Transfer control device, transfer control method, and transfer control program

Abstract

To optimize power consumption in data centers. [Solution] The transfer control device 10 has a determination unit 153 and a transfer control unit 154. The determination unit 153 determines which data center will execute the task from among multiple data centers based on the power supply status to multiple data centers. The transfer control unit 154 controls the transfer of data used for the task to the data center determined by the determination unit 153. For example, the determination unit 153 determines which data center will execute the task according to the amount of power supplied to multiple data centers.

Description

Technical Field

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

Background Art

[0002] Conventionally, a technique called DCI (Data Center Interconnection) for interconnecting data centers has been known. Also, a technique is known for eliminating surpluses and shortages in the power supply and demand situation for each server by changing the total number of servers deployed in the data center or the power settings of each operating server (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, it may be difficult to improve the power consumption efficiency in the data center.

[0005] Recently, some data centers are equipped with a solar power generation system and may be self-powered. In that case, from the viewpoints of economy and environmental load, etc., it is preferable that the power supplied from the solar power generation system is preferentially consumed rather than the grid power. Note that the grid power is the power purchased from and supplied by an electric power company.

[0006] On the other hand, for example, the technique of Patent Document 1 improves the power supply and demand situation within the data center. For this reason, for example, when a surplus occurs in the power supplied from the solar power generation system to the data center, the surplus power cannot be utilized by the servers in the data center, and there may be waste.

[0007] The present invention has been made in view of the above, and aims to improve the efficiency of power consumption in data centers. [Means for solving the problem]

[0008] To solve the above-mentioned problems and achieve the objective, the transfer control device of the present invention is characterized by comprising: a determination unit that determines which data center to execute a task from among a plurality of data centers based on the power supply status to the plurality of data centers; and a transfer control unit that controls the transfer of data used for the task to the data center determined by the determination unit. [Effects of the Invention]

[0009] According to the present invention, power consumption in data centers can be made more efficient. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 is a diagram illustrating the overview of the transfer control system according to the first embodiment. [Figure 2] Figure 2 shows an example of the configuration of a transfer control device according to the first embodiment. [Figure 3] Figure 3 shows an example of data center information. [Figure 4] Figure 4 shows an example of server information. [Figure 5] Figure 5 shows an example of task information. [Figure 6] Figure 6 shows an example of weather information. [Figure 7] Figure 7 is a flowchart showing the processing flow of the transfer control device. [Figure 8] Figure 8 shows an example of the configuration of a computer that executes a transfer control program. [Modes for carrying out the invention]

[0011] The transfer control device, transfer control method, and transfer control program according to the present application will be described in detail below based on the drawings. Note that the present invention is not limited to the embodiments described below.

[0012] [First Embodiment] The configuration of the network system will be described using FIG. 1. FIG. 1 is a diagram for explaining the outline of the transfer control system according to the first embodiment.

[0013] As shown in FIG. 1, the network system 1 includes data centers 20a, 20b, 20c, 20d, and 20e. The network system 1 also includes a transfer control device 10.

[0014] Hereinafter, the data centers included in the network system 1 may be referred to as data center 20 without distinction, or simply as a data center. Also, the number and arrangement of the data centers included in the network system 1 are examples and are not limited to those shown in FIG. 1.

[0015] A data center is a building in which a plurality of network devices and a plurality of servers are arranged. In the first embodiment, the data center may mean a system including a plurality of arranged network devices and a plurality of servers.

[0016] The servers arranged in the data center may be servers owned by users such as companies, or rental servers leased to users. Users can exchange data with the servers arranged in the data center 20 from a remote location.

[0017] As shown in FIG. 1, the plurality of data centers included in the network system 1 are installed at locations separated from each other. The data centers are connected by a network.

[0018] At least a part of the network between data centers includes an All-Photonics Network (APN).

[0019] APN is a technology that enables the construction of a high-speed network by processing all network transfer functions in the optical domain. Specifically, APN is a technology based on optical (photonics-based) technologies such as "optoelectronic fusion technology", "high-capacity optical transmission system and device technology", "optical lithography machine", "optical lattice clock network", etc., which realizes low-power consumption and high-quality, high-capacity, and low-latency communication. For example, by using APN, Network System 1 can transfer a large amount of data between data centers in a short time.

