,j using the function B.

[0030] Equation (1-4) is a constraint that indicates that the value of the variable xi,j is fixed to G in a specific time slot F. This term is introduced to ensure that the state of the substitute at the relevant time slot is the same as, or as close as possible to, the state of the target object. Therefore, it is desirable that F and G be determined from the state of the target object. Also, instead of including them in the mathematical model of optimization as in equation (1-4), it is also possible to exclude them from the target of optimization decision variables in advance and store fixed values.

[0031] The evaluation optimization model generation unit 5 includes a time slot variable generation unit 8, an objective function generation unit 9, and a constraint condition generation unit 10.

[0032] The time slot variable generation unit 8 generates an "operating state vector" by converting the operating state of the object during the evaluation period 21 into a constant vector of 0 and 1. The time slot variable generation unit 8 also generates an "alternative state variable vector", a variable vector for the optimization problem, which has the same time slot size and number of elements as the operating state vector. Each element of the "alternative state variable vector" is a decision variable for the optimization problem. The time slot variable generation unit 8 also generates an "exclusive OR vector" that takes the exclusive OR between the state of adjacent time slots j and j+1 of the alternative state variable vector or the operating state vector.

[0033] The objective function generating unit 9 generates an objective function such as the above-mentioned formula (1-1) based on the "operating state vector", the "alternative state variable vector", and the "exclusive OR vector".

[0034] The constraint generating unit 10 generates constraints such as the above-mentioned formulas (1-2) to (1-4) based on the "operating state vector", the "alternative state variable vector", and the "exclusive OR vector".

[0035] The optimization unit 6 identifies values ​​of decision variables that optimize the value of the objective function generated by the objective function generation unit 9 under the constraints generated by the constraint generation unit 10. The optimization unit 6 may be implemented by a CPU (Central Processing Unit) having one or more physical or virtual cores. Alternatively, the optimization unit 6 may be implemented using "dedicated optimization technology." Typically, the optimization unit 6 may be a hardware circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPU (Graphics Processing Unit), for example, a semiconductor computer (e.g., a CMOS annealing machine) that simulates the operation of an Ising model using a semiconductor circuit (e.g., a CMOS (Complementary Metal Oxide Semiconductor) circuit). For example, the optimization unit 6 may be implemented by an algorithm (e.g., momentum annealing) that runs on a GPU. Alternatively, the optimization unit 6 may be implemented using an annealing quantum computer or a general-purpose quantum computer instead of a digital computer.

[0036] In the case of an annealing quantum computer, for example, an Ising model using adiabatic quantum computing (quantum annealing) is used. Adiabatic quantum computing converts a problem so that the ground state of a physical system becomes the solution, and obtains a solution by finding the ground state (Reference: E. Farhi, et al., "A quantum adiabatic evolution algorithm applied to random instances of an NP-complete problem", Science 292, 472 (2001).). The principles and solution methods of the Ising model are publicly known and are disclosed, for example, in Japanese Patent Application Laid-Open No. 2022-151199, Japanese Patent Application Laid-Open No. 2022-116909, and Japanese Patent Application Laid-Open No. 2024-017959.

[0037] The solution processing unit 7 (output unit) outputs the solution obtained by the optimization unit 6 to the external output device 3 in a format that can be understood by the user. The solution processing unit 7 outputs at least a substitution evaluation result 30 indicating whether the target object can be replaced with an alternative object to the external output device 3.

[0038] 3 is a diagram showing an example of the hardware configuration of the information processing device 1. As an example, the information processing device 1 includes a processing device 11 such as a CPU (Central Processing Unit), a memory 12 such as a RAM (Random Access Memory) or a ROM (Read Only Memory), a storage device 13 such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), an input device 14 such as a keyboard, a mouse, or a touch panel, an output device 15 such as a display or a printer, and a communication device 16 configured with a NIC (Network Interface Card), a wireless communication module, a USB (Universal Serial Interface) module, a serial communication module, or the like.

[0039] In the information processing device 1, data such as programs used to execute predetermined processes is stored in the storage device 13, for example, and the processing device 11 reads the data into the RAM of the memory 12 and executes it. For example, the information processing device 1 realizes each of the functions of the evaluation optimization model generation unit 5, the optimization unit 6, and the solution processing unit 7 by having the processing device 11 read the programs stored in the storage device 13 into the memory 12 and execute them.

[0040] In addition, the programs that realize the functions of the object state memory unit 4, evaluation optimization model generation unit 5, optimization unit 6, and solution processing unit 7 can be recorded on, for example, a portable or fixed recording medium and distributed.

[0041] Next, the processing performed by the information processing device 1 will be described.

[0042] <Processing Overview> 4 is a processing flow diagram illustrating an outline of processing performed by the information processing device 1 according to the first embodiment. The processing shown in this diagram is executed, for example, when a predetermined input (e.g., input data 20) is made to the information processing device 1 by a user, or at a predetermined timing (e.g., a predetermined time or a predetermined time interval).

[0043] First, in step S101, the time slot variable generation unit 8 reads the object operation status information 40 for the evaluation period 21 from the object operation status information 40, and generates an "operation status vector" by converting the operation status of the object represented by the read object operation status information 40 into a constant vector of "0" or "1".

[0044] (operational status vector) 5 is a diagram showing an example of an operation status vector. The operation status vector has the following data items: column C401 in which the year, month, date, and time of the time slot is set; column C402 in which a time slot ID that is identification information for the time slot is set; column C403 in which the operation status of object 1 is set; column C404 in which the operation status of object 2 is set; and column C405 in which the operation status of object 3 is set.

[0045] First, the time slot variable generation unit 8 prepares time slots by dividing the evaluation period 21 by the increment 22 of the evaluation period time axis. For example, as shown in column C401, the time slot variable generation unit 8 prepares time slots by dividing a day into 24 one-hour segments. Then, the time slot variable generation unit 8 assigns a time slot ID as shown in column C402 to each time slot. Next, the time slot variable generation unit 8 sets the operating status (operating or not) of each object in each time slot as a value of "0" or "1." Specifically, the time slot variable generation unit 8 assigns "1" to the time within each time slot if the object is moving, and "0" otherwise. For example, the operating statuses of objects 1, 2, and 3 in Figure 2 are converted as shown in the example data set in columns C403, C404, and C405, respectively. Depending on the application of the present invention, if it is difficult to represent the operating state with a binary variable, for example, when there are multiple states, the operating state may be represented with an integer variable.

