Information processing system

Abstract

An information processing system capable of suppressing data degradation caused by the generation of unprocessed data and the passage of time is provided. The information processing system (1) includes a buffer unit (5), a processing unit (6), and a control unit (9). The buffer unit (5) sequentially receives data acquired by the observation terminal (2) from the observation terminal (2). The processing unit (6) sequentially processes the data received by the buffer unit (5). The control unit (9) controls an index value representing information freshness by adjusting the processing resources of the processing unit (6). The index value representing information freshness is calculated based on the elapsed time since the time when the data was acquired by the observation terminal (2).

Description

Technical Field

[0001] The present invention relates to an information processing system. Background Art

[0002] Patent Document 1 discloses an example of an information processing system. The information processing system collects data from terminals. The information processing system selects data to be sent to a data processing device from the collected data according to the load state of the data processing device.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: International Publication No. 2016 / 208354 Summary of the Invention

[0006] Problems to be Solved by the Invention

[0007] However, in the information processing system of Patent Document 1, the unselected data is not sent to the data processing device. Therefore, unprocessed data may be generated in the data processing device. When the state of the object represented by the data changes over time, the data sometimes deviates from the current state of the object as time elapses since the data was acquired. That is, the data sometimes deteriorates over time.

[0008] The present invention has been completed to solve such problems. An object of the present invention is to provide an information processing system capable of suppressing data deterioration caused by the generation of unprocessed data and the passage of time.

[0009] Means for Solving the Problems

[0010] The information processing system of the present invention includes: a buffer unit that sequentially receives data acquired by an observation terminal from the observation terminal; a processing unit that sequentially processes the data received by the buffer unit; and a control unit that controls an index value indicating information freshness by adjusting the processing resources of the processing unit, and the index value is calculated based on the elapsed time since the data was acquired by the observation terminal.

[0011] Advantages of the Invention

[0012] According to the present invention, the information processing system includes a buffer unit, a processing unit, and a control unit. The buffer unit sequentially receives data acquired by an observation terminal from the observation terminal. The processing unit sequentially processes the data received by the buffer unit. The control unit controls an index value indicating information freshness by adjusting the processing resources of the processing unit. The index value indicating information freshness is calculated based on the elapsed time since the data was acquired by the observation terminal. Thereby, it is possible to suppress data deterioration caused by the generation of unprocessed data and the passage of time. Brief Description of the Drawings

[0013] Figure 1 It is a structural diagram of the information processing system of Embodiment 1.

[0014] Figure 2 It is a diagram showing an example of the time change of AoI.

[0015] Figure 3 It is a diagram showing an example of the relationship between the utilization rate and the time average of AoI in the steady state.

[0016] Figure 4 It is a diagram showing an example of the utilization rate control performed by the control unit of Embodiment 1.

[0017] Figure 5 It is a diagram showing the hardware structure of the main part of the information processing system of Embodiment 1.

[0018] Figure 6 It is a structural diagram of the information processing system of Embodiment 2.

[0019] Figure 7 It is a diagram showing an example of the control of the index value indicating the freshness of information performed by the control unit of Embodiment 2.

[0020] Figure 8 It is a diagram showing an example of the control of the index value indicating the freshness of information performed by the control unit of Embodiment 3. Detailed Embodiments

[0021] The embodiments for implementing the present invention will be described with reference to the accompanying drawings. In each figure, the same or corresponding parts are denoted by the same reference numerals, and repeated descriptions are appropriately simplified or omitted.

[0022] Embodiment 1

[0023] Figure 1 It is a structural diagram of the information processing system of Embodiment 1.

[0024] The information processing system 1 is applied to, for example, a remote monitoring system of an elevator. The information processing system 1 includes one or more observation terminals 2, a display device 3, and a receiving terminal 4. In this example, the observation terminal 2 is a remote monitoring device provided in the elevator unit. At this time, the receiving terminal 4 is, for example, a server device provided in the information center. The elevator unit is a device including a car that moves inside a hoistway extending in the vertical direction. The remote monitoring device is a device that monitors the state of the elevator unit. The information center is a base for collecting information related to the elevator.

[0025] The observation terminal 2 is a device for acquiring data. In this example, the observation terminal 2 is a device for acquiring data representing the state of the elevator unit in which the observation terminal 2 is installed. The data acquired by the observation terminal 2 includes information on the time when the data is acquired. The observation terminal 2 is connected to the receiving terminal 4 so as to be able to output the acquired data.