[0020] Also, assume that the data centers included in Network System 1 are equipped with solar power generation systems. Each data center can use not only the grid power supplied by the power company but also the power supplied by the solar power generation system.

[0021] From the perspectives of economy and environmental load, etc., it is preferable that the power supplied by the solar power generation system is preferentially consumed rather than the grid power. Therefore, the transfer control device 10 performs control such that the power supplied by the solar power generation system is preferentially utilized based on the power supply and demand situation.

[0022] For example, the transfer control device 10 not only allocates the tasks of each data center so that the power supplied by the solar power generation system is consumed without waste, but also transfers the data required for the tasks between the data centers.

[0023] The size of the data required for the tasks of the data center may be very large. In contrast, in Network System 1 of the first embodiment, since the data centers are connected by APN, it is possible to transfer large-size data at high speed.

[0024] The transfer control device 10 may be a computer independent of each data center, or it may be a server located in one of the data centers.

[0025] The configuration of the transfer control device 10 will be explained using Figure 2. Figure 2 is a diagram showing an example of the configuration of a transfer control device according to the first embodiment. As shown in Figure 2, the transfer control device 10 has a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0026] The communication unit 11 is an interface for communicating with other devices. For example, the communication unit 11 is a NIC (Network Interface Card).

[0027] The input unit 12 is an interface for receiving data input. For example, the input unit 12 is connected to input devices such as a keyboard and a mouse.

[0028] The output unit 13 is an interface for outputting data. For example, the output unit 13 is connected to output devices such as a display and a speaker.

[0029] The storage unit 14 is a storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or optical disc. Alternatively, the storage unit 14 may be a rewritable semiconductor memory such as RAM (Random Access Memory), flash memory, or NVSRAM (Non-Volatile Static Random Access Memory). The storage unit 14 stores the OS (Operating System) and various programs executed by the transfer control device 10.

[0030] The memory unit 14 stores data center information 141, server information 142, task information 143, and weather information 144.

[0031] Data center information 141 is information about a data center included in network system 1. Figure 3 shows an example of data center information. As shown in Figure 3, data center information 141 is a table with columns for "Data Center ID", "Latitude and Longitude", and "Operating Status".

[0032] The "Data Center ID" column stores information that identifies the data center. The "Latitude and Longitude" column stores the latitude and longitude of the data center's location. For example, the "Availability" column stores the data center's utilization rate. The utilization rate is, for example, the ratio of the current processing load to the maximum processing load of the servers located in the data center. For example, the processing load is calculated based on the utilization rate of processors (e.g., CPU (Central Processing Unit) and GPU (Graphics Processing Unit)).

[0033] Furthermore, the "Operating Level" column may store an absolute value representing the operating level of the data center. For example, the operating level may be the number of processors currently in operation. In the following explanation, we will assume that "Operating Level" is the utilization rate.

[0034] Hereafter, a data center with data center ID X will be referred to as data center X. Similarly, a server with server ID Y will be referred to as server Y.

[0035] For example, Figure 3 shows that data center 20a is located at the latitude and longitude "43.537413, 142.624511" and has an operating rate of "20%". A low operating rate also means that the demand for electricity is low.

[0036] Server information 142 is information about servers located in the data center. Figure 4 shows an example of server information. As shown in Figure 4, server information 142 is a table with columns for "Data Center ID", "Server ID", "Configuration", and "Task".

[0037] The "Data Center ID" column stores information identifying the data center. The "Server ID" column stores information identifying the server. The "Configuration" column stores information indicating the server's configuration. The "Task" column stores information identifying the task the server is currently running.

[0038] For example, the configuration is represented by information indicating the performance of the processors (product name, model number, etc.) and the number of processors. For instance, "P100 x 10" means that there are 10 processors (e.g., GPUs) with the model number "P100".

[0039] For example, Figure 4 shows that the configuration of server 201a in data center 20a is "P100×10" and that the tasks currently running are "T001,T002".