[0046] Subsequently, in step S102, the time slot variable generation unit 8 generates a variable vector for the optimization problem, an "alternative state variable vector," which has the same time slot size and number of elements as the operating state vector.

[0047] For example, the time slot variable generation unit 8 imports a module for optimization problems using Python (registered trademark) or the like, and generates an "alternative state variable vector" using a program that contains statements that create decision variables using the functions of this module.

[0048] The time slot variable generation unit 8 generates a variable vector (e.g., xi,j,bi,j in the above-mentioned formula (1)) that determines the operating state of each time slot as a solution to the optimization problem when at least a substitute that operates on a storage battery is used. However, the meaning and type of the variables differ depending on the embodiment. In the embodiment described later, an implementation method will be shown in which the variables include variables that represent not only the running state but also the charging state.

[0049] Next, in step S103, the time slot variable generation unit 8 generates an "exclusive OR vector" that takes the exclusive OR between the state of adjacent time slot j and the state of j+1 of the alternative state variable vector or the operating state vector. Hereinafter, the exclusive OR vector of the operating state vector may be referred to as the "operating state exclusive OR vector," and the exclusive OR vector of the alternative state variable vector may be referred to as the "alternative state exclusive OR variable vector."

[0050] FIG. 6 is a diagram showing an example of a method for expressing an exclusive OR vector. To simplify the explanation, this diagram uses constants instead of variables as an example. The illustrated constant vector 501 stores values ​​when, for example, Xi,j is an operating state vector that is originally a constant, or a constant vector when a value is determined using an alternative state variable vector. All Xi,j corresponding to the time slot IDs omitted by ellipsis lines in the diagram are 0. Ri,j,j+1 is an exclusive OR vector 502 of two adjacent time slots (j and j+1) for the constant vector 501.

[0051] In constant vector 501, 1s are consecutive for time slot IDs "11" to "13." Also, Ri,j,j+1 corresponding to time slot IDs omitted by ellipsis lines are all 0. As shown in the figure, exclusive OR vector 502 takes a value of 1 for the time slot IDs before and after the value of constant vector 501 switches. A specific method for implementing exclusive logic may be to perform a logical operation such as in equation (2) below, or to calculate from a formula such as equation (3) or equation (4) below. However, equations (2) to (4) are merely examples, and calculation may be performed using other formulas, etc., as long as the numerical value of exclusive OR vector 502 can be obtained.

[0052]

number

[0053]

number

[0054]

number

[0055] Subsequently, in step S104, the constraint generating unit 10 generates constraints such as the above-mentioned formulas (1-2), (1-3), and (1-4). For example, the constraint generating unit 10 generates constraints by executing a program containing statements for creating constraints using functions of the imported module for the optimization problem.

[0056] Here, the constraint generating unit 10 uses the value of the operating state vector in the constraint for making the operating state of the substitute always or as close to the state of the target object as possible at the corresponding time slot, such as in the above-mentioned formula (1-4). For example, the constraint generating unit 10 uses, for F in formula (1-4), a set of time slots for which it is desired to make the values ​​of the operating state vector and the substitute state variable vector match, and for G, the operating state vector value at the time slot included in F. To give a specific example, if the time slot corresponds to a time slot where the state in FIG. 2 is "Visit," the constraint generating unit 10 always fixes the operating state of the substitute to "0" because the vehicle will not be running and the time slot contains a schedule that cannot be determined solely by the user (for example, a stay at a business-related visit (e.g., a customer's site)).

[0057] In time slots other than the time slots for which the constraint generating unit 10 has imposed a constraint to match the value of the operating state vector, the alternative state variable vector can take any value within a range that satisfies the other constraints.

[0058] Next, in step S105, the objective function generation unit 9 generates an objective function such as the above-mentioned formula (1-1). For example, the objective function generation unit 9 generates the objective function by using the function of the imported module for the optimization problem to execute a program containing statements for creating an objective function whose variables are the exclusive OR vector and alternative state variable vector created by the time slot variable generation unit 8.

[0059] In this embodiment, the objective function generation unit 9 stores in the objective function at least information regarding the "deviation value" that represents the degree of deviation between the state of the object and the state of the substitute, and generates an objective function that minimizes the deviation value so that when the object is replaced with the substitute, the state of the object is maintained in the substitute as much as possible.

[0060] Specifically, the objective function generating unit 9 defines the deviation value using an exclusive OR vector, and provides an objective function that minimizes the deviation value, for example, in the form of the following equations (5-1) to (5-2).

[0061]

number

[0062] Since it is an objective function, X in the above-mentioned formula (2), formula (3), or formula (4) is not a constant, and r is generated using the alternative state variable x, as in formula (5-2). In formula (5-2), the form of formula (4) is used, but formula (2), formula (3), or an exclusive OR expressed in another form may also be used.

[0063] An example of the deviation value is shown by the following equation (6).

[0064]

number

[0065] Ri,j,j+1 is the "element of the exclusive OR vector calculated from the vector whose value is determined by optimization using the alternative state variable vector," and Gi,j,j+1 is the "element of the exclusive OR vector calculated from the operation state vector." In other words, the deviation value is the value obtained by subtracting the "sum of the elements of the exclusive OR vector calculated from the operation state vector" from the "sum of the elements of the exclusive OR vector calculated from the vector whose value is determined by optimization using the alternative state variable vector." In other words, the deviation value is the difference between the number of times the operation status of the target object switches (the operation status switches from "0" to "1" or from "1" to "0") and the number of times the operation status of the alternative object switches.

[0066] That is, the objective function generation unit 9 uses the distance between the operating state exclusive OR vector and the alternative state exclusive OR variable vector, as expressed in equation (6), as the deviation value, and generates an objective function having a parameter that represents the degree of deviation between the operating state of the target object and the operating state of the alternative object in order to minimize the deviation value.

[0067] As long as it is fixed under the constraints shown in the above-mentioned formula (1-4), the minimum value of the "sum of the elements of the exclusive OR vector calculated from the vector whose value is determined by optimization in the alternative state variable vector" will match the "sum of the elements of the exclusive OR vector calculated from the operating state vector." As a result, if the deviation value calculated by formula (6) is 0, it can be determined that there is no deviation, and if it is different, it can be determined that there is a deviation of that magnitude.

[0068] Next, in step S106, the optimization unit 6 optimizes the objective function generated by the objective function generation unit 9 under the constraint conditions generated by the constraint condition generation unit 10. Then, the optimization unit 6 generates a solution vector as a result of the optimization.