[0026] The observation terminal 2 repeatedly acquires data. The acquisition interval of the data acquired by the observation terminal 2 is distributed, for example, according to an exponential distribution, a degradation distribution, an Erlang distribution, or other general distributions. Here, the acquisition interval of the data is the time from the time when data is acquired from any one of the one or more observation terminals 2 to the time when data is acquired from any one of the one or more observation terminals 2 next time. At this time, the data acquisition rate λ is the reciprocal of the average value of the data acquisition interval. The data acquisition rate λ can also be, for example, a variable value calculated based on the number of data acquisitions per unit time between the current time and the time obtained by tracing back a preset time from the current time.

[0027] The display device 3 is a device for displaying the object status of the data acquired by the observation terminal 2. In this example, the display device 3 is a device for displaying the elevator status. The display device 3 is, for example, a display device.

[0028] The receiving terminal 4 includes a buffer unit 5, a processing unit 6, an output unit 7, a first calculation unit 8, and a control unit 9.

[0029] The buffer unit 5 is a part that sequentially accepts the data output by the observation terminal 2 in sequence. The buffer unit 5 has a queue structure such as FIFO (First-In First-Out) for temporarily storing data.

[0030] The processing unit 6 is a part that sequentially processes the data accepted by the buffer unit 5. The processing by the processing unit 6 is, for example, processing for displaying the data content, processing for recording the data, or processing for extracting information from the data, etc. In this example, the processing unit 6 does not select and discard the data to be processed.

[0031] The processing resources of the processing unit 6 are variable. Here, the processing resources are, for example, computing resources. An upper limit can also be set for the processing resources of the processing unit 6. The processing unit 6 can also have, for example, a processing device with a variable operating frequency. At this time, the processing resources of the processing unit 6 are controlled, for example, by the operating frequency. At this time, the upper limit of the processing resources of the processing unit 6 is set, for example, by the operating frequency. Or, the processing unit 6 can also have, for example, multiple processing devices with different processing performances. At this time, the processing resources of the processing unit 6 are controlled, for example, by the selection of the processing device for performing the operation. At this time, the upper limit of the processing resources of the processing unit 6 is set, for example, by the processing resources of the selected processing device. Or, the processing unit 6 can also have, for example, a processing device with a variable number of cores for performing the operation. In addition, the processing unit 6 can also be clustered by multiple computers. At this time, the processing resources of the processing unit 6 are controlled, for example, by the number of cores for performing the operation. At this time, the upper limit of the processing resources of the processing unit 6 is set, for example, by the number of cores.

[0032] The service intervals of the processing by the processing unit 6 are distributed, for example, according to an exponential distribution, a degenerate distribution, an Erlang distribution, or other general distributions. Here, the service interval of the processing is the time from the moment when the processing unit 6 finishes data processing to the moment when the processing unit 6 finishes data processing next time. At this time, the service rate μ of the processing is the reciprocal of the average value of the service intervals of the processing. The service rate μ of the processing can also be, for example, a variable value calculated based on the number of processes completed per unit time between the current moment and the moment that is traced back a preset time from the current moment.

[0033] The output unit 7 is the part that outputs the processing result of the processing unit 6. The output unit 7 outputs, for example, information for displaying the data content to the display device 3.

[0034] The first calculation unit 8 is the part that calculates the acquisition rate λ of the data acquired by the observation terminal 2. In addition, the first calculation unit 8 is also the part that calculates the service rate μ of the processing by the processing unit 6. The first calculation unit 8 calculates the acquisition rate λ, for example, based on the time of acquiring the data included in the data accepted by the buffer unit 5. The first calculation unit 8 calculates the service rate μ, for example, by monitoring the time when the processing unit 6 acquires the process.

[0035] The control unit 9 is the part that controls the index value representing the freshness of information by adjusting the processing resources of the processing unit 6. The index value representing the freshness of information is calculated based on the elapsed time from the moment when the data is acquired by the observation terminal 2. The index value representing the freshness of information is, for example, a value represented by AoI (Age of Information).

[0036] Figure 2 is a diagram showing an example of the time change of AoI.

[0037] In Figure 2In this case, the horizontal axis represents time t. In Figure 2 In this case, the vertical axis represents the AoI at time t.

