Control device, control program, and control method

Abstract

The present invention makes it possible to more efficiently utilize data center resources.　A control device (1) is for allocating processing of data for which a request has been received to any of a plurality of data centers (3) and comprises a selection unit that refers to required-power information indicating power consumption required for the processing and power consumption information representing, in processing units, the current power consumption of each processing device provided in each of the plurality of data centers, and selects, from among the plurality of data centers, a data center including a processing device for which power consumption upon execution of the processing will not exceed the maximum power consumption thereof.

Description

Control device, control program, and control method

[0001] The present disclosure relates to a control device, a control program, and a control method.

[0002] Conventionally, for example, an image processing apparatus as described in Patent Document 1 is known.

[0003] Japanese Unexamined Patent Publication No. 2012-105067

[0004] A control device according to an aspect of the present disclosure is a control device for allocating processing of requested data to any one of a plurality of data centers, the control device comprising: a selection unit that selects, from among the plurality of data centers, a data center including a processing device whose power consumption does not exceed the maximum power consumption when the processing is executed, with reference to required power information indicating power consumption required for the processing and power consumption information representing current power consumption of each processing device provided in each of the plurality of data centers in processing units.

[0005] A control program according to another aspect of the present disclosure is a control program that causes a computer to execute processing for allocating processing of requested data to any one of a plurality of data centers, the control program causing the computer to execute: a selection step of selecting, from among the plurality of data centers, a data center including a processing device whose power consumption does not exceed the maximum power consumption when the processing is executed, with reference to required power information indicating power consumption required for the processing and power consumption information representing current power consumption of each processing device provided in each of the plurality of data centers in processing units.

[0006] A control method according to another aspect of the present disclosure is a control method for a processor of a computer to allocate processing of requested data to any one of a plurality of data centers, the control method comprising: a selection step of selecting, from among the plurality of data centers, a data center including a processing device whose power consumption does not exceed the maximum power consumption when the processing is executed, with reference to required power information indicating power consumption required for the processing and power consumption information representing current power consumption of each processing device provided in each of the plurality of data centers in processing units.

[0007] This is a block diagram showing an example of the schematic configuration of an information processing system equipped with a control device 1 according to the present disclosure. This is a block diagram showing an example of the functional configuration of the control device according to the same embodiment. This is a flowchart showing an example of the processing flow executed by

[0008] <Background, Problems, Solutions, and Principles of Solution> Before describing the embodiments of this disclosure, the background of this disclosure, the problems of the prior art, the means of solving the problems, and the principles of solution by the solutions will be explained.

[0009] [Background] When requesting various AI-based processes from data centers, instead of supplying power to the data center that will actually perform the processing, it is common practice to request the processing from a data center that has surplus power.

[0010] [Problem] Until now, power consumption required for processing could only be measured on a per-server basis. As a result, if a server in a data center was performing a light, low-power process, that server would be considered "in use." In other words, previously, unless there was at least one server that was not performing any processing, the data center would not be considered free, and it was sometimes impossible to request processing.

[0011] [Solution] To solve the above problems, a control device according to one aspect of the present disclosure refers to required power information indicating the power consumption required for processing, and power consumption information representing the current power consumption of each processing unit in each of the multiple data centers. The control device then selects from among the multiple data centers a data center equipped with a processing unit whose power consumption when processing is performed does not exceed the maximum power consumption.

[0012] [Solution Principle] The control device according to this disclosure can grasp the power consumption required for processing and the current power consumption of each processing unit in each of the multiple data centers on a processing unit basis. Therefore, the control device determines that there is available capacity in the data center as long as the power consumption of the data center is lower than the maximum power consumption by the amount of power consumption required for processing. In this way, the control device according to this disclosure can request processing from processing units that are already performing processing, depending on their power consumption. As a result, the resources of the data center can be used more efficiently.