[0069] (solution vector) FIG. 7 is a diagram showing an example of a solution vector. For example, the optimization unit 6 generates a solution vector as shown in this diagram in response to an input of the operating state vector shown in FIG. 5. The solution vector is the value of the alternative state variable vector obtained by optimizing the objective function described above. The solution vector 601 shown in the diagram is the alternative evaluation result for object 1, the solution vector 602 is the alternative evaluation result for object 2, and the solution vector 603 is the alternative evaluation result for object 3.

[0070] Next, in step S106, the solution processing unit 7 converts the solution vector into a format that the user can understand and outputs the converted data to the external output device 3. In the example shown in FIG. 7, the sum of the elements of the exclusive OR vector (the number of points where the continuous 1s change) is 4 for all solution vectors. When the solution vector 601 shown in FIG. 7 is compared with the column C403 of the operating state vector shown in FIG. 5, the solution vector 602 with the column C404 of the operating state vector, and the solution vector 603 with the column C405 of the operating state vector, the deviation values ​​calculated by equation (6) are all 0. Therefore, in this example, the solution processing unit 7 determines that the deviation value is 0, indicating no deviation, and outputs information indicating the substitution evaluation result "substitutable" to the external output device 3. On the other hand, if the deviation value is greater than 0, the solution processing unit 7 outputs information indicating the substitution evaluation result "non-substitutable" to the external output device 3. The external output device 3 displays the alternative evaluation results input from the solution processing unit 7. Then, the process ends.

[0071] In this embodiment, the solution processing unit 7 determines that the object can be "substituted" for an alternative when the deviation value is 0, but this is not limited to this. The solution processing unit 7 may determine that the object can be "substituted" for an alternative when the deviation value is equal to or less than a predetermined threshold value greater than 0, and may determine that the object cannot be "substituted" for an alternative when the deviation value is greater than the threshold value.

[0072] Furthermore, the order of steps S104 and S105 described above may be reversed.

[0073] As described above, the information processing device 1 of this embodiment evaluates the substitution of an object that operates using a means other than a storage battery with a substitute that operates using a storage battery. That is, the information processing device 1 includes: an objective function generation unit 9 that acquires object operating state information from an object state storage unit 4 that stores object operating state information that indicates changes in the past operating state of the object; an objective function generation unit 9 that generates an objective function having a parameter term that indicates the degree of deviation between the operating state of the object and the operating state of the substitute, using the operating state of the substitute as a decision variable; a constraint condition generation unit 10 that generates constraint conditions related to the remaining capacity of the storage battery that allows the substitute to operate; an optimization unit 6 that identifies values ​​of decision variables that optimize the value of the objective function under the constraint conditions; and a solution processing unit 7 that outputs an evaluation result based on the optimization result.

[0074] That is, the information processing device 1 of this embodiment determines the operating state of the substitute so that the operating state of the substitute is as close as possible to the operating state of the target object (that is, the difference between the operating state of the substitute and the operating state of the target object can be reduced) while keeping the remaining charge of the storage battery within the range in which the substitute can operate. This makes it possible to appropriately evaluate the substitution of the target object with the substitute.

[0075] Furthermore, the information processing device 1 of this embodiment generates a constraint condition that causes the operating state of the substitute to match the operating state of the target object during a predetermined time period.

[0076] That is, the information processing device 1 of the present embodiment matches the operating state of the substitute with the operating state of the target object during a time period when there is an unchangeable schedule for the business (for example, a stay at a business-related visit (for example, a client's site)). This makes it possible to appropriately evaluate whether the business can be performed using the substitute.

[0077] In addition, the information processing device 1 of this embodiment uses the presence or absence of a substitute as a decision variable, generates an objective function having a term representing the difference between the number of times the target object switches between being in operation and being in operation and the number of times the substitute switches between being in operation and being in operation, and identifies the presence or absence of the substitute that minimizes the value of the objective function under constraints related to a specified time.

[0078] As long as the operating status of the substitute is fixed by a constraint that matches the operating status of the target object during a specified time period, the fewer the number of times the operating status switches between on and off, the smaller the discrepancy between the operating status of the target object and the operating status of the substitute. Therefore, it is possible to identify the "operating status of the substitute" that can reduce the discrepancy between the operating status of the substitute and the operating status of the target object, thereby making it possible to more appropriately evaluate the replacement of the target object with the substitute.

[0079] Furthermore, the information processing device 1 of this embodiment determines that the target object can be replaced by a substitute if the deviation value between the operating state of the target object and the operating state of the substitute is less than a predetermined threshold value as a result of optimization, and determines that the target object cannot be replaced by a substitute if the deviation value is greater than the threshold value, and outputs the determination result as an evaluation result.

[0080] That is, the information processing device 1 of the present embodiment outputs, as an evaluation result, whether or not the target object can be replaced with an alternative, thereby enabling the user to easily know whether or not the task can be performed if the target object is replaced with an alternative.

[0081] In addition, the information processing device 1 of this embodiment further includes a time slot variable generation unit 8 that generates an operating state vector that represents whether or not an object is operating for each time slot obtained by dividing the time axis at a predetermined interval, and an alternative state variable vector that represents whether or not an alternative object is operating for each time slot.The alternative state variable vector is used as a decision variable, and an objective function is generated having a term in which the distance between an operating state exclusive-OR vector that represents the exclusive-OR of whether or not an object is operating in two adjacent time slots in the operating state vector and an alternative state exclusive-OR variable vector that represents the exclusive-OR of whether or not an object is operating in two adjacent time slots in the alternative state variable vector is used as a deviation value that represents the degree of deviation, and an alternative state variable vector that minimizes the value of the objective function under constraints is identified.

[0082] In this way, by generating vectors that represent the operating state in time slots that divide the time axis, it is possible to more accurately calculate the deviation value between the operating state of the target object and the operating state of the substitute, thereby enabling more appropriate substitution evaluation.

[0083] [Second embodiment] Next, an information processing device, an information processing method, and an information processing program according to a second embodiment will be described.

[0084] This embodiment shows an example of an EV conversion plan evaluation that determines whether multiple gasoline-powered vehicles belonging to a specified base and used for sales and delivery operations can be replaced with electric vehicles (EVs). A gasoline-powered vehicle is a vehicle that runs on gasoline. An electric vehicle is a vehicle that uses electricity as its energy source and runs on an electric motor. In the following, replacing (substituting) gasoline-powered vehicles with electric vehicles may be referred to as "EV conversion."

