Control device and control method

Abstract

Provided is a control device that controls a system in which data acquired by a terminal is processed by a calculation device, the control device comprising: a requirement determination unit that determines, on the basis of peripheral information about the terminal, a first required value relating to the quality of the data and a second required value relating to a processing delay of the data; and a control unit that designates a communication resource amount and a calculation resource amount for the system on the basis of the first required value and the second required value.

Description

Control device and control method

[0001] The present invention relates to a technique for allocating computing resources and communication resources in a mobile network system.

[0002] As a conventional technique related to the allocation of processing in a mobile network system, Patent Document 1 discloses a technique aimed at efficiently using computing resources while satisfying processing requirements in the form of edge computing.

[0003] In the technique disclosed in Patent Document 1, the processing request delay is not treated as a fixed value but is treated as varying depending on the surrounding environment. Specifically, based on the peripheral state of the terminal such as location, date and time, and weather, the current delay requirement necessary for processing is calculated, and from the calculated delay requirement, it is determined whether to execute the processing on the edge server or the cloud server.

[0004] Generally, since the edge server exists near the terminal, the delay caused by communication can be reduced, but the available computing resources are limited. On the other hand, since the cloud server exists far from the terminal, it requires a delay caused by communication, but has abundant computing resources.

[0005] From such a viewpoint, in the technique disclosed in Patent Document 1, processing that requires low latency is allocated to the edge server, and processing for which delay is tolerated is allocated to the cloud server, thereby achieving both the delay requirement and the effective utilization of computing resources. By applying the technique disclosed in Patent Document 1 to in-network computing, it is considered that the limited computing resources in the network can be efficiently utilized.

[0006] Japanese Patent Application Laid-Open No. 2024-15022

[0007] However, the above conventional technique has the following two problems.

[0008] (1) Communication resources when transferring processing target data from the terminal to the network or returning the processing result from the network to the terminal are not considered. Therefore, when performing high-priority processing in the network, communication resources may be insufficient, and delays may occur due to waiting for transmission.

[0009] (2) The amount of computing resources allocated to processing is not taken into consideration. Therefore, it is possible that limited computing resources may not be used efficiently, as sufficient computing resources may not be allocated to high-priority processing, or conversely, excessive computing resources may be allocated to low-priority processing.

[0010] This invention has been made in view of the above points, and aims to provide a technology that enables efficient use of limited computing resources while satisfying latency requirements in a network system that processes data.

[0011] According to the disclosed technology, a control device is provided for controlling a system that processes data acquired by a terminal in a computing device, comprising: a requirements determination unit that determines a first requirement value regarding the quality of the data and a second requirement value regarding the processing delay of the data based on peripheral information of the terminal; and a control unit that specifies the amount of communication resources and the amount of computing resources to the system based on the first requirement value and the second requirement value.

[0012] The disclosed technology provides a method for network systems that process data to efficiently utilize limited computing resources while meeting latency requirements.

[0013] This figure shows an example of the overall configuration of a mobile network system in an embodiment of the present invention. This is a flowchart for explaining the operation of the system. This figure shows an example of a requirements table. This figure shows an example of a requirements table. This figure shows an example of a requirements table. This figure shows an example of a hardware configuration of the device.

[0014] Hereinafter, embodiments of the present invention (this embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the embodiments described below.

[0015] The following describes an embodiment of a mobile network system consisting of a terminal equipped with sensors, a wireless base station (hereinafter referred to as "base station"), and a core network having network computing capabilities. Specifically, it describes a technique for determining and allocating computing and communication resources to the system in a configuration where sensor data acquired by the terminal is analyzed using network computing capabilities on the core network.

[0016] (System Configuration Example) Figure 1 shows an example of the overall configuration of the mobile network system in this embodiment. As shown in Figure 1, this system has terminals 100, base stations 200, and a core network 300, as well as an orchestrator 400 that is responsible for controlling them. Also in Figure 1, examples of external systems 500 are shown, such as AMEDAS 510 and ITS (Intelligent Transport Systems) 520. The orchestrator 400 may also be called a control device. The orchestrator 400 has a requirements determination unit 410 and a control unit 420.

[0017] Terminal 100 has a sensor data measurement unit 110 and a communication unit 120. The sensor data measurement unit 110 acquires sensor data from the orchestrator 400 at a specified quality and passes the sensor data to the communication unit 120. The communication unit 120 transmits the sensor data wirelessly to the base station 200.