[0013] <Embodiment> Next, an embodiment of the present disclosure will be described in detail with reference to the drawings. The present disclosure relates to a technology that provides highly immediate services with low latency to users and devices around a base station by utilizing the computing infrastructure of the base station. In this technology, by deploying AI (Artificial Intelligence) and machine learning technology applications at the network edge through a RAN (Radio Access Network), the creation of new industries and solutions that leverage low latency and confidentiality is promoted. Furthermore, the functions of the base station (RAN) may be realized as vRAN (virtualized RAN). For example, RUs (Radio Units) may be installed at multiple sites as devices that process the antenna portion and the lowest layer of the PHY layer of the base station, and the modulation and demodulation of signals and the retransmission of lost signals may be controlled by DUs (Distributed Units) located in data centers, etc. Furthermore, a RIC (RAN Intelligent Controller) that controls the operation of the RUs and DUs may be provided in the data center, etc.

[0014] [Outline Configuration of Information Processing System 100] First, an information processing system 100 equipped with a control device 1 according to the embodiment of this disclosure will be described. Figure 1 is a block diagram showing an example of the outline configuration of the information processing system 100 according to the embodiment.

[0015] As shown in Figure 1, the information processing system 100 includes a control device 1, a database 2, multiple data centers 3, a storage device 4, and a receiving device 5. The control device 1 and the database 2 are connected to each other via wired or wireless means so that they can communicate with one another. The control device 1 and the multiple data centers 3 are also connected to each other via wired or wireless means so that they can communicate with one another. Furthermore, the control device 1 and the storage device 4, and the control device 1 and the receiving device 5 are also connected to each other via wired or wireless means so that they can communicate with one another. Wireless communication includes communication via a base station (cellular communication). In addition, the information processing system 100 (control device 1) does not necessarily have to include at least one of the multiple data centers 3, the storage device 4, and the receiving device 5.

[0016] [Data Center 3] Multiple data centers 3 are equipped with at least one processing unit 31 (server). Each data center 3 processes data using the processing unit 31. "Processing" includes image processing, building trained models (including fine tuning), and prediction and information generation using trained models. Each data center 3 may differ in processing capacity, the maximum amount of power it can receive, and the power source (e.g., thermal power plant, wind power plant, solar power plant). In addition, each data center 3's processing unit 31 measures its current power consumption on a processing unit (container unit) basis. Specifically, the processing unit 31 measures the usage of the installed processor (resource) as power consumption. For example, if the processor usage is 10% of the maximum usage, the processing unit 31 equipped with that processor will measure its power consumption as 10%.

[0017] [Control device 1] Control device 1 is a device for assigning the processing of data received as a request to one of the multiple data centers 3. Details of control device 1 will be described later.

[0018] [Database 2] Database 2 stores performance information. "Performance information" is information indicating the power consumption when the processing unit 31 performed processing in the past. Database 2 in this embodiment stores at least one of result information and statistical information. "Result information" is information indicating the results when processing was performed in the data center 3 in the past. "Statistical information" is information that the control device 1, described later, uses to determine the relationship between parameters and performance information. Database 2 may be integrated with the control device 1.

[0019] [Storage device 4] Storage device 4 stores the data to be processed. Note that storage device 4 may be integrated with control device 1.

[0020] [Reception Device 5] The reception device 5 is configured to receive processing requests from users. When the reception device 5 receives a processing request, it transmits the request information to the control device 1. The request information includes at least one of the following: requester identification information, processing identification information, type information, time information, quantity information, delay information, source code, location information, and priority information. "Requester identification information" is information that identifies the person who requested the processing (e.g., name). "Processing identification information" is information that identifies the processing to be executed (e.g., ID). "Type information" is information that indicates the content of the processing to be executed (e.g., inference, fine tuning, etc.). "Time information" is information that indicates the maximum time that can be spent on the processing. "Quantity information" is information that indicates the number of processors to be used for processing. "Delay information" is information that indicates the maximum allowable delay time in processing. "Location information" is information that specifies the data center 3 where the processing will be executed. "Priority information" is information that indicates the priority level of the processing for which the request was received. The request information may include at least one of the following: source code, model information, size information, and method information. The source code may include parameters used to execute the processing. The receiving device 5 may be integrated with the control device 1. The receiving device 5 may also be integrated with the storage device 4.