[0038] In this example, α i is the time when the i-th data is obtained. β i is the time when the processing of the i-th data is completed. In this example, β i is the time when the display device 3 receives the information for displaying the content of the i-th data from the output unit 7. Here, it is assumed that the time from the completion of data processing to the reception of information by the display device 3 is much shorter than the data processing time. In Figure 2 In this case, A peak,i represents the i-th peak AoI. The i-th peak AoI is the AoI immediately before the time β i when the i-th data is updated.

[0039] The AoI represents the elapsed time since the time when the latest data is obtained by the observation terminal 2. The latest data is, for example, the data whose content is displayed on the display device 3. In this example, the content displayed on the display device 3 is updated discontinuously by the completion of processing by the processing unit 6. Therefore, as Figure 2 shown, the AoI at time t is represented by a plurality of discontinuous line segments.

[0040] In this way, the AoI represents the freshness of information that deteriorates over time. The control unit 9, for example, uses the time average E[A] of the AoI in the steady state as an index value representing the freshness of information. When the receiving terminal 4 is modeled by a waiting queue model, the time average of the AoI in the steady state is obtained by the utilization rate ρ of this waiting queue model. Here, the utilization rate ρ is the value obtained by dividing the arrival rate λ by the service rate μ.

[0041] Figure 3 is a diagram showing an example of the relationship between the utilization rate and the time average of the AoI in the steady state.

[0042] In Figure 3 In this case, the horizontal axis represents the utilization rate ρ. In Figure 3 In this case, the vertical axis represents the time average E[A] of the AoI in the steady state.

[0043] In Figure 3In this case, the AoI when the receiving terminal 4 is modeled by the M / M / 1 waiting queue model and the AoI when the receiving terminal 4 is modeled by the D / M / 1 waiting queue model are shown. Here, the waiting queue model is represented by Kendall's notation. The M / M / 1 waiting queue model is a waiting queue model in which the acquisition interval of data is based on an exponential distribution, the service interval of processing is based on an exponential distribution, and the number of processing units 6 is 1. The D / M / 1 waiting queue model is a waiting queue model in which the acquisition interval of data is based on a degenerate distribution, the service interval of processing is based on an exponential distribution, and the number of processing units 6 is 1. The receiving terminal 4 can also be modeled by a waiting queue model not illustrated here.

[0044] Regarding the M / M / 1 waiting queue model, the time average E[A] of the AoI in the steady state is represented by the following equation (1).

[0045] [Equation 1]

[0046]

[0047] Regarding the D / M / 1 waiting queue model, the time average E[A] of the AoI in the steady state is represented by the following equation (2). Here, W is the Lambert W function.

[0048] [Equation 2]

[0049]

[0050] As Figure 3 shown, the change in the time average E[A] of the AoI in the steady state with respect to the utilization rate ρ when the service rate μ is given has a minimum value. In addition, the utilization rate that minimizes E[A] is determined by the waiting queue model. Thus, when setting the minimum value of E[A] as the target value of the index value representing the information freshness, the utilization rate ρ * is determined by the waiting queue model.

[0051] In addition, for example, in the case where there is an upper limit set for the processing resources of the processing unit 6 or in the case where there is a range of acceptable values for the service rate μ, the range of acceptable values of the utilization rate ρ is determined according to the acquisition rate λ. In the steady state at this time, the change in the time average E[A] of the AoI with respect to the utilization rate ρ within the range of acceptable values has a minimum value. In addition, the utilization rate that minimizes E[A] within the range of the utilization rate ρ determined according to the acquisition rate λ is determined by the waiting queue model. Thus, when setting the minimum value of E[A] corresponding to the acquisition rate λ as the target value of the index value representing the information freshness, the utilization rate ρ * is determined by the waiting queue model.

[0052] The control unit 9 adjusts the service rate μ by adjusting the processing resources of the processing unit 6 so that the utilization rate ρ obtained from the acquisition rate λ calculated by the first calculation unit 8 and the service rate μ becomes the utilization rate ρ corresponding to the target value of the index value indicating the information freshness. * 。

[0053] Figure 4 FIG. is an example of the utilization rate control performed by the control unit according to Embodiment 1.