[0040] Task information 143 is information about tasks performed by servers located in the data center. Figure 5 shows an example of task information. As shown in Figure 5, task information 143 is a table with columns for "Task ID", "Task Details", "Processing Load", "Dynamic Data", and "Static Data".

[0041] The "Task ID" column stores information that identifies the task. The "Task Description" column stores information that describes the task's content. The "Processing Load" column stores information that represents the task's processing load. For example, a task with a high processing load will increase processor utilization, which in turn increases data center utilization.

[0042] The "Dynamic Data" column stores the size of the dynamic data required for the task. For example, dynamic data is the size of the data that the data center sends and receives with external devices during task execution.

[0043] The "Static Data" column stores the size of the static data required for the task. For example, static data is the size of the data that is prepared when the task starts executing.

[0044] For example, Figure 5 shows that for task "T001," the content is "analysis of still images," the processing load is "medium," the dynamic data is "1 Gbps," and the static data is "500 TB."

[0045] Weather information 144 is information about the weather. Figure 6 shows an example of weather information. As shown in Figure 6, weather information 144 is a table with columns for "Location", "1 day later", "2 days later", "3 days later", "4 days later", "5 days later", "6 days later", and "7 days later".

[0046] The "Location" column stores information that identifies the location. The "1 day later," "2 days later," "3 days later," "4 days later," "5 days later," "6 days later," and "7 days later" columns store predicted solar radiation values ​​for the corresponding days. Note that solar radiation is an example of weather information. Weather information may include information indicating the weather, such as "sunny" or "cloudy," or it may include measured or predicted values ​​related to weather, such as precipitation.

[0047] For example, Figure 6 shows that the predicted solar radiation for the location "Hokkaido" one day later is "15 MJ / m²". 2 It is indicated that it is " / day".

[0048] Returning to Figure 2, the control unit 15 controls the entire transfer control device 10. The control unit 15 is, for example, an electronic circuit such as a CPU, MPU (Micro Processing Unit), or GPU, or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0049] The control unit 15 has an internal memory for storing programs and control data that define various processing procedures, and executes each process using the internal memory. In addition, the control unit 15 functions as various processing units when various programs are run. For example, the control unit 15 has an acquisition unit 151, a prediction unit 152, a determination unit 153, and a transfer control unit 154.

[0050] The acquisition unit 151 acquires information about the data center, information about the servers, information about tasks, and information about the weather. The acquisition unit 151 registers the acquired information in data center information 141, server information 142, task information 143, and weather information 144.

[0051] The prediction unit 152 predicts some of the information that the decision unit 153, described later, will refer to when determining which data center will perform the task. For example, the prediction unit 152 predicts the power supply status to multiple data centers for dates and times beyond the current date and time, using methods such as linear forecasting.

[0052] The decision unit 153 determines which data center will execute the task from among multiple data centers based on the power supply status to multiple data centers.

[0053] The transfer control unit 154 controls the transfer of data used for a task to the data center determined by the determination unit 153. The transfer control unit 154 can instruct data transfer between data centers. Furthermore, for example, the transfer control unit 154 can instruct a device located outside of a data center to transfer data to a specific data center.

[0054] Figure 7 illustrates an example of the specific processing flow of the transfer control device 10. Figure 7 is a flowchart showing the processing flow of the transfer control device. Here, it is assumed that each of the multiple data centers is equipped with facilities that generate electricity using sunlight, i.e., a solar power generation system. Note that a solar power generation system is an example of facilities that generate electricity using renewable energy.

[0055] As shown in Figure 7, first, the acquisition unit 151 acquires weather information for each location (step S101). Next, the prediction unit 152 predicts the amount of solar power generation for each data center based on the weather information (step S102).

[0056] The prediction unit 152 may predict the amount of solar power generation on the current day, the amount of solar power generation one day later, or the amount of solar power generation for a certain period, such as from one day to seven days later. Furthermore, the prediction unit 152 predicts the power supply and demand situation for each data center (step S103).

[0057] The decision unit 153 calculates the priority for executing tasks at each data center based on the power supply and demand situation and other factors (step S104). The decision unit 153 determines which data center will execute the tasks based on the priority (step S105). The transfer control unit 154 then controls the transfer of data according to the determined information (step S106).