[0021] [Control device 1] Next, a specific configuration of the control device 1 according to the embodiment of this disclosure will be described. Figure 2 is a block diagram showing an example of a specific configuration of the control device 1 according to the embodiment.

[0022] [Configuration of Control Device 1] As shown in Figure 2, the control device 1 comprises a communication unit 11, a storage unit 12, and an arithmetic unit 13.

[0023] (Communication Unit 11) The communication unit 11 communicates with the database 2 via wired or wireless connection. The communication unit 11 also communicates with each data center 3 via wired or wireless connection. Furthermore, the communication unit 11 communicates with the storage device 4 and the receiving device 5. In this embodiment, the communication unit 11 is composed of a communication module.

[0024] (Storage Unit 12) The storage unit 12 stores the control program 121. The control program 121 is a program that causes the computer to function as the control device 1. In this embodiment, the storage unit 12 is composed of a semiconductor memory (e.g., a Solid State Drive: SSD), a hard disk drive (HDD), etc. The storage unit 12 may also be configured to store various calculation results from the arithmetic unit 13.

[0025] (Calculation Unit 13) The calculation unit 13 comprises an allocation unit 131, a pre-allocation processing unit 132, and a post-allocation processing unit 133. The calculation unit 13 according to this embodiment consists of a processor and memory. In other words, the control device 1 is composed of a computer.

[0026] - Pre-allocation processing unit 132 The pre-allocation processing unit 132 is for obtaining required power information. "Required power information" is information indicating the power consumption required for processing. The pre-allocation processing unit 132 includes a request acquisition unit 132a, a first judgment unit 132b, a prediction unit 132c, a second judgment unit 132d, a first information acquisition unit 132e, a third judgment unit 132f, and a second information acquisition unit 132g. As described above, the arithmetic unit 13 according to this embodiment is composed of a processor and memory. Therefore, the functions of each control block 132a to 132g are realized when the arithmetic unit 13 executes the pre-allocation step S12 in the flow shown in Figure 3 according to the control program 121 stored in the storage unit 12.

[0027] Request Acquisition Step S12a, Request Acquisition Unit 132a In the initial request acquisition step S12a, the request acquisition unit 132a acquires request information indicating the content of the received request. In the request acquisition step S12a according to this embodiment, the request acquisition unit 132a acquires the request information received by the communication unit 11.

[0028] First Decision Step S12b, First Decision Unit 132b After the Request Acquisition Step S12a, the process moves to the First Decision Step S12b. In the First Decision Step S12b, the First Decision Unit 132b determines whether or not the request information includes type information.

[0029] Prediction step S12c, prediction unit 132c If the first determination unit 132b determines in the first determination step S12b that the request information includes type information (S12b: YES), the process proceeds to prediction step S12c. In prediction step S12c, the prediction unit 132c predicts the power consumption required for the processing for which the request was received, based on the request information, as required power information.

[0030] Second Decision Step S12d, Second Decision Unit 132d If the First Decision Unit 132b determines in the First Decision Step S12b that the request information does not contain type information (S12b: NO), the process moves to the Second Decision Step S12d. In the Second Decision Step S12d, the Second Decision Unit 132d determines whether or not performance information corresponding to the request information is stored in the database 2. "Performance information" is information on power consumption when processing was performed in the data center 3 in the past.

[0031] In the first information acquisition step S12e, the first information acquisition unit 132e determines in the second judgment step S12d that actual data information corresponding to the request information is stored in the database 2 (S12d: YES), then the process proceeds to the first information acquisition step S12e. In the first information acquisition step S12e, the first information acquisition unit 132e acquires actual data information on power consumption from past processing at the data center as required power information, based on the request information.