[0085] In this example, it is assumed that EV chargers will be installed in the parking lots of business bases. In addition, if EVs are used, there is the option of using charging spots accessible from public roads (hereinafter sometimes referred to as "route chargers") in addition to those at the bases.

[0086] <Input / output data of information processing device> 8 is a block diagram showing an example of input / output data of an information processing device according to the second embodiment. In this figure, the same components as those in the first embodiment shown in FIG. 1 are given the same reference numerals, and the description thereof will be omitted.

[0087] In this embodiment, input data 720 to the information processing device 701 includes parameters related to the EVs to be substituted, which are optionally provided by the user. By adjusting these parameters, the user can perform substitution simulations assuming various chargers and EV models. EV-related parameters include, for example, the number of station chargers, station charger specifications, the desired number of vehicles to be replaced, the desired EV electricity cost, the desired EV battery capacity, or the maximum cost for introducing EVs. Station chargers are EV chargers installed at stations. The desired number of replacements is the desired number of gasoline-powered vehicles to be replaced with EVs.

[0088] The output data 730 from the information processing device 701 may be text data or image data. The output data 730 includes an EV conversion feasibility determination result indicating whether or not a vehicle can be converted into an EV, an EV conversion feasibility rate indicating the percentage of vehicles that can be converted into an EV, information related to the SoC, etc.

[0089] The object state storage unit 704 stores object state information 740, which is the operational performance of the target gasoline-powered vehicle obtained by using telematics or the like, as information equivalent to the object state information 40 for the entire period in the first embodiment. The telematics data included in the object state information 740 include the base parking lot location, which is the location of the parking lot at the base, the daily departure and arrival times of each vehicle, travel routes, parking and stopping locations of visited destinations, and visit times. The travel routes are chronological location information of the vehicle. The object state storage unit 704 may be included inside the device that realizes the information processing device 701, may be externally attached, or may be cloud storage via a network.

[0090] Furthermore, in this embodiment, the information processing device 701 is connected to a route charger information storage unit 705. The route charger information storage unit 705 stores route charger position information indicating the position of each route charger, and route charger information 750 including the specifications of each route charger. Similar to the object state storage unit 704, the route charger information storage unit 705 may be included inside the device that implements the information processing device 701, may be externally attached, or may be cloud storage via a network.

[0091] <Functional configuration of information processing device> Fig. 9 is a block diagram showing an example of the configuration of an information processing device according to the second embodiment. As shown in the figure, an information processing device 701 according to this embodiment further includes a hashing unit 907 and a route charging spot calculation unit 902 in addition to the configuration of the information processing device 1 shown in Fig. 1. Furthermore, the information processing device 701 is connected to an object state storage unit 704 and a route charger information storage unit 705.

[0092] The hashing unit 907 acquires travel route position information (position and time information) indicating the travel route (time and position) of each candidate vehicle to be replaced with an EV from the object state storage unit 704, and acquires route charger position information from the route charger information storage unit 705. The hashing unit 907 then hashes the travel route position information and route charger position information of each vehicle. Hashing means calculating a hash value. When hashing, the accuracy of the position information is determined by the length of the hash value, but the length of the hash value can be set arbitrarily by the user. The hashing unit 907 may be located on the same device as the route charging spot calculation unit 902, or may be located on the cloud or a different device.

[0093] The route charging spot calculation unit 902 calculates the time at which each vehicle can be charged along the travel route. That is, the route charging spot calculation unit 902 calculates time information representing the time in the travel route position information of each vehicle that indicates a position that approximately matches the position indicated by the route charger position information. Specifically, the route charging spot calculation unit 902 first compares the hash value of the travel route position information of each vehicle with the hash value of the route charger position information. If the two compared hash values ​​match, the route charging spot calculation unit 902 determines that route charging is possible at the time when the target vehicle is at the corresponding position; otherwise, it determines that there is no location where route charging is possible. Route charging means charging at a charging spot along the travel route. The route charging spot calculation unit 902 outputs time information representing the time at which it was determined that route charging is possible to the evaluation optimization model generation unit 903.

[0094] 10 is a diagram showing the functional configuration of the evaluation optimization model generation unit 903 according to the second embodiment. The evaluation optimization model generation unit 903 in this embodiment includes a time slot variable generation unit 1102, an objective function generation unit 1103, and a constraint condition generation unit 1104.

[0095] The time slot variable generation unit 1102 includes a variable fixing unit 1105, and generates three types of substitute variable vectors: a traveling state variable vector, a station charging state variable vector, and a route charging state variable vector. Other processing by the time slot variable generation unit 1102 is similar to the processing by the time slot variable generation unit 8 in the first embodiment, and therefore description thereof will be omitted.

[0096] The variable fixing unit 1105 replaces some elements of the traveling state variable vector, the station charging state variable vector, or the route charging state variable vector with constants instead of variables. Fixing the variables to constants reduces the number of variables, making it possible to complete the simulation in a short time.

[0097] The objective function generation unit 1103 uses the three types of alternative variable vectors generated by the time slot variable generation unit 1102 to generate an objective function that minimizes the deviation value between the driving state when converted to an EV and the driving state of the actual data of the target object, as well as the operating cost of the EV.

[0098] The constraint generating unit 1104 generates constraints that determine the upper and lower limits of the SoC given by the above-mentioned equations (1-2) and (1-3), in the same way as the constraint generating unit 10 in the first embodiment.

[0099] 9, the functional configuration of the information processing device 701 will be further described. The optimization unit 904 optimizes the objective function generated by the objective function generation unit 1103 under the constraint conditions generated by the constraint condition generation unit 1104.

[0100] The solution processing unit 905 outputs the solution obtained by the optimization unit 904 to the external output device 3 in a format that can be understood by the user.

[0101] Next, the processing performed by the information processing device 701 will be described.

[0102] <Processing Overview> 11 is a processing flow diagram illustrating an outline of processing performed by the information processing device 701 according to the second embodiment. The processing shown in this diagram is executed, for example, when a predetermined input (e.g., input data 720) is made to the information processing device 701 by a user, or at a predetermined timing (e.g., a predetermined time or a predetermined time interval).

[0103] First, in step S201, the hashing unit 907 acquires travel route position information indicating the travel route (time and position) of each vehicle that is a candidate to be replaced with an EV from the object state storage unit 704, and acquires route charger position information indicating the route charger positions from the route charger information storage unit 705. Then, the hashing unit 907 calculates a hash value for each of the travel route position information and the route charger position information of each vehicle.