[0058] Here, the decision unit 153 calculates that data centers with a larger predicted solar power generation amount should be given a higher priority.

[0059] For example, the decision unit 153 calculates a higher priority for data centers where the weather forecast for the location is sunny compared to data centers where the weather forecast for the location is cloudy or rainy. This is because locations with sunny weather are predicted to generate more solar power than locations with cloudy or rainy weather.

[0060] Furthermore, for example, the decision unit 153 prioritizes data centers with higher predicted solar radiation values ​​for their location. This is because higher solar radiation is predicted to result in greater solar power generation.

[0061] The prediction unit 152 can obtain the amount of solar radiation at each location by referring to the weather information 144. The weather information 144 may also include weather conditions such as "sunny" or "cloudy" for each location.

[0062] Furthermore, weather information 144 contains weather information registered at the prefectural level in Japan. The forecasting unit 152 can identify prefectures based on the latitude and longitude of the data centers included in the data center information 141 and compare them with the weather information 144.

[0063] Data center 20a is located in Hokkaido. Data center 20b is located in Fukushima Prefecture. Data center 20c is located in Tokyo. Data center 20d is located in Shimane Prefecture. Data center 20e is located in Fukuoka Prefecture.

[0064] Here, as shown in Figure 3, the utilization rate of data center 20c is high at 75% (high power demand), so the transfer control device 10 determines which data center will execute the task currently being performed by data center 20c. In this case, the transfer control device 10 also determines the data center based on the amount of power generated by the solar power generation system one day later.

[0065] As shown in Figure 6, the solar radiation amount for one day later is highest in Fukushima Prefecture. Therefore, the decision unit 153 determines that the data center 20c located in Fukushima Prefecture will be the data center to execute the task.

[0066] In this way, the decision unit 153 determines which data center will perform the task based on the amount of power supplied to multiple data centers.

[0067] Tasks can be categorized into those requiring high real-time capabilities (e.g., real-time risk prediction for connected cars) and those that do not (e.g., analysis of healthcare data over a certain period). The decision unit 153 may prioritize determining data centers that perform tasks requiring a high degree of real-time capability. For example, the decision unit 153 may determine data centers that perform tasks whose real-time capability is above a certain threshold.

[0068] The decision unit 153 may determine that the larger the size of the dynamic data shown in Figure 5, the greater the degree of real-time nature of the task. Alternatively, the decision unit 153 may determine the degree of real-time nature based on the content of the task.

[0069] Furthermore, facilities that generate electricity using renewable energy are not limited to solar power generation systems. Facilities that generate electricity using renewable energy may also be wind power generation systems. In this case, the decision unit 153 prioritizes data centers with high predicted wind speeds at their location from among multiple data centers equipped with wind-power generation facilities, and determines the data center to execute the task.

[0070] The decision unit 153 may determine the data center to execute the task based on information predicting the weather from the current date and time to a certain period in advance. For example, the decision unit 153 may determine the data center to execute the task based not on the predicted solar radiation value for one day from now, but on the sum of the predicted solar radiation values ​​for one to seven days from now.

[0071] Furthermore, the decision unit 153 may determine which data center to execute the task on, based on seasonal information in addition to the weather conditions at the location of each of the multiple data centers. In the example in Figure 1, the multiple data centers are located within Japan. On the other hand, the data centers may be located in countries other than Japan.

[0072] For example, a data center may be located in a country in the Southern Hemisphere, such as Australia. December is summer in Australia, and the amount of sunlight is high. On the other hand, December is winter in Japan, and the amount of sunlight is low. For this reason, the decision unit 153 may decrease the priority of data centers located in the Northern Hemisphere and increase the priority of data centers located in the Southern Hemisphere in December.

[0073] Furthermore, in cold regions, the demand for electricity from general consumers other than data centers increases in winter for heating, which may lead to a shortage of grid power. For this reason, the decision unit 153 may decrease the priority of data centers located in cold regions and increase the priority of data centers located in warm regions during winter. Conversely, the decision unit 153 may decrease the priority of data centers located in hot regions and increase the priority of data centers located in cool regions during summer.

