Information processing device and information processing system

Abstract

Tasks are allocated according to the power supply situation. [Solution] An information processing device mounted on the vehicle acquires power status data, which is data indicating the amount of surplus power, from an edge server equipped with renewable energy power generation equipment. Based on the power status data, the device requests the edge server to execute at least some of the multiple calculation tasks that have occurred in the vehicle.

Description

Technical Field

[0001] The present disclosure relates to a vehicle.

Background Art

[0002] There is a technique for providing information to a vehicle by using edge servers associated with geographically dispersed regions (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present disclosure aims to distribute tasks according to the power situation.

Means for Solving the Problems

[0005] One aspect of the present disclosure is an information processing device mounted on a vehicle, having a control unit that acquires power situation data, which is data indicating the amount of surplus power of an edge server equipped with power generation equipment using renewable energy, and requests the edge server to execute at least some of a plurality of calculation tasks generated in the vehicle based on the power situation data.

[0006] One aspect of the present disclosure is one or more edge servers equipped with power generation equipment using renewable energy, and An information processing system including an information processing device mounted on a vehicle, wherein each of the one or more edge servers transmits power status data, which is data indicating the amount of surplus power, to the information processing device, and when the power status data received from the one or more edge servers indicates that there is an edge server with surplus power, the information processing device requests the corresponding edge server to execute at least some of the computation tasks among a plurality of computation tasks.

[0007] Other embodiments include a method performed by the above-mentioned apparatus or system, a program for causing a computer to perform said method, or a computer-readable storage medium that non-temporarily stores said program. [Effects of the Invention]

[0008] According to this disclosure, tasks can be allocated according to the power supply situation. [Brief explanation of the drawing]

[0009] [Figure 1] A schematic diagram illustrating the communication system according to the embodiment. [Figure 2] Configuration diagram of an in-vehicle device according to an embodiment. [Figure 3] Configuration diagram of the edge server and central server according to the embodiment. [Figure 4] A diagram illustrating the processing flow performed by each device. [Figure 5] An example of power status data and decision data used by an in-vehicle device. [Figure 6] A flowchart of the processes performed by the in-vehicle device. [Modes for carrying out the invention]

[0010] There is a system that collects data (sensor data) from various sensors mounted on the vehicle and processes it on a central server. This makes it possible, for example, to automatically generate or update maps of roads that the vehicle can travel on. However, if all sensor data is aggregated and processed on a central server, it puts a load on the server's computing resources and communication bandwidth, leading to a decrease in the overall efficiency and reliability of the system.

[0011] Therefore, a system has been devised in which edge servers are placed in each of the multiple areas on which vehicles travel, and the edge servers perform data preprocessing. For example, the edge servers collect data from vehicles passing through a predetermined area, perform primary processing, and send the results to the central server. For example, by performing primary processing such as data aggregation, filtering, removal of outliers, and data compression at the edge servers and sending the results to the central server at a predetermined time, the load on the central server can be reduced.

[0012] Furthermore, in recent years, there have been attempts to install power generation facilities using renewable energy sources such as solar power alongside edge servers, and to power the edge servers with the electricity produced by these facilities.

[0013] In this configuration, the computing resources that edge servers can provide may increase beyond the design value depending on the amount of power generated. For example, in clear weather, the amount of power that edge servers can consume increases along with the increase in power generation. By allocating this to processors and other components, the computing power of the edge servers can be increased beyond the design value. In such circumstances, edge servers can provide services beyond their intended data processing services, such as receiving tasks from external devices (for example, vehicles traveling nearby) and executing those tasks on behalf of those external devices.

[0014] However, since the amount of power generated by renewable energy is not constant, depending on the power generation situation, the amount of computing resources available to provide to external devices may vary. As a result, due to the weather, it may become possible or impossible to accept tasks from external devices. Also, from the perspective of external devices, whether or not a task can be requested to be executed by an edge server varies depending on the weather, making it impossible to appropriately determine the task execution plan. The information processing apparatus according to the present disclosure solves such problems.

[0015] An information processing apparatus according to an aspect of the present disclosure is an information processing apparatus mounted on a vehicle, and includes acquiring power status data, which is data indicating the amount of surplus power of an edge server equipped with power generation facilities using renewable energy, and based on the power status data, requesting the edge server to execute at least some of a plurality of computing tasks generated in the vehicle. The information processing apparatus has a control unit that executes the above.