[0104] Next, in step S202, the route charging spot calculation unit 902 executes a route charging spot calculation process to calculate the time when each vehicle can be charged along the travel route.

[0105] <Route charging spot calculation process> 12 is a process flow diagram illustrating the details of the route charging spot calculation process, which is the details of the process in step S202 described above.

[0106] First, in step S1001, the route charging spot calculation unit 902 compares the hash value of the travel route position information of each vehicle with the hash value of the route charger position information, and determines whether the two compared hash values ​​match. If the hash values ​​do not match (step S1001: No), the route charging spot calculation unit 902 determines that there is no location where the vehicle can charge along the route, and ends the route charging spot calculation process.

[0107] On the other hand, if the hash values ​​match (step S1002: No), the route charging spot calculation unit 902 determines in step S1002 that route charging is possible at the time when the vehicle is at the position where the hash values ​​match, and outputs time information indicating that time to the evaluation optimization model generation unit 903. Thereafter, the route charging spot calculation process ends.

[0108] 11, next, in step S203, the time slot variable generating unit 1102 generates an “operating state vector.” The method for generating the operating state vector is the same as in the first embodiment, and therefore a description thereof will be omitted.

[0109] Subsequently, in step S204, the time slot variable generation unit 1102 generates three types of substitute variable vectors: a traveling state variable vector, a station charging state variable vector, and a route charging state variable vector.

[0110] (substitution variable vector) FIG. 13 is a diagram showing an example of a substitute variable vector. The driving state variable vector 1210 is a vector that stores binary variables that take a value of "1" when the EV is driving and a value of "0" when it is not driving. However, not all elements of the vector are necessarily assigned binary variables. For example, a decision variable is assigned to the portion where "B" is set, such as time slots C1212 and C1214 shown in the figure, but the remaining portions may be fixed to "0". The variable fixing unit 1105 of the time slot variable generation unit 1102 fixes the driving state variable vector to "0" using two different types of variable fixing processing.

[0111] In the first variable fixing process, the variable fixing unit 1105 of the time slot variable generation unit 1102 fixes the time slot of the time period when the operating state of the object (for example, the "state" column shown in FIG. 2) is "Visit" to "0." For example, if the operating state of the object is "Visit" while visiting a customer, even if the object is substituted with an EV, "Visit" must be achieved during that time period (for example, C1213) while visiting a customer, so the time slot is fixed to "0" so that it does not become a running state.

[0112] In the second variable fixing process, the variable fixing unit 1105 of the time slot variable generation unit 1102 fixes to "0" the time slots of time periods when the user clearly does not perform work, such as late at night or early in the morning. The time periods when the user clearly does not perform work, i.e., the time periods when the object is not used for work, are set in advance by the user. The variable fixing unit 1105 of the time slot variable generation unit 1102 fixes to "0" the time slots corresponding to the time periods set in advance by the user (for example, the time slot of the early morning time period shown in C1211 and the time slot of the late night time period shown in C1215).

[0113] The route charging status variable vector 1220 is a vector that stores a binary variable that takes on a value of "1" when the EV is undergoing route charging and a value of "0" when it is not. Route charging is not possible anywhere; charging is not possible unless there is a charging spot on the route of each target vehicle. Therefore, the variable fixing unit 1105 of the time slot variable generation unit 1102 assigns "B" only to the time slots that correspond to the time information input from the route charging spot calculation unit 902 (in the illustrated example, the time slots of C1221 and C1222) and sets them as decision variables, and fixes the other time slots to "0."

[0114] The station charging state variable vector 1230 is a binary variable that takes on a value of "1" when the EV is being charged at a station and a value of "0" when it is not. In the driving state variable vector 1210, the late-night or early-morning time slots of C1211 and C1215 are fixed to "0." Conversely, during these time slots, the EV is not in operation and therefore station charging is possible. Therefore, the variable fixing unit 1105 of the time slot variable generation unit 1102 assigns "B" to the time slot corresponding to the time slot specified by the user in the second variable fixing process described above, as a decision variable, and fixes the other time slots to "0."

[0115] 11, subsequently, in step S205, the time slot variable generation unit 1102 generates an “exclusive OR variable vector.” The method for generating the exclusive OR variable vector is the same as in the first embodiment, and therefore description thereof will be omitted.

[0116] Next, in step S206, the objective function generation unit 1103 generates an objective function using the operating state vector, three types of alternative variable vectors, and the exclusive OR variable vector generated by the time slot variable generation unit 1102. For example, the objective function generation unit 1103 generates the objective function shown in the following equation (7).

[0117]

number

[0118] In equation (7), the first term related to coefficient α1 is a term for minimizing the EV operation budget. The first term is the cost of operating the station charger, and the second term is the cost of using the route charger. In other words, the first term related to coefficient α1 is a parameter term that represents the operating cost based on the cost of charging the substitute's storage battery. Here, zij is the variable assigned to the jth time slot of the station charging variable vector for the i-th EV, and yij is the variable assigned to the jth time slot of the route charging variable vector for the i-th EV. The coefficient Cp is the cost of using the station charger per time slot. Furthermore, the coefficient Cs is the cost of using the route charger per time slot. While equation (7) assumes a uniform cost per time slot, the coefficient Cp or coefficient Cs may be set so that the cost varies depending on the time of day or location.

[0119] In equation (7), the second term related to coefficient α2 is a term for minimizing the deviation value, similar to equation (5) above. In other words, the second term related to coefficient α2 is a parameter term that represents the degree of deviation between the operating state of the target object and the operating state of the substitute object. An example of element Ri,j,j+1 of the exclusive OR vector is shown in the following equation (8).

[0120]

number

[0121] Here, since it is desirable that the sum of the traveling state variable x and the route charging variable y coincide with the traveling state of the object, it is defined as in equation (8).

[0122] Equation (7) is multi-objective optimization, and which term is given priority depends on the user's needs, so the ratio is adjusted using coefficients α1 and α2.

[0123] Next, in step S206, the constraint generator 1104 sets the upper and lower limits of the SoC given by equations (1-2) and (1-3), similarly to the constraint generator 10 according to the first embodiment. However, unlike the example of equation (1), which is a typical example, in this embodiment, the SoC variables are determined using not only the values ​​of the driving state variable vector but also the values ​​of the route charging variable vector.

[0124] The constraint generating unit 1104 specifically generates the following equations (9-1) to (9-2) as the functional form of equation (1-3) that determines the SoC variables.