[0074] Furthermore, a task may be a VM (Virtual Machine). In order to run a VM that was running in one data center on another VM, it is necessary to transfer data equivalent to the VM's memory and storage. The decision unit 153 determines which data center will run the VM task from among multiple data centers. Then, the transfer control unit 154 controls the transfer of the data constituting the VM to the data center determined by the decision unit 153. A task may also be a container. VMs and containers are examples of virtualized environments.

[0075] [Data transfer related to machine learning] In data centers, tasks may be performed that involve training machine learning models or using already trained machine learning models. Tasks involving machine learning models can place a heavy processing load on servers and may require vast amounts of data.

[0076] For example, data for training machine learning models may be constantly sent to a data center from sensors and other devices installed in various locations. In this case, the transfer control unit 154 instructs multiple devices that acquire data for training machine learning models to transfer the training data to the data center determined by the decision unit 153.

[0077] Furthermore, constructing large-scale machine learning models such as LLMs (Large Language Models) requires a vast number of parameters, resulting in a large amount of data being used. Therefore, the decision unit 153 determines which data center will execute the task using the machine learning model from among multiple data centers. The transfer control unit 154 then controls the transfer of data for constructing the machine learning model to the data center determined by the decision unit 153.

[0078] [Determining a data center based on hardware resources] The decision unit 153 can determine which data center will execute the task from among multiple data centers based on the power supply status to multiple data centers and the status of hardware resources held by multiple data centers. The transfer control unit 154 controls the transfer of data used for the task to the data center determined by the decision unit 153.

[0079] For example, the status of hardware resources could be the number of processors in servers located in multiple data centers. Processors may include CPUs, GPUs, and AI chips specifically designed for machine learning tasks.

[0080] The decision unit 153 can determine which data center to execute the task from among multiple data centers based on the status of hardware resources, which is the ratio of unused processing power to the total processing power of the processors of servers installed in multiple data centers.

[0081] For example, the total processing capacity of a processor is the sum of the processor time used by processors in each data center. Also, for example, unused processing capacity is the sum of the processor time that was not used by processors in each data center. The ratio of unused processing capacity to the total processing capacity of processors may be the utilization rate in Figure 3 minus 100%. The decision unit 153 assigns a higher priority to data centers with lower utilization rates.

[0082] Furthermore, the decision unit 153 may determine which data center to execute the task in from among multiple data centers based on the status of hardware resources, which is the number of unused processors among the processors of servers provided in multiple data centers. For example, the decision unit 153 can calculate the number of processors (e.g., GPUs) in each data center based on the server information 142 in Figure 4, and then determine the number of unused processors by subtracting the number of processors in use from the calculated number. The decision unit 153 may obtain the number of processors in use from the data center or server, or it may estimate it based on the task being executed. With this method, the decision unit 153 can obtain the status of hardware resources in absolute terms, such as the number of processors, rather than as a percentage.

[0083] [Effects of the first embodiment] As explained above, the decision unit 153 determines which data center will execute the task from among multiple data centers based on the power supply status to multiple data centers. The transfer control unit 154 controls the transfer of data used for the task to the data center determined by the decision unit 153. For example, the decision unit 153 determines which data center will execute the task according to the amount of power supplied to multiple data centers.

[0084] This allows the transfer control device 10 to optimize power consumption in the data center. In particular, the transfer control device 10 not only transfers tasks to other data centers, but also transfers the data used in those tasks to other data centers, thereby consolidating tasks and data in data centers with sufficient power capacity.

[0085] The decision unit 153 determines which data center will execute tasks whose real-time performance is above a threshold. The required real-time performance differs for each task. The transfer control device 10 can prioritize transferring tasks requiring real-time performance to data centers with sufficient power resources.

[0086] The decision unit 153 selects a data center to perform the task from among multiple data centers equipped with facilities that generate electricity using renewable energy, based on weather information for each location of the multiple data centers.