[0016] A computing task is a task generated within a vehicle. Typical examples include image recognition processing for autonomous driving, anomaly detection processing based on sensor data, data encryption processing, and the like. The control unit acquires power status data regarding a predetermined edge server equipped with power generation facilities using renewable energy.

[0017] The power status data is data indicating the amount of surplus power in the edge server. Since the power generation facilities using renewable energy have variable available power, surplus power may occur depending on the load of the edge server. The power status data is data for notifying the amount of this surplus power. The power status data may include, for example, data indicating the currently available power by the power generation facilities, data indicating the current power consumption by the edge server, or both. The control unit can determine whether surplus power is generated in the edge server based on the power status data.

[0018] Based on the power situation data, the control unit requests at least some of the plurality of calculation tasks generated in the self-device to be executed by the edge server. For example, when the control unit determines based on the power situation data that surplus power is generated in the target edge server, in order to process the calculation tasks with the surplus power, it can request the edge server corresponding to execute the calculation tasks generated in the vehicle. According to such a configuration, it becomes possible to efficiently utilize the surplus power in the edge server.

[0019] Note that the power situation data may include any data as long as it can estimate the amount of surplus power in the edge server.

[0020] In addition, the control unit may request the edge server to execute more calculation tasks or calculation tasks with a larger amount of computation as the surplus power in the edge server is more. This is because it is considered that the more surplus power there is, the more computing resources the edge server can provide.

[0021] Hereinafter, specific embodiments of the present disclosure will be described based on the drawings. The hardware configuration, module configuration, functional configuration, etc. described in each embodiment are not intended to limit the technical scope of the disclosure only to those without special description.

[0022] (First Embodiment) [System Overview] The overview of the communication system according to the first embodiment will be described with reference to FIG. 1. The communication system according to the present embodiment includes an in-vehicle device 10 mounted on a vehicle, a plurality of edge servers 20 installed along the road, and a center server 30.

[0023] Vehicle 1 is a connected vehicle capable of wireless communication with the edge server 20. Vehicle 1 is equipped with an on-board device 10. The on-board device 10 has the function of collecting sensor data while Vehicle 1 is in motion and transmitting the collected sensor data to the edge server 20.

[0024] The edge server 20 is a server device that can communicate wirelessly with a vehicle 1 (in-vehicle device 10) traveling within a predetermined communication area. The edge server 20 is configured to communicate wirelessly with the vehicle 1 within a predetermined communication area centered on itself. The edge server 20 also has the function of performing primary processing on sensor data collected from the vehicle 1 and transmitting the results to the center server 30.

[0025] The center server 30 is a server device that performs predetermined data processing based on sensor data collected from multiple vehicles 1. For example, the center server 30 can generate three-dimensional road map data based on image data (images taken by on-board cameras) collected from multiple vehicles 1.

[0026] The edge server 20 is positioned between the center server 30 and the vehicle 1 and performs the process of collecting sensor data from the vehicle 1. The edge server 20 also performs primary processing on the collected sensor data and sends the results to the center server 30. Primary processing is, for example, Alternatively, the process may involve converting sensor data into intermediate products. For example, if the center server 30 performs a process to generate a three-dimensional road map based on sensor data, the edge server 20 may perform a process to estimate the three-dimensional shape of a building based on sensor data such as image data. By having the edge server 20 perform information processing at a geographically close location to the vehicle 1, the load on the center server 30 and the amount of data flowing through the network can be reduced.

[0027] In this embodiment, the edge server 20 has a renewable energy power generation device and can operate on electricity generated by renewable energy (typically solar power). The edge server 20 can operate by securing a minimum amount of power from the commercial power supply while also using power supplied from the power generation device. In other words, as the amount of power generated by the power generation device increases, the amount of power available to the edge server 20 increases, and therefore the computing resources available to the edge server 20 also increase. In this embodiment, when computing resources increase beyond a predetermined value (when computing resources exceed the amount that can provide the original service), the edge server 20 uses the increased computing resources to provide a service to an external device (for example, an in-vehicle device 10) that performs the requested computing task.