[0018] The base station 200 has a communication resource allocation unit 210 and a communication unit 220. The communication resource allocation unit 210 allocates a specified amount of communication resources to the terminal 100 from the orchestrator 400. The communication resources are, for example, wireless resources such as resource blocks. The communication unit 220 consumes the allocated communication resources to communicate wirelessly with the terminal 100 and receives sensor data. The communication unit 220 then transfers the received sensor data to the core network 300.

[0019] The core network 300 includes a relay server 320 that performs packet routing and other operations, and a network computing resource allocation unit 310. The relay server 320 includes a computing unit 321 and a communication unit 322. The communication unit 322 can be thought of as having the function of routing packets, and the computing unit 321 as having the function of processing data (such as analyzing sensor data).

[0020] The relay server 320 may also be called a computing device. The calculation unit 321 may also be called a computing device. Figure 1 shows relay server A (320A) and relay server B (320B) as examples of relay servers. Examples of operation using these relay servers A and B will be described later.

[0021] The network computing resource allocation unit 310 can allocate a portion of the relay server 320's unused computing resources to sensor data analysis processing based on a specification from the orchestrator 400. Sensor data analysis processing is performed using the computing resources allocated to the relay server 320. Figure 1 shows an image of the case where analysis processing is performed on the relay server 320B. The analysis results can be returned to the terminal 100, or transmitted to a cloud server.

[0022] The orchestrator 400 may also specify the amount of communication resources for communication within the core network to the network resource allocation unit 310. In this case, for example, the network resource allocation unit 310 sets the amount of communication resources between relay servers to the specified amount.

[0023] (Example of system operation) Next, we will explain how the orchestrator 400 shown in Figure 1 allocates communication resources and computing resources, following the steps in the flowchart shown in Figure 2.

[0024] <S101 (Step 101): Information Acquisition> In S101, the requirements determination unit 410 within the orchestrator 400 acquires information about the terminal 100's surroundings, such as location, date and time, and weather. Possible sources of information about the terminal's surroundings include information from other systems such as AMEDAS 510 and ITS (Intelligent Transport Systems) 520. Although terminal 100 is assumed to be a mobile terminal, it may also be a fixed terminal.

[0025] <S102: Requirements Table Creation> In S102, the requirements determination unit 410 creates a requirements table. Specifically, it performs the following processes.

[0026] First, the requirements determination unit 410 determines two types of values ​​to be requested by the system in relation to the analysis process of sensor data acquired by the terminal 100, based on the acquired surrounding conditions of the terminal 100.

[0027] The first value is the quality of the sensor data acquired by terminal 100. Examples of sensor data quality include the number of quantization bits and the sensor data acquisition interval. One possible criterion for determining the number of quantization bits is whether or not precise sensor analysis processing is required. If detailed processing results are needed, the required value is set high; if rough results are acceptable, the required value is set low, saving communication resources required for sensor data transmission. Another possible criterion for determining the acquisition interval is the temporal variation of the environment surrounding the terminal. If the temporal variation of the environment is large and high-frequency analysis is required, the acquisition interval is set short; conversely, if low-frequency analysis is acceptable, the acquisition interval is set high, saving communication resources required for sensor data transmission.

[0028] The second value is the sensor processing request delay value. This represents the time from when terminal 100 transmits sensor data until the sensor processing result (sensor analysis processing result) is obtained, and is determined based on whether a slight processing delay in sensor analysis will affect the application.

[0029] From the above perspective, the requirements determination unit 410 creates a requirements table. An example of a requirements table is shown in Figure 3. In the example in Figure 3, "sensor data quantization bit count" and "sensor data transmission frequency" are requirement values ​​corresponding to the "first value" above, and "computational resource deployment location" and "computational resource deployment amount" are requirement values ​​corresponding to the "second value" above.

[0030] <S103: Instructions> In S103, instructions are given based on the requirements table. Specifically, they are as follows:

[0031] The control unit 420 refers to the requirements table created by the requirements determination unit 410 and issues instructions to the terminal 100, the base station 200, and the network computing resource allocation unit 310, respectively.

[0032] First, the control unit 420 instructs (specifies) the terminal 100 to acquire the quality of the sensor data to be acquired. Based on this instruction, the terminal 100 acquires the sensor data and transmits it to the base station 200.