[0087] For example, the decision unit 153 selects a data center from among multiple data centers equipped with solar power generation facilities that has a sunny weather forecast for its location, prioritizing that data center over data centers with cloudy or rainy weather forecasts for its location, to execute the task. Alternatively, the decision unit 153 selects a data center from among multiple data centers equipped with solar power generation facilities that has a large predicted solar radiation value for its location, prioritizing that data center to execute the task. Furthermore, the decision unit 153 selects a data center from among multiple data centers equipped with wind power generation facilities that has a large predicted wind speed for its location, prioritizing that data center to execute the task.

[0088] This allows the transfer control device 10 to promote the efficient use of renewable energy obtained from sunlight or wind.

[0089] The decision unit 153 determines the data center to execute the task based on information predicting the weather from the current date and time to a certain period in advance. This allows the transfer control device 10 to improve not only the instantaneous efficiency of power usage but also the long-term efficiency. For example, the transfer control device 10 can reduce the frequency of data transfers between data centers.

[0090] The transfer control unit 154 instructs multiple devices that acquire training data for machine learning models to transfer the training data to the data center determined by the decision unit 153. This allows the transfer control device 10 to quickly transfer the machine learning model training task, including the collection of training data, to another data center.

[0091] The decision unit 153 determines which data center will execute the task using the machine learning model from among multiple data centers. The transfer control unit 154 controls the transfer of data for configuring the machine learning model to the data center determined by the decision unit 153. As a result, the transfer control device 10 can quickly transfer tasks such as inference using the machine learning model to other data centers.

[0092] The determination unit 153 determines which data center will execute the VM task from among multiple data centers. The transfer control unit 154 controls the transfer of the data constituting the VM to the data center determined by the determination unit 153. As a result, the transfer control device 10 can achieve stable VM execution in a data center with sufficient power.

[0093] The decision unit 153 determines which data center will execute the task from among multiple data centers based on the power supply status to multiple data centers and the status of hardware resources possessed by multiple data centers. The transfer control unit 154 controls the transfer of data used for the task to the data center determined by the decision unit 153. For example, the decision unit 153 determines which data center will execute the task from among multiple data centers based on the status of hardware resources, which is the number of processors in the servers provided in multiple data centers.

[0094] This allows the transfer control device 10 to efficiently utilize not only power but also hardware resources. For example, the transfer control device 10 can avoid GPU shortages when performing machine learning tasks.

[0095] The decision unit 153 determines which data center to execute the task from among multiple data centers based on the status of hardware resources, which is the ratio of unused processing power to the total processing power of the processors of the servers installed in the multiple data centers. Alternatively, the decision unit 153 may determine which data center to execute the task from among multiple data centers based on the status of hardware resources, which is the number of unused processors among the processors of the servers installed in the multiple data centers. This allows the transfer control device 10 to prevent situations in which the migrated task cannot be executed due to insufficient processing power.

[0096] [System configuration, etc.] Each component of the illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed or integrated in any unit according to various loads and usage conditions. Furthermore, each processing function performed by each device can be implemented, all or any part of it, by a CPU and a program that is analyzed and executed by that CPU, or by hardware using wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0097] Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

[0098] [program] In one embodiment, the transfer control device 10 can be implemented by installing a program that performs the above processing as packaged software or online software on a desired computer. For example, by having the above program run on an information processing device, the information processing device can function as the transfer control device 10. The information processing device referred to here includes desktop or notebook personal computers. In addition, mobile communication terminals such as tablet terminals and smartphones are also included in the category of information processing devices.

[0099] Furthermore, the transfer control device 10 may be implemented as a web server, or it may be implemented as a cloud service that provides the above processing services through outsourcing.

[0100] Figure 8 shows an example configuration of a computer running a transfer control program. Computer 1000 has, for example, memory 1010 and a CPU 1020. Computer 1000 also has a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0101] Memory 1010 includes ROM (Read Only Memory) 1011 and RAM (Random Access Memory) 1012. ROM 1011 stores, for example, a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090. The disk drive interface 1040 is connected to the disk drive 1100. For example, a removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0102] The hard disk drive 1090 stores, for example, the OS 1091, application programs 1092, program modules 1093, and program data 1094. That is, the programs that define each process of the transfer control device 10 are implemented as program modules 1093 in which executable code for the computer is written. The program modules 1093 are stored, for example, in the hard disk drive 1090. For example, a program module 1093 for performing processes similar to the functional configuration of the transfer control device 10 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

[0103] Furthermore, the configuration data used in the processing of the above-described embodiment is stored as program data 1094 in, for example, memory 1010 or hard disk drive 1090. The CPU 1020 then reads the program module 1093 and program data 1094 stored in memory 1010 or hard disk drive 1090 into RAM 1012 as needed and executes the processing of the above-described embodiment.