[0032] Third Decision Step S12f, Third Decision Unit 132f If the second decision unit 132d determines in the second decision step S12d that no performance information corresponding to the request information is stored in the database 2 (S12d: NO), the process moves to the third decision step S12f. In the third decision step S12f, the third decision unit 132f determines whether or not the request information contains parameters. If the third decision unit 132f determines that the request information does not contain parameters (S12f: NO), the process moves to the allocation unit 131, which will be described later.

[0033] In the second information acquisition step S12g, the second information acquisition unit 132g determines in the third judgment step S12f that the requested information includes parameters (S12f: YES), and proceeds to the second information acquisition step S12g. In the second information acquisition step S12g, if there is no actual power consumption information from when the processing was performed, the second information acquisition unit 132g acquires the actual power information that has the highest relationship with the parameters from among multiple actual power information sources as the required power information.

[0034] - Assignment Unit 131 As shown in Figure 2, the assignment unit 131 includes a selection unit 131a. The assignment unit 131 according to this embodiment further includes a fourth determination unit 131b, a processing order determination unit 131c, a status acquisition unit 131d, a ranking unit 131e, and an assignment instruction unit 131f. As described above, the arithmetic unit 13 according to this embodiment is composed of a processor and memory. Therefore, the functions of each control block 131a to 131c are realized when the arithmetic unit 13 executes the assignment step S11 in the flow shown in Figure 4 according to the control program 121 stored in the storage unit 12.

[0035] Fourth Decision Step S11b, Fourth Decision Unit 131b In the first fourth decision step S11b, the fourth decision unit 131b determines whether or not there is required power information. If the fourth decision unit 131b determines that there is required power information (S11b: YES), the process proceeds to the selection step S11a (S114) described later.

[0036] Processing Order Determination Step S11c, Processing Order Determination Unit 131c If the fourth determination unit 131b determines that there is required power information in the fourth determination step S11b (S11b: YES), the process proceeds to the processing order determination step S11c. In the processing order determination step S11c, the processing order determination unit 131c refers to the priority information contained in each of the multiple request information and determines the order in which each request corresponds (the order in which the data is processed).

[0037] Status acquisition step S11d, status acquisition unit 131d The status acquisition step S11d is performed before the selection step S11a. In the status acquisition step S11d, the status acquisition unit 131d acquires various status information from the data center 3. The "status information" includes power consumption information. The "power consumption information" is information that represents the current power consumption of each processing unit in each of the multiple data centers, on a processing unit basis. In the status acquisition step S11d according to this embodiment, the status information acquired by the status acquisition unit 131d further includes at least one of the power supply information, resource status information, and termination information. The "power supply information" is information that indicates the power that can be supplied to each of the multiple data centers. The "resource status information" is information that indicates the usage status of the processors in each data center 3. The "termination information" is information that indicates the predicted time of termination of the processing being performed by each processing unit 31, or the time remaining until termination.

[0038] Ranking step S11e, Ranking unit 131e After the status acquisition step S11d, the process moves to ranking step S11e. In ranking step S11e, the ranking unit 131e creates a ranking of data centers 3 that should process the data determined by the processing order determination unit 131c in the processing order determination step S11c (information indicating the order of suitability of each data center 3 to the request content), based on the status information.

[0039] Selection step S11a, Selection unit 131a After the processing order determination step S11c, the process moves to selection step S11a. In selection step S11a, the selection unit 131a refers to the required power information and the power consumption information to select a data center. In selection step S11a according to this embodiment, the selection unit 131a further refers to the request information to select the data center. Specifically, the selection unit 131a first determines whether the request information includes location information (S111). If it is determined that the request information includes location information (S111: YES), the selection unit 131a refers to the required power information and the current power consumption information of the processing unit 31 provided by the data center 3 indicated by the location information. In selection step S11a after the prediction step S12c, the selection unit 131a refers to the predicted value. On the other hand, in the selection step S11a, which has gone through the first information acquisition step S12e or the second information acquisition step S12g, the selection unit 131a refers to the actual information. Then, in the selection step S11a, the selection unit 131a determines whether the power consumption when the processing unit 31 of the data center 3 specified by the location information performs processing exceeds the maximum power consumption (S112). "Maximum power consumption" is the power consumption when the processing unit 31 is operating at its maximum capacity. If it is determined that the power consumption does not exceed the maximum power consumption (S112: NO), the selection unit 131a selects the data center 3 indicated by the location information (S114). If it is determined that the power consumption exceeds the maximum power consumption (S112: YES), the process proceeds to the allocation instruction step S11f, which will be described later.