[0033] The control unit 420 communicates to the base station 200 the amount of communication resources necessary to transmit sensor data to the terminal 100 under the specified quality. Specific examples of communication resources to be secured include resource blocks and spreading codes.

[0034] Based on the above, it is possible to secure the necessary communication resources for terminal 100 to transmit data without excess or deficiency, based on the environment surrounding the terminal.

[0035] Furthermore, the control unit 420 specifies to the network computing resource allocation unit 310 the location and amount of computing resources to be allocated. For example, if it is determined that processing needs to be performed with low latency, it instructs the network computing resource allocation unit 310 to allocate a large amount of computing resources to a relay server near the terminal. On the other hand, if it is determined that processing delay is acceptable, it instructs the network computing resource allocation unit 310 to allocate a small amount of computing resources to a relay server far from the terminal. As a result, more flexible optimization of computing resources can be performed than with conventional technology.

[0036] (Example) Next, a more specific example of the operation of this system will be described as an example. In the example shown below, we assume a scenario in which a vehicle transmits an image from an onboard camera to a relay server 320, the relay server 320 analyzes obstacles and other objects in the image, and the results are distributed to the vehicle. In the configuration of Figure 1, terminal 100 corresponds to the vehicle. Alternatively, terminal 100 may be considered as a device inside the vehicle. Operation example 1 and operation example 2 will be described below.

[0037] <Operation Example 1> In Operation Example 1, consider a scenario where communication resources and computing resources are determined in an environment where the area around the vehicle is experiencing bad weather. Under bad weather conditions, images captured by the on-board camera become unclear, so it is necessary to transmit the captured images to the relay server 320 in high resolution.

[0038] Furthermore, since the braking distance of vehicles increases compared to sunny conditions, it is necessary to perform image analysis with low latency and quickly transmit the results to the vehicles.

[0039] From the above perspective, the requirements determination unit 410 creates a requirements table as shown in Figure 4. The control unit 420 refers to the requirements table and issues instructions to the terminal 100 (vehicle), base station 200, and network computing resource allocation unit 310. The instructions based on the requirements table shown in Figure 4 are as follows.

[0040] The control unit 420 instructs terminal 100 to transmit high-resolution images at a normal frequency. At the same time, it instructs base station 200 to secure an adequate amount of communication resources so that terminal 100 can transmit high-resolution images to the network. Furthermore, it instructs network computing resource allocation unit 310 to allocate a large amount of computing resources to the vicinity of terminal 100 (in this case, relay server A) in order to analyze and process the images transmitted from terminal 100 with low latency.

[0041] <Operation Example 2> Next, operation example 2 will be described. In operation example 2, consider a scenario where communication resources and computing resources are determined in an environment with low surrounding traffic volume. In such an environment, compared to an environment where a large number of people and vehicles come and go, a detailed analysis that takes into account the details of the image is not required. In addition, since the risk of a collision accident with surrounding people and vehicles is low due to a slight processing delay, the analysis frequency may be reduced, and a certain processing delay is also acceptable for image analysis.

[0042] From the above viewpoints, the requirement determination unit 410 creates a requirement table as shown in FIG. 5. The control unit 420 refers to the requirement table and issues instructions to the terminal 100 (vehicle), the base station 200, and the in-network computing resource allocation unit 310. The instruction content based on the requirement table shown in FIG. 5 is as follows.

[0043] The control unit 420 instructs the terminal 100 to transmit the captured image to the network at a low frequency while reducing the resolution of the captured image for the purpose of saving communication resources. At the same time, for the base station 200, to ensure an appropriate amount of communication resources for the terminal 100 to transmit low-resolution images to the network at a low frequency. Furthermore, for the in-network computing resource allocation unit 310, since a certain delay is allowed for the image analysis process, a small number of computing resources are allocated to the relay server B far from the terminal.

[0044] (Hardware Configuration Example) Any of the devices (orchestrator, control device, etc.) described in this embodiment can be realized by, for example, causing a computer to execute a program. This computer may be a physical computer or a virtual machine on the cloud.

[0045] That is, the device can be realized by using hardware resources such as a CPU and a memory built in the computer to execute a program corresponding to the processing performed by the device. The above program can be recorded on a computer-readable recording medium (portable memory, etc.) for storage or distribution. It is also possible to provide the above program through a network such as the Internet or email.

[0046] Figure 6 is a diagram showing an example of the hardware configuration of the computer. The computer in Figure 6 includes a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., which are mutually connected by a bus B. Note that the computer may further include a GPU.