[0104] Furthermore, the program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090; for example, they may be stored in a removable storage medium and read by the CPU 1020 via a disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via a network interface 1070. [Explanation of Symbols]

[0105] 1 Network System 10 Transfer control device 11 Communications Department 12 Input section 13 Output section 14 Storage section 15 Control Unit 141 Data Center Information 142 Server Information 143 Task Information 144 Weather Information 151 Acquisition Department 152 Prediction Section 153 Decision Section 154 Transfer Control Unit

Claims

1. A decision unit that determines which data center to execute a task from among the multiple data centers based on the power supply status to the multiple data centers, A transfer control unit that controls the transfer of data used for the task to the data center determined by the determination unit, It has, The decision unit determines that tasks with a large amount of dynamic data required for execution have a higher degree of real-time capability, and prioritizes determining which data center will execute the task with the highest degree of real-time capability among multiple tasks. A transfer control device characterized by the following:

2. The determination unit determines which data center will perform the task based on the amount of power supplied to the plurality of data centers. The transfer control device according to feature 1.

3. The determination unit determines, from among the plurality of data centers equipped with facilities for generating electricity using renewable energy, which data center will perform the task based on weather information for the location of each of the plurality of data centers. The transfer control device according to feature 1.

4. The decision unit, from among the plurality of data centers equipped with solar power generation facilities, determines that a data center whose location has a sunny weather forecast will be prioritized over data centers whose location has a cloudy or rainy weather forecast to be the data center that will perform the task. The transfer control device according to feature 3.

5. The determination unit prioritizes data centers with high predicted solar radiation values ​​at their location from among the multiple data centers equipped with solar power generation facilities, and determines which data center will perform the task. The transfer control device according to feature 3.

6. The determination unit prioritizes data centers with high predicted wind speeds at their locations from among the multiple data centers equipped with wind-powered power generation facilities, and determines which data center will perform the task. The transfer control device according to feature 3.

7. The aforementioned determination unit determines the data center to execute the task based on information predicting the weather from the current date and time to a certain period in advance. The transfer control device according to feature 1.

8. The transfer control unit instructs multiple devices that acquire training data for a machine learning model to transfer the training data to a data center determined by the decision unit. The transfer control device according to feature 1.

9. The decision unit determines from among the plurality of data centers which data center will perform the task using the machine learning model. The transfer control unit controls the transfer of data for configuring the machine learning model to the data center determined by the determination unit. The transfer control device according to feature 1.

10. The determination unit determines from among the plurality of data centers which data center will execute the task which is a VM, The transfer control unit performs control to transfer the data constituting the VM to the data center determined by the determination unit. The transfer control device according to feature 1.

11. A transfer control method performed by a computer, A decision step of determining which data center to execute the task from among the multiple data centers based on the power supply status to the multiple data centers, A transfer control step is performed to control the transfer of data used for the task to the data center determined by the determination step, Includes, The aforementioned decision process determines that tasks with a larger size of dynamic data required for execution have a higher degree of real-time capability, and prioritizes determining which data center will execute the task with the highest degree of real-time capability among multiple tasks. A transfer control method characterized by the following.

12. A decision step in which, based on the power supply status to multiple data centers, a data center is selected from among the multiple data centers to perform the task, A transfer control step which controls the transfer of data used for the task to the data center determined by the decision step, Have the computer run it, The aforementioned decision step determines that tasks requiring a large amount of dynamic data have a higher degree of real-time capability, and prioritizes determining which data center will execute the task with the highest degree of real-time capability among multiple tasks. A transfer control program characterized by the following:

Images