[0125]

number

[0126] bi0 is the SoC value of the substitute vehicle i in time slot 0. Here, it is assumed that the vehicle is at the base and fully charged during time slot 0. Although the vehicle is being charged at the base, in order to maintain good battery condition, the battery is not fully charged, but rather a constraint such as that in equation (9-1) is imposed so that the upper limit of the battery capacity Cbat is U (for example, 0.8). Therefore, bi0 is a constant. bij is the SoC value of vehicle i during time slot j, which is 1 or greater. Here, P is the charge amount per time slot of the route charger, and Ci is the power consumption (electricity cost) per time slot of vehicle i.

[0127] Furthermore, in this embodiment, the constraint generating unit 1104 also generates the constraint of the following equation (10).

[0128]

number

[0129] For each time slot, an EV can only be in one of three states: driving, route charging, or station charging, or in a standby state where it does nothing. Therefore, as shown in equation (10), for each time slot of each EV, the sum of the variables representing the driving state, route charging state, and station charging state must be less than or equal to 1.

[0130] Next, in step S208, the optimization unit 904 optimizes the objective function generated by the objective function generation unit 1103 under the constraint conditions generated by the constraint condition generation unit 1104. Then, the optimization unit 904 generates a solution vector as the optimization result. The solution vector is the value of the alternative state variable vector obtained by optimizing the above-mentioned objective function equation (7).

[0131] Next, in step S209, the solution processing unit 905 converts the solution vector into a format that the user can understand, and outputs the converted output data 730 to the external output device 3. The external output device 3 displays the output data 730 input from the solution processing unit 905. The processing then ends. For example, the solution processing unit 905 outputs the EV conversion feasibility result indicating whether or not EV conversion is possible, as well as the EV conversion feasibility rate indicating the percentage of vehicles that can be converted into EVs, SoC results processed from the optimized calculation results, etc.

[0132] (Display screen example) 14 is a diagram showing an example of a display format of SoC. In a graph displayed on a screen 801, the horizontal axis represents time and the vertical axis represents SoC (unit: %). The external output device 3 outputs, on the screen 801, a time series transition of SoC (unit: %) during the evaluation period using a solid line L810. The external output device 3 also visualizes the constraint conditions of the upper and lower limits of SoC as shown in the above-mentioned formula (1-2) using a dotted line L820 (upper limit) and a dotted line L830 (lower limit).

[0133] The order of steps S206 and S207 may be reversed.

[0134] As described above, the object state memory unit 704 of this embodiment stores position and time information (travel route position information), which is time-series position information of the object, which is a vehicle, and the information processing device 701 acquires the position and time information from the object state memory unit 704, calculates time information representing the time at the position and time information indicating a position that approximately coincides with the position indicated by the route charger position information, which is position information of a charging spot where the storage battery can be charged, generates a driving state variable vector representing the driving state of the substitute object and a route charging state variable vector representing the charging state at the charging spot as the alternative state variable vector, and in the route charging state variable vector, the charging state of the time slot corresponding to the time information is used as the decision variable.

[0135] That is, the information processing device 701 of this embodiment determines the operating state of the substitute by simulating a route for charging the substitute, which is an EV, at a location where charging is possible. That is, the information processing device 701 determines the operating state of the substitute so that the route for charging is not routed to a location where charging is not possible. This enables more accurate simulations and more appropriate evaluation of the transition to EVs.

[0136] Furthermore, the information processing device 701 of this embodiment converts the position information into a hash value, and calculates time information indicating the time when the hash value of the position time information and the hash value of the route charger position information match.

[0137] This makes it possible to more efficiently calculate the time when charging is possible along the route.

[0138] In addition, the information processing device 701 of this embodiment generates a driving state variable vector, a route charging state variable vector, and a base charging state vector representing the charging state at bases related to business as alternative state variable vectors, and in the driving state variable vector, the driving state of the time slot corresponding to the time period when the object is used for business is used as the decision variable, and in the base charging state vector, the charging state of the time slot corresponding to the time period when the object is not used for business is used as the decision variable.

[0139] That is, the information processing device 701 of this embodiment sets decision variables according to the time period when the object is used for business, and fixes other elements of the variable vector to constants. Fixing variables to constants in this way reduces the number of variables, and enables the simulation to be completed in a short time.

[0140] In addition, the information processing device 701 of this embodiment generates an objective function having a parameter term representing the operating cost based on the cost of charging the storage battery and a parameter term representing the degree of deviation, and generates constraint conditions that determine the upper and lower limits of the remaining capacity of the storage battery.

[0141] This makes it possible to calculate a solution vector (driving conditions of the substitute) that is closer to the driving conditions of the target object while keeping operating costs down within the scope in which operations can be carried out with the substitute, thereby enabling the evaluation of EV conversion while also taking operating costs into account.

[0142] Furthermore, the information processing device 701 of this embodiment outputs the time series transition of the remaining capacity (SoC) of the storage battery.

[0143] This allows users to consider converting to an EV by referring to the progress of the SoC.

[0144] [Third embodiment] Next, an information processing device, an information processing method, and an information processing program according to the third embodiment will be described.

[0145] <Overall overview of information processing equipment> Fig. 15 is a block diagram showing an example of the configuration of an information processing device according to the third embodiment. In this figure, the same components as those in the first embodiment shown in Fig. 1 or the second embodiment shown in Fig. 9 are denoted by the same reference numerals, and their description will be omitted.

[0146] The information processing device 1301 in this embodiment further has a recommendation function for recommending a combination of EV models that are recommended as alternatives when converting a gasoline-powered vehicle into an EV as in the second embodiment.

[0147] In this embodiment, input data 1320 to the information processing device 1301 includes a desired vehicle type and a desired number of vehicles. The desired vehicle type is the type of EV that the user desires as a replacement. The desired number of vehicles is the number of EVs that the user desires to replace gasoline-powered vehicles with.

[0148] The output data 1330 from the information processing device 1301 includes a recommendation for a combination of vehicle types of EVs to be replaced, and the operating costs for the recommended combination of vehicle types.

[0149] Furthermore, the information processing device 1301 in this embodiment is connected to a vehicle model information storage unit 1304. The vehicle model information storage unit 1304 pre-stores vehicle model information 1340 relating to a wide variety of EVs that can be the subject of simulation. The vehicle model information 1340 includes, for example, the name of each EV model (model name), the electricity consumption of each model, the battery capacity (storage battery capacity) of each model, and the operating costs of each model.