[0054] In Figure 4 , the horizontal axis represents the time t. In Figure 4 , the vertical axis represents the utilization rate ρ obtained from the acquisition rate λ calculated by the first calculation unit 8 and the service rate μ. In Figure 4 , the utilization rate ρ corresponding to the target value of the index value indicating the information freshness * is represented by a dotted line.

[0055] The control unit 9 outputs a control signal for adjusting the resources to the processing unit 6. The control unit 9 controls the adjustment amount of the resources by, for example, PID (Proportional-Integral-Differential) control or the like. Alternatively, the control unit 9 can also control the adjustment amount of the resources by, for example, reinforcement learning. At this time, the reward of the reinforcement learning is calculated according to the value of the service rate μ, for example. Alternatively, the reward of the reinforcement learning can also be calculated based on the deviation between the target value ρ of the utilization rate determined according to the acquisition rate λ and the utilization rate ρ calculated by the first calculation unit 8. * and the utilization rate ρ calculated by the first calculation unit 8.

[0056] As described above, the information processing system 1 according to Embodiment 1 includes a buffer unit 5, a processing unit 6, and a control unit 9. The buffer unit 5 sequentially receives the data acquired by the observation terminal 2 from the observation terminal 2. The processing unit 6 sequentially processes the data received by the buffer unit 5. The control unit 9 controls the index value indicating the information freshness by adjusting the processing resources of the processing unit 6. The index value indicating the information freshness is calculated based on the elapsed time since the data was acquired by the observation terminal 2.

[0057] The control unit 9 controls the index value indicating the information freshness by adjusting the processing resources of the processing unit 6. The data received by the buffer unit 5 is sequentially processed by the processing unit 6. Therefore, the generation of unprocessed data can be suppressed. In addition, the deterioration of the data due to the passage of time can be suppressed. Therefore, the information processing system 1 can also be applied to a system such as a remote monitoring system for an elevator, etc., which preferably does not select or discard the acquired data.

[0058] In addition, the information processing system 1 has a first calculation unit 8. The first calculation unit 8 calculates the acquisition rate λ of the data acquired by the observation terminal 2. The first calculation unit 8 calculates the service rate μ of the processing by the processing unit 6. The relationship between the utilization rate ρ obtained by dividing the acquisition rate λ by the service rate μ and the index value is determined in advance by a waiting queue model. At this time, the control unit 9 controls the service rate μ by adjusting the processing resources of the processing unit 6 so that the utilization rate ρ calculated from the acquisition rate λ and the service rate μ calculated by the first calculation unit 8 becomes the utilization rate ρ corresponding to the target value of the index value. * The target value of the index value is a value determined in advance based on the acquisition rate λ and the waiting queue model.

[0059] The relationship between the target value of the index value and the utilization rate ρ is determined by the waiting queue model. Therefore, the target value ρ of the utilization rate for making the index value the target value corresponding to the acquisition rate λ is determined. * The acquisition rate λ, the service rate μ, and the utilization rate ρ are values that can be calculated successively according to the status of data acquisition and processing. Therefore, the control unit 9 can calculate the control amount of the service rate μ based on the utilization rate ρ so that the index value becomes the target value. In addition, in the calculation of the acquisition rate λ, the service rate μ, and the utilization rate ρ, the first calculation unit 8 does not need to set individual parameters for each data. Therefore, the information processing system 1 can be widely applied to systems that can be modeled by a waiting queue model.

[0060] In addition, the target value of the index value based on the acquisition rate λ and the waiting queue model can also be determined by a penalty function, for example. The penalty function is, for example, a function that takes a larger value as the service rate μ increases. The penalty function can be, for example, a linear function, a power function, a step function, an exponential function, or a monotonically increasing function based on a combination of these functions. At this time, the target value of the index value can also be set such that the sum of the time average E[A] of AoI and the penalty function is minimized. That is, the utilization rate ρ corresponding to the target value at this time * is the utilization rate calculated from the acquisition rate λ and the service rate μ that minimize the sum of the time average E[A] of AoI and the penalty function.

[0061] In addition, the observation terminal 2 can also be each sensor provided in the elevator unit. In this case, the receiving terminal 4 is, for example, a remote monitoring device provided in the unit. In this case, the processing unit 6 of the receiving terminal 4, for example, performs processing to convert the collected sensor data into a form that can be used in the remote monitoring of the unit. The output unit 7 of the receiving terminal 4, for example, sends the processing result of the processing unit 6 to the server device of the information center.