[0040] On the other hand, in S111, if it is determined that the request information does not include location information (S111: NO), the selection unit 131a refers to the required power information and the current power consumption information of the processing unit 31 installed in each data center listed in the ranking. Then, in the selection step S11a, the selection unit 131a determines whether the power consumption of the processing unit 31 installed in the highest-ranked data center 3 exceeds the maximum power consumption when it performs processing (S113). If it is determined that the power consumption exceeds the maximum power consumption, the selection unit 131a then determines whether the power consumption of the next highest-ranked data center 3 exceeds the maximum power consumption. If it is determined that the power consumption does not exceed the maximum power consumption (S113: NO), the selection unit 131a selects the data center 3 in the ranking for which it was determined whether the power consumption exceeds the maximum power consumption (S114). If it is determined that the power consumption of the processing unit 31 installed in the lowest-ranked data center 3 exceeds the maximum power consumption when it performs processing (S113: NO), the process proceeds to the allocation instruction step S11f, which will be described later.

[0041] If the fourth determination unit 131b determines in the fourth determination step S11b that there is information regarding the required power (S11b: YES), then in S114, an available data center 3 is selected.

[0042] Assignment instruction step S11f, Assignment instruction unit 131f After selection step S11a, the process moves to assignment instruction step S11f. In assignment instruction step S11f, which follows S115, the assignment instruction unit 131f sends a signal to the storage device 4 instructing it to send data to the selected data center 3. Also in assignment instruction step S11f, the assignment instruction unit 131f sends a signal to the selected data center 3 instructing it to start processing the data. The data to be processed is then sent from the storage device 4 to the selected data center 3. The data center 3, having received the data, starts processing it using the processing unit 31. On the other hand, in assignment instruction step S112 or when NO is determined in S112, the assignment instruction unit 131f notifies the user that, for example, it was not possible to assign data center 3.

[0043] ・Post-allocation processing unit 133 The post-allocation processing unit 133 includes a result acquisition unit 133a, a creation unit 133b, an update instruction unit 133c, and a calculation unit 133d. As described above, the arithmetic unit 13 according to the present embodiment is configured by a processor and a memory. Therefore, the functions of the respective control blocks 133a to 133d are realized by the arithmetic unit 13 executing the post-allocation step S13 according to the flow shown in FIG. 5 in accordance with the control program 121 stored in the storage unit 12.

[0044] Result acquisition step S13a, result acquisition unit 133a The initial result acquisition step S13a is a step executed when the data center 3 completes processing. In the result acquisition step S13a, the result acquisition unit 133a acquires result information indicating a processing result from the data center 3 that has executed the processing.

[0045] Creation step S13b, creation unit 133b After the result acquisition step S13a, the process proceeds to the creation step S13b. In the creation step S13b, the creation unit 133b creates statistical information for determining a relationship based on the result information.

[0046] Update instruction step S13c, update instruction unit 133c After the result acquisition step S13a or the creation step S13b, the process proceeds to the update instruction step S13c. In the update instruction step S13c, the update instruction unit 133c instructs the database 2 to update the content. Specifically, the update instruction unit 133c transmits at least one of the result information and the performance information to the database 2 together with a signal instructing to update the content. The database 2 that has received the signal accumulates at least one of the received result information and performance information.