[0150] Moreover, the information processing device 1301 further includes a combination generation unit 1308 in addition to the configuration of the information processing device 701 in the second embodiment.

[0151] The combination generation unit 1308 generates a plurality of combinations for the desired number of vehicles from among the desired vehicle models included in the input data 1320 .

[0152] The evaluation optimization model generation unit 1305 generates an evaluation optimization model (objective function and constraint conditions) for each generated combination.

[0153] The optimization unit 1306 optimizes the evaluation optimization model for each combination.

[0154] The solution processing unit 1307 outputs the solution obtained by the optimization unit 1306 to the external output device 3 in a format that can be understood by the user.

[0155] <Processing Overview> Fig. 16 is a diagram showing an example of processing performed by the information processing device 1301 according to the third embodiment. Fig. 17 is a processing flow diagram illustrating an outline of processing performed by the information processing device 1301 according to the third embodiment. The processing shown in this diagram is executed, for example, when a predetermined input (e.g., input data 1320) is made to the information processing device 1 by the user, or at a predetermined timing (e.g., a predetermined time, a predetermined time interval).

[0156] The processing in steps S301 and S302 is the same as the processing in steps S201 and S202 described above, and therefore a description thereof will be omitted.

[0157] Following step S302, in step S303, the combination generation unit 1308 generates a plurality of combinations of the desired number of vehicles from the desired vehicle models included in the input data 1320. The number of combinations to be generated can be set arbitrarily by the user. The combination generation unit 1308 may randomly generate a predetermined number of combinations, or may generate all combinations. Below, an example will be described in which four combinations are randomly generated.

[0158] 16, the input data 1320 includes the desired number of vehicles "3" and the desired vehicle types {"A-1", "A-2", "B-1", "B-2"}. The combination generation unit 1308 generates four combinations for the input data 1320: combination 1 {"A-2", "A-2", "B-2"}, combination 2 {"A-2", "B-1", "B-2"}, combination 3 {"A-2", "B-2", "A-1"}, and combination 4 {"A-2", "B-1", "A-1"}. Each combination includes the desired number of vehicles "3".

[0159] Next, the information processing device 1301 executes the processes of steps S304 to S305 for each of the generated combinations.

[0160] Specifically, in step S304, the evaluation optimization model generation unit 1305 generates an evaluation optimization model (objective function and constraint conditions) for the corresponding combination. The process of generating the evaluation optimization model is the same as the process in steps S203 to S207 described above, and therefore a description thereof will be omitted.

[0161] At this time, the evaluation optimization model generation unit 1305 reads out from the vehicle model information storage unit 1304 numerical values ​​to be used in the evaluation model, such as the operating costs of each vehicle model used to minimize operating costs, and the electricity cost and battery capacity of each vehicle model used to calculate the SoC constraints.

[0162] Next, in step S306, the optimization unit 1306 optimizes the evaluation optimization model generated by the evaluation optimization model generation unit 1305. The process of optimizing the evaluation optimization model is the same as the process in step S208 described above, and therefore a description thereof will be omitted.

[0163] After executing the processes of steps S304 and S305 for each of the generated combinations, the solution processing unit 1307 converts the solution vector into a format that can be understood by the user, and outputs the converted output data 1330 to the external output device 3.

[0164] The solution processing unit 1307 in this embodiment recommends a combination of alternative EV vehicle types in addition to the output data 930 output by the solution processing unit 905 in the second embodiment. Specifically, the solution processing unit 1307 first calculates the operating cost of each combination. For example, the solution processing unit 1307 may calculate the operating cost using the first term of the above-mentioned equation (7). Specifically, the solution processing unit 1307 calculates the operating cost of each combination by substituting the solution vector of each combination into the following equation (11).

[0165]

number

[0166] The solution processor 1307 may add the initial installation cost and the cost related to maintenance to the operating cost. The solution processor 1307 may also calculate the operating cost using another model.

[0167] The solution processor 1307 then compares the calculated operating costs of each combination to determine the best cost, which may be, for example, the lowest operating cost.

[0168] In the example shown in FIG. 16, the solution processing unit 1307 selects combination 1, which has the lowest operating cost, from among the operating cost of combination 1 (5), the operating cost of combination 2 (6), the operating cost of combination 3 (10), and the operating cost of combination 4 (15), as the combination of vehicle models with the best cost, and outputs a recommendation for the selected combination and its operating cost to the external output device 3. The external output device 3 displays the input recommendation "Combination 1 is the lowest cost and recommended" and the operating cost of combination 1 (5). Then, the processing ends.

[0169] In this embodiment, an example has been described in which a plurality of vehicles are desired, but the desired number may be 1. When the desired number is 1, the solution processing unit 1307 recommends the vehicle model with the lowest operating cost as an alternative.

[0170] As described above, the information processing device 1301 of this embodiment optimizes the value of the objective function for each of a plurality of vehicle types as substitutes, and outputs information indicating the vehicle type with the lowest operating costs as a result of the optimization.

[0171] That is, the information processing device 1301 of this embodiment compares the operating costs of multiple vehicle types and recommends a vehicle type to the user as a substitute EV. This allows the user to refer to the recommendation and select a vehicle type of EV to adopt as a substitute.

[0172] In addition, the information processing device 1301 of this embodiment generates multiple combinations of vehicle types based on multiple vehicle types of substitutes and the number of target objects to be replaced with the substitutes, optimizes the value of the objective function for each of the multiple combinations, and outputs information representing the combination with the lowest operating cost as a result of the optimization.

[0173] That is, the information processing device 1301 of this embodiment recommends to the user the combination with the lowest operating cost among multiple vehicle type combinations as a substitute EV combination, allowing the user to easily know which combination of EV types from the many available to substitute will most likely reduce operating costs.

[0174] The present invention is not limited to the above-described embodiments, and can be implemented using any components within the scope of the present invention. The above-described embodiments and modifications are merely examples, and the present invention is not limited to these contents as long as the characteristics of the invention are not impaired. Furthermore, although various embodiments and modifications have been described above, the present invention is not limited to these contents. Other aspects conceivable within the scope of the technical idea of ​​the present invention are also included within the scope of the present invention.

[0175] For example, part of the hardware provided in each device of this embodiment may be provided in another device.

[0176] Furthermore, each program of the information processing devices 1, 701, 1301 may be provided in another device, a program may consist of multiple programs, or multiple programs may be integrated into one program.