[0062] In addition, the information processing system 1 can also be applied to systems that repeatedly acquire data, such as escalators or other building equipment, for example.

[0063] Next, use Figure 5An example of the hardware configuration of the information processing system 1 will be described.

[0064] Figure 5 This is a diagram showing the hardware configuration of a main part of the information processing system according to the first embodiment.

[0065] Each function of the information processing system 1 can be realized by a processing circuit. The processing circuit has at least one processor 1b and at least one memory 1c. The processing circuit may have at least one dedicated hardware 1a together with or instead of the processor 1b and the memory 1c.

[0066] When the processing circuit has a processor 1b and a memory 1c, each function of the information processing system 1 is implemented by software, firmware, or a combination of software and firmware. At least one of the software and firmware is referred to as a program. The program is stored in the memory 1c. The processor 1b reads and executes the program stored in the memory 1c, thereby implementing each function of the information processing system 1.

[0067] The processor 1b is also called a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP. The memory 1c is composed of, for example, a RAM, a ROM, a flash memory, an EPROM, an EEPROM, or other nonvolatile or volatile semiconductor memory, a magnetic disk, a floppy disk, an optical disk, a high-density disk, a mini disk, a DVD, or the like.

[0068] In the case where the processing circuit has dedicated hardware 1a, the processing circuit is implemented by, for example, a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0069] Each function of the information processing system 1 can be realized by a processing circuit separately. Alternatively, each function of the information processing system 1 can also be realized by a processing circuit in a unified manner. Regarding each function of the information processing system 1, a part can be realized by dedicated hardware 1a, and another part can be realized by software or firmware. In this way, the processing circuit realizes each function of the information processing system 1 through hardware 1a, software, firmware or a combination thereof.

[0070] Implementation Method 2

[0071] In Embodiment 2, differences from the example disclosed in Embodiment 1 are described in detail. With regard to features not described in Embodiment 2, any features of the example disclosed in Embodiment 1 can be adopted.

[0072] Figure 6 This is a structural diagram of the information processing system according to the second embodiment.

[0073] The receiving terminal 4 of Embodiment 2 has a second calculation unit 10.

[0074] The second calculation unit 10 is a part that calculates an index value indicating the freshness of information based on the elapsed time since the time when data is acquired from the observation terminal 2.

[0075] The second calculation unit 10 uses, for example, the moving average MA[A] of AoI as the index value indicating the freshness of information. The moving average is the time average between the current time and the time that is set in advance and traced back from the current time. Alternatively, the second calculation unit 10 may use the average value of the peak AoI between the current time and the time that is set in advance and traced back from the current time as the index value indicating the freshness of information. Here, the smaller the value of AoI, the higher the freshness of the information. That is, the moving average MA[A] of AoI and the average value of the peak AoI are examples of index values where the smaller the value, the higher the freshness of the information.

[0076] Figure 7 It is a diagram showing an example of the index value control indicating the freshness of information performed by the control unit of Embodiment 2.

[0077] In Figure 7 the horizontal axis represents the time t. In Figure 7 the vertical axis represents the index value of the freshness of information. In this example, the smaller the index value, the higher the freshness of the information.

[0078] The control unit 9 adjusts the processing resources of the processing unit 6 to reduce the index value calculated by the second calculation unit 10. The control unit 9 outputs a control signal for adjusting the resources to the processing unit 6. The control unit 9 controls the adjustment amount of the resources by, for example, reinforcement learning. At this time, the reward of the reinforcement learning is calculated based on the index value, for example. For example, when the index value is the moving average MA[A] of AoI, the reward of the reinforcement learning is a value calculated in such a way that the smaller the moving average MA[A], the higher the value. Alternatively, the control unit 9 may adjust the resources of the processing unit 6 by PID control or the like.

[0079] As described above, the information processing system 1 of Embodiment 2 has a second calculation unit 10. The second calculation unit 10 calculates an index value indicating the freshness of information based on the elapsed time since the time when data is acquired from the observation terminal 2. The control unit 9 adjusts the processing resources of the processing unit 6 to increase the freshness of the information indicated by the index value calculated by the second calculation unit 10.