[0047] Calculation step S13d, calculation unit 133d After the result acquisition step S13a, the process proceeds to the calculation step S13d. In the calculation step S13d, the calculation unit 133d calculates a fee to be charged to the processing requester based on priority information and the result information, further comprising:

[0048] [Operational effects of control device 1] The control device 1 described above refers to required power information and power consumption information. In selection step S11a, a selection unit 131a selects, from among a plurality of data centers 3, a data center 3 that includes a processing device 31 whose power consumption does not exceed the maximum power consumption when the processing is executed. Therefore, according to the control device 1, resources of the data centers 3 can be used more efficiently.

[0049] <Modification> The present disclosure is not limited to the embodiments described above, and various modifications can be made within the scope recited in the claims.

[0050] For example, the above control program is not temporary, and may be recorded in one or more computer-readable recording media. This recording medium may or may not be provided in each unit. In the latter case, the above control program may be supplied to each unit via any wired or wireless transmission medium.

[0051] In addition, some or all of the functions of the control blocks 131a to 131c, 132a to 132g, and 133a to 133d included in the arithmetic unit 13 may be implemented by logic circuits. For example, an integrated circuit formed with a logic circuit that functions as each of the control blocks 131a to 131c, 132a to 132g, and 133a to 133d is also included in the scope of the present disclosure. In addition, it is also possible to implement the functions of the control blocks 131a to 131c, 132a to 132g, and 133a to 133d by, for example, a quantum computer.

[0052] [Summary] The control device according to aspect 1 of the present invention is a control device for assigning the processing of data received as a request to one of a plurality of data centers, and includes a selection unit that refers to required power information indicating the power consumption required for the processing and power consumption information representing the current power consumption of each processing unit in each of the plurality of data centers in a processing unit, and selects a data center among the plurality of data centers that has a processing unit in which the power consumption when the processing is executed does not exceed the maximum power consumption. The control device according to aspect 2 of the present invention is further comprising a request acquisition unit that acquires request information indicating the content of the received request in aspect 1 above, and the selection unit may further refer to the request information to select the data center. The control device according to aspect 3 of the present invention is further comprising a request acquisition unit that acquires request information indicating the content of the received request in aspect 1 above, and the selection unit may further refer to the request information to select the data center. A control device according to aspect 4 of the present invention may further include a prediction unit that predicts the power consumption required for the requested processing based on the request information, as the required power information, in the above-described aspect 2. A control device according to aspect 5 of the present invention may further include a first information acquisition unit that acquires actual power consumption information from when the processing was performed in the data center in the past, as the required power information, based on the request information, and the selection unit may refer to the actual information as the required power information. A control device according to aspect 6 of the present invention may further include a second information acquisition unit that, in the above-described aspect 5, if the request information includes parameters used to execute the processing and there is no actual power consumption information from when the processing was performed, acquires the actual information from among a plurality of actual information that has the highest relationship with the parameters as the required power information.A control device according to aspect 7 of the present invention may further include, in aspect 6 above, a result acquisition unit that acquires result information indicating the result of processing from the data center that performed the processing, and a creation unit that creates statistical information for determining the relationship based on the result information. A control device according to aspect 8 of the present invention may further include, in aspect 2 above, a result acquisition unit that acquires result information indicating the result of processing from the data center that performed the processing, and a calculation unit that calculates the fee to be charged to the requester for the processing based on the priority information and the result information. A control program according to aspect 9 of the present invention is a control program that causes a computer to execute processing to assign the processing of data for which a request has been received to one of a plurality of data centers, and is configured to execute a selection step that refers to required power information indicating the power consumption required for the processing and power consumption information that expresses the current power consumption of each processing unit in each of the plurality of data centers in terms of processing unit, and selects a data center among the plurality of data centers that has a processing unit in which the power consumption when the processing is performed does not exceed the maximum power consumption. A control method according to aspect 10 of the present invention is a control method for a computer processor to assign the processing of data for which a request has been received to one of a plurality of data centers, and includes a selection step of referring to required power information indicating the power consumption required for the processing and power consumption information representing the current power consumption of each processing unit in each of the plurality of data centers, and selecting a data center among the plurality of data centers that has a processing unit in which the power consumption when the processing is performed does not exceed the maximum power consumption.