[0177] Furthermore, the objective function and constraint conditions shown in the above-described embodiment are merely examples, and any function that can optimize the deviation between the operating state of the target object and the operating state of the substitute object may be used. In addition to mathematical models, an Ising model using an annealing machine (adiabatic quantum computing, etc.) may also be adopted. [Explanation of symbols]

[0178] 701,1301 Information processing equipment 2 External input devices 3 External output device 4,704 Object state memory section 5,903,1305 Evaluation optimization model generation part 6,904,1306 Optimization Department 7,905,1307 Solution processing department 8,1102 Time slot variable generation unit 9,1103 Objective function generator 10,1104 Constraint condition generator 705 Route charger information storage unit 902 Route charging spot calculation unit 907 Hashing section 1308 Combination Generation Unit

Claims

1. An information processing device that evaluates whether to replace an object that operates by means other than a storage battery with an alternative that operates by a storage battery, a processor and a memory; an objective function generation unit that acquires the object operating state information from an object state storage unit that stores object operating state information that represents changes in the past operating state of the object, and generates an objective function that uses the operating state of the substitute as a decision variable and has a parameter term that represents the degree of deviation between the operating state of the object and the operating state of the substitute; a constraint condition generating unit that generates a constraint condition related to a remaining capacity of the storage battery that allows the substitute to operate; an optimization unit that identifies values ​​of decision variables that optimize the value of the objective function under the constraints; an output unit that outputs an evaluation result based on the result of the optimization; An information processing device comprising:

2. the constraint condition generation unit generates a constraint condition that causes an operating state of the substitute to match an operating state of the target object during a predetermined time period; The information processing device according to claim 1 .

3. The objective function generation unit generating an objective function having a term representing the difference between the number of times the target object switches between operating and not operating and the number of times the substitute object switches between operating and not operating, using the presence or absence of the substitute as a decision variable; The optimization unit Minimizing the value of the objective function under the constraint condition related to the predetermined time, and identifying whether or not the substitute is in operation. The information processing device according to claim 2 .

4. the output unit determines that the object can be substituted with the substitute when a deviation value between the operating state of the object and the operating state of the substitute is equal to or smaller than a predetermined threshold value as a result of the optimization, and determines that the object cannot be substituted with the substitute when the deviation value is greater than the threshold value, and outputs the determination result as the evaluation result. The information processing device according to claim 1 .

5. an operation state vector representing whether the object is operating for each time slot obtained by dividing a time axis by a predetermined interval; a substitute state variable vector representing whether the substitute is operating for each time slot; a time slot variable generation unit that generates a time slot variable; The objective function generation unit an objective function is generated using the alternative state variable vector as a decision variable, and having a term in which the distance between an operating state exclusive-OR vector representing the exclusive-OR of whether or not an operation is occurring in two adjacent time slots in the operating state vector and an alternative state exclusive-OR variable vector representing the exclusive-OR of whether or not an operation is occurring in two adjacent time slots in the alternative state variable vector is a deviation value representing the degree of deviation; The optimization unit identifying the alternative state variable vector that minimizes the value of the objective function subject to the constraints; The information processing device according to claim 3 .

6. the object state storage unit stores position time information that is time-series position information of the object, which is a vehicle; a route charging spot calculation unit that acquires the position and time information from the object state storage unit and calculates time information that represents a time in the position and time information that indicates a position that approximately coincides with a position indicated by route charger position information that is position information of a charging spot that can charge the storage battery; The time slot variable generation unit Generate, as the alternative state variable vectors, a driving state variable vector representing a driving state of the alternative and a route charging state variable vector representing a charging state at the charging spot; In the path charging state variable vector, the charging state of the time slot corresponding to the time information is set as a decision variable. The information processing device according to claim 5 .

7. the route charging spot calculation unit converts the location information into a hash value, and calculates time information representing a time when the hash value of the location time information and the hash value of the route charger location information match; The information processing device according to claim 6 .

8. The time slot variable generation unit generating the driving state variable vector, the route charging state variable vector, and a station charging state vector representing a charging state at a station related to the business as the alternative state variable vector; In the travel state variable vector, a travel state of a time slot corresponding to a time period during which the object is used for the business is set as a decision variable; In the station charging state vector, a charging state of a time slot corresponding to a time period during which the object is not used for the business is set as a decision variable. The information processing device according to claim 6 .

9. the objective function generation unit generates an objective function having a parameter term representing an operating cost based on an expense related to charging the storage battery and a parameter term representing a degree of the deviation; the constraint condition generation unit generates constraint conditions that define upper and lower limits of the remaining capacity of the storage battery. The information processing device according to claim 6 .

10. the output unit outputs a time series transition of the remaining capacity of the storage battery. The information processing device according to claim 9 .

11. the optimization unit optimizes a value of the objective function for each of a plurality of vehicle types as the alternatives; the output unit outputs information indicating the vehicle model with the lowest operating cost as a result of optimization. The information processing device according to claim 9 .

12. a combination generation unit that generates a plurality of combinations of vehicle types based on a plurality of vehicle types of the substitutes and the number of the target objects to be replaced with the substitutes; the optimization unit optimizes a value of the objective function for each of the plurality of combinations; the output unit outputs information indicating the combination with the lowest operating cost as a result of optimization. The information processing device according to claim 9 .

13. An information processing device that evaluates whether to replace an object that operates by means other than a storage battery with an alternative that operates by a storage battery, an objective function generation process for acquiring the object operating state information from an object state storage unit that stores object operating state information that indicates changes in the past operating state of the object, using the operating state of the substitute as a decision variable, and generating an objective function having a parameter term that indicates the degree of deviation between the operating state of the object and the operating state of the substitute; a constraint condition generation process for generating a constraint condition related to a remaining capacity of the storage battery that allows the substitute to operate; an optimization process that identifies values ​​of decision variables that optimize the value of the objective function under the constraints; an output process for outputting an evaluation result based on the result of the optimization; An information processing method that performs the above.

14. An information processing device that evaluates the replacement of an object that operates by means other than a storage battery with an alternative that operates by a storage battery, an objective function generation process for acquiring the object operating state information from an object state storage unit that stores object operating state information that indicates changes in the past operating state of the object, using the operating state of the substitute as a decision variable, and generating an objective function having a parameter term that indicates the degree of deviation between the operating state of the object and the operating state of the substitute; a constraint condition generation process for generating a constraint condition related to a remaining capacity of the storage battery that allows the substitute to operate; an optimization process that identifies values ​​of decision variables that optimize the value of the objective function under the constraints; an output process for outputting an evaluation result based on the result of the optimization; An information processing program that executes the above.

Images