[0080] The control unit 9 does not require the target value of the metric value based on the waiting queue model. Therefore, the information processing system 1 can also be applied to a system that is not modeled by the waiting queue model. In addition, when the model of the system changes dynamically, the control unit 9 can also adjust the processing resources of the processing unit 6 following the changed model.

[0081] Embodiment 3

[0082] In Embodiment 3, the differences from the examples disclosed in Embodiment 1 or Embodiment 2 are described in detail. Regarding the features not described in Embodiment 3, any features of the examples disclosed in Embodiment 1 or Embodiment 2 can be adopted.

[0083] Figure 8 It is a diagram showing an example of the control of the metric value indicating the information freshness performed by the control unit of Embodiment 3.

[0084] In Figure 8 , the horizontal axis represents the time t. In Figure 8 , the vertical axis represents the metric value of the information freshness. In this example, the smaller the metric value, the higher the information freshness.

[0085] In Figure 8 , the target value of the metric value calculated by the second calculation unit 10 is indicated by a dashed line. The metric value is set in advance. The metric value of the information freshness is, for example, the moving average MA[A] of AoI. Here, the target value of the metric value can also be a value larger than the minimum value that the metric value can take. The target value of the metric value is, for example, set in advance to maintain the necessary information freshness.

[0086] The control unit 9 adjusts the processing resources of the processing unit 6 so that the metric value calculated by the second calculation unit 10 becomes the target value. The control unit 9 outputs a control signal for adjusting the resources to the processing unit 6. The control unit 9 controls the adjustment amount of the resources, for example, by PID control or the like. Or, the control unit 9 can also control the adjustment amount of the resources, for example, by reinforcement learning. At this time, the reward of the reinforcement learning is calculated, for example, based on the deviation between the calculated value and the target value of the metric value.

[0087] As described above, the information processing system 1 of Embodiment 3 has a second calculation unit 10. The second calculation unit 10 calculates a metric value indicating the information freshness based on the elapsed time since the time when data is obtained from the observation terminal 2. The control unit 9 adjusts the processing resources of the processing unit 6 so that the metric value calculated by the second calculation unit 10 becomes a predetermined target value.

[0088] Accordingly, the control unit 9 does not increase the index value of information freshness to a level higher than necessary. Therefore, the processing resources of the processing unit 6 are not allocated to data processing to a degree higher than necessary. For example, when the processing unit 6 also performs other processing in addition to the processing of data received by the buffer unit 5, the resources of the processing unit 6 are not allocated to the data processing of the buffer unit 5 to a degree higher than necessary.

[0089] Industrial Applicability

[0090] The information processing system of the present invention can be applied to the processing of sequentially acquired data.

[0091] Reference Signs Explanation

[0092] 1: Information processing system; 2: Observation terminal; 3: Display device; 4: Receiving terminal; 5: Buffer unit; 6: Processing unit; 7: Output unit; 8: First calculation unit; 9: Control unit; 10: Second calculation unit; 1a: Hardware; 1b: Processor; 1c: Memory.

Claims

1. An information processing system, the information processing system having: a buffer unit that sequentially receives data acquired by the observation terminal from the observation terminal; a processing unit that sequentially processes the data received by the buffer unit; and a control unit that controls an index value indicating information freshness by adjusting the processing resources of the processing unit, the index value being calculated based on the elapsed time since the time when the data is acquired by the observation terminal; the information processing system further has a first calculation unit that calculates an acquisition rate at which the observation terminal acquires data and a service rate of the processing by the processing unit, when the control unit determines the relationship between the utilization rate obtained by dividing the acquisition rate by the service rate determined in advance by a waiting queue model and the index value, the control unit controls the service rate by adjusting the processing resources of the processing unit so that the utilization rate calculated based on the acquisition rate and the service rate calculated by the first calculation unit becomes a utilization rate corresponding to a target value of the index value determined in advance based on the acquisition rate and the waiting queue model.

2. The information processing system according to claim 1, wherein, the information processing system further has a second calculation unit that calculates the index value based on the elapsed time, the control unit adjusts the processing resources of the processing unit to increase the information freshness indicated by the index value calculated by the second calculation unit.

3. The information processing system according to claim 1, wherein, the information processing system further has a second calculation unit that calculates the index value based on the elapsed time, the control unit adjusts the processing resources of the processing unit so that the index value calculated by the second calculation unit becomes a predetermined target value.

Images