[0053] 100 Information Processing System 1 Control Device 2 Database 3 Data Center 31 Processing Unit 4 Storage Device 5 Reception Device 11 Communication Unit 12 Memory Unit 13 Calculation Unit 121 Control Program 131 Assignment Unit 131a Selection Unit 131b Fourth Decision Unit 131c Processing Order Determination Unit 131d Status Acquisition Unit 131e Ranking Unit 131f Assignment Instruction Unit 132 Pre-Assignment Processing Unit 132a Request Acquisition Unit 132b First Decision Unit 132c Prediction Unit 132d Second Decision Unit 132e First Information Acquisition Unit 132f Third Decision Unit 132g Second Information Acquisition Unit 133 Post-Assignment Processing Unit 133a Result Acquisition Unit 133b Creation Unit 133c Update Instruction Unit 133d Calculation Unit S11 Assignment Step S11a Selection Step S11b Fourth Decision Step S11c Processing Order Determination Step S11d Status Acquisition Step S11e Ranking Step S11f Assignment Instruction Step S12 Pre-Assignment Step S12a Request Acquisition Step S12b First Decision Step S12c Prediction Step S12d Second Decision Step S12e First Information Acquisition Step S12f Third Decision Step S12g Second Information Acquisition Step S13 Post-Assignment Step S13a Result Acquisition Step S13b Creation Step S13c Update Instruction Step S13d Calculation Step

Claims

1. A control device for assigning the processing of data received as a request to one of several data centers, comprising a selection unit that refers to required power information indicating the power consumption required for the processing and power consumption information representing the current power consumption of each processing unit in each of the several data centers, and selects a data center among the several data centers that has a processing unit whose power consumption when the processing is performed does not exceed the maximum power consumption.

2. The control device according to claim 1, further comprising a request acquisition unit that acquires request information indicating the content of a received request, wherein the selection unit further refers to the request information to select the data center.

3. The control device according to claim 2, wherein the request information includes location information specifying a data center in which the processing will be performed, and the selection unit determines whether the power consumption when the processing is performed by a processing device provided in the data center specified by the location information exceeds the maximum power consumption, and selects the data center if it determines that the power consumption of the processing device does not exceed the maximum power consumption.

4. The control device according to claim 2, further comprising a prediction unit that predicts the power consumption required for the processing for which a request has been received, based on the request information, as the required power information.

5. The control device according to claim 2, further comprising a first information acquisition unit that acquires actual power consumption information, which indicates the power consumption when the processing was performed in the data center in the past, based on the request information, as the required power information.

6. The control device according to claim 5, wherein the request information includes parameters used to execute the process, and if there is no actual power consumption information when the process is performed, the control device further comprises a second information acquisition unit that acquires the actual power information with the highest relationship to the parameters from among multiple actual information sources as the required power information.

7. The control device according to claim 6, further comprising: a result acquisition unit that acquires result information indicating the result of the processing from a data center that has performed the processing; and a creation unit that creates statistical information for determining the relationship based on the result information.

8. The control device according to claim 2, further comprising: a request information which includes priority information indicating the priority of the processing for which the request was received; a result acquisition unit which acquires result information indicating the result of the processing from a data center which performed the processing; and a calculation unit which calculates the fee to be charged to the requester of the processing based on the priority information and the result information.

9. A control program that causes a computer to perform a process to assign the processing of data received as a request to one of several data centers, the control program to perform a selection step of selecting a data center from among the several data centers that has a processing unit whose power consumption when the processing is performed does not exceed the maximum power consumption, by referring to required power information indicating the power consumption required for the processing and power consumption information representing the current power consumption of each processing unit in each of the several data centers.

10. A control method for a computer processor to assign the processing of data for which a request has been received to one of several data centers, the control method comprising a selection step of referring to required power information indicating the power consumption required for the processing and power consumption information representing the current power consumption of each processing unit in each of the several data centers, and selecting a data center among the several data centers that has a processing unit whose power consumption when the processing is performed does not exceed the maximum power consumption.

Images