[0047] A program for realizing the processing on the computer is provided by a recording medium 1001 such as a CD-ROM or a memory card, for example. When the recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 via the drive device 1000 into the auxiliary storage device 1002. However, the installation of the program does not necessarily have to be performed from the recording medium 1001, and it may be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program and also stores necessary files, data, etc.

[0048] When an instruction to start the program is given, the memory device 1003 reads out and stores the program from the auxiliary storage device 1002. The CPU 1004 realizes the functions related to the device according to the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network or the like. The display device 1006 displays a GUI (Graphical User Interface) etc. by the program. The input device 1007 is composed of a keyboard, a mouse, buttons, or a touch panel, etc., and is used to input various operation instructions. The output device 1008 outputs the calculation result.

[0049] (Summary of the embodiment, effects, etc.) As described above, according to the technology described in this embodiment, in a network system that processes data, it is possible to efficiently use limited computing resources while satisfying the delay requirement.

[0050] In other words, in this embodiment, fluctuations in user requirements are estimated by taking into account the state of the terminal surroundings, and communication and computing resources are allocated appropriately according to the estimated user requirements. This makes it possible to meet user demands while effectively utilizing limited resources, leading to the ability to accommodate a large number of users.

[0051] The following additional information is disclosed regarding the embodiments described above.

[0052] <Notes> (Note 1) A control device that controls a system that processes data acquired by a terminal in a computing device, comprising: a memory; and at least one processor connected to the memory, wherein the processor determines a first requirement value regarding the quality of the data and a second requirement value regarding the processing delay of the data based on peripheral information of the terminal, and specifies the amount of communication resources and the amount of computing resources to the system based on the first requirement value and the second requirement value. (Note 2) The control device according to Note 1, wherein the processor specifies the amount of communication resources to a base station that performs wireless communication with the terminal based on the first requirement value, and specifies the amount of computing resources to a computing resource allocation unit that allocates computing resources to the computing device based on the second requirement value. (Note 3) The control device according to Note 2, wherein the processor specifies to the computing resource allocation unit a computing device that performs the processing of the data. (Appendix 4) A control method executed by a control device that controls a system that processes data acquired by a terminal in a computing device, comprising: a requirements determination step of determining a first requirement value regarding the quality of the data and a second requirement value regarding the processing delay of the data based on peripheral information of the terminal; and a control step of specifying the amount of communication resources and the amount of computing resources to the system based on the first requirement value and the second requirement value. (Appendix 5) A non-temporary storage medium storing a program for causing a computer to function as a control device described in any one of Appendix 1 to 3.

[0053] Although this embodiment has been described above, the present invention is not limited to this specific embodiment, and various modifications and changes are possible within the scope of the gist of the invention as described in the claims.

[0054] 100 Terminal 110 Sensor data measurement unit 120 Communication unit 200 Base station 210 Communication resource allocation unit 220 Communication unit 300 Core network 310 Network computing resource allocation unit 320 Relay server 400 Orchestrator 410 Requirements determination unit 420 Control unit 500 External system 510 AMEDAS 520 ITS (Intelligent Transport Systems) 1000 Drive device 1001 Recording medium 1002 Auxiliary storage device 1003 Memory device 1004 CPU 1005 Interface device 1006 Display device 1007 Input device 1008 Output device

Claims

1. A control device for controlling a system that processes data acquired by a terminal in a computing device, comprising: a requirements determination unit that determines a first requirement value regarding the quality of the data and a second requirement value regarding the processing delay of the data based on peripheral information of the terminal; and a control unit that specifies the amount of communication resources and the amount of computing resources to the system based on the first requirement value and the second requirement value.

2. The control device according to claim 1, wherein the control unit specifies the amount of communication resources to a base station that performs wireless communication with the terminal based on the first request value, and specifies the amount of computing resources to a computing resource allocation unit that allocates computing resources to the computing device based on the second request value.

3. The control device according to claim 2, wherein the control unit specifies to the computing resource allocation unit a computing device that performs the processing of the data.

4. A control method executed by a control device that controls a system that processes data acquired by a terminal in a computing device, comprising: a requirements determination step of determining a first requirement value regarding the quality of the data and a second requirement value regarding the processing delay of the data based on peripheral information of the terminal; and a control step of specifying the amount of communication resources and the amount of computing resources to the system based on the first requirement value and the second requirement value.

Images