[0028] In this embodiment, the edge server 20 transmits data regarding the power status of its device to a vehicle 1 traveling within a predetermined communication area. This data may include data indicating the power that can be supplied by the power generator and data indicating the power consumption of the edge server itself. Based on this data, the on-board device 10 determines whether or not surplus power is being generated at the target edge server 20. If surplus power is being generated at the target edge server 20, the on-board device 10 requests the edge server 20 to execute at least a portion of the computation tasks generated in its own vehicle. This makes it possible to efficiently utilize the surplus power generated at the edge server 20.

[0029] In this embodiment, the edge server 20 performs data processing for generating a three-dimensional road map, that is, it periodically collects sensor data from the vehicle 1, performs primary processing, and then transmits it to the center server 30. This processing can be said to be the original role of the edge server 20. In addition, during periods when surplus power is generated, the edge server 20 responds to requests from the vehicle 1 and processes tasks transmitted from the vehicle 1. Tasks transmitted from the vehicle 1 can be, for example, computational tasks that analyze data necessary for the vehicle 1 to perform autonomous driving.

[0030] [System Configuration] Next, we will describe the hardware and software configurations of each device that makes up the system. Figure 2 is a schematic diagram showing an example of the configuration of an on-board device 10 that can be mounted on vehicle 1.

[0031] The in-vehicle device 10 can be configured as a computer having a processor (CPU, GPU, etc.), main memory (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.). The auxiliary storage contains an operating system (OS), various programs, various tables, etc., and by executing the programs stored therein, various functions (software modules) that match a predetermined purpose, as described later, can be realized. However, some or all of the functions may be realized as hardware modules by hardware circuits such as ASICs and FPGAs.

[0032] The in-vehicle device 10 includes a control unit 101, a storage unit 102, a communication unit 103, and an input / output unit 104. It is composed of including the following.

[0033] The control unit 101 is a computing unit that realizes various functions of the in-vehicle device 10 by executing a predetermined program. The control unit 101 can be implemented by a hardware processor such as a CPU. The control unit 101 may also be configured to include RAM, ROM (Read Only Memory), cache memory, etc.

[0034] In this embodiment, the control unit 101 of the in-vehicle device 10 is configured as a software module comprising a driving control unit 1011, a task control unit 1012, and a data transmission unit 1013. These software modules may be implemented by the control unit 101 (CPU, etc.) executing a program stored in the storage unit 102.

[0035] The driving control unit 1011 controls the autonomous driving of vehicle 1. The driving control unit 1011 analyzes sensor data acquired from the sensor group 11 (described later) to extract information necessary for autonomous driving, and controls the driving of vehicle 1 based on that information.

[0036] Specifically, the driving control unit 1011 performs tasks such as analyzing sensor data to recognize objects such as other vehicles, road signs, lane boundaries, and traffic lights, and determining the vehicle's trajectory and acceleration / deceleration based on the analysis results. Sensor data analysis can be performed, for example, using a machine learning model. The machine learning model may be divided into multiple parts, such as one that handles the detection of obstacles, one that handles the detection of traffic lights, and one that handles the detection of lanes. For example, deep neural networks (DNNs) can be used as machine learning models. The number of layers in a DNN can be arbitrarily set depending on the object of analysis. For example, when analyzing simple features such as lane boundary detection, a shallow neural network may be used, while when analyzing higher-order concepts such as object classification, a deep neural network may be used. These tasks may be performed in the control unit 101 or in the edge server 20 (as described later).

[0037] The task control unit 1012 decides whether to execute the task generated by the driving control unit 1011 on its own device or to request the edge server 20 to execute it. Specifically, the task control unit 1012 receives data regarding the power status of the edge server 20 (hereinafter referred to as power status data) from a communicable edge server 20, and based on the power status data and the power status of its own vehicle, it decides whether to execute the task generated by the driving control unit 1011 on its own device or on the edge server 20. For example, if the vehicle itself has insufficient power but the edge server 20 has surplus power, the task control unit 1012 can decide to request the edge server 20 to execute the task in question. In this case, the task control unit 1012 sends the task to the edge server 20 and receives the result from the edge server 20. Furthermore, if the vehicle has sufficient power, or if the edge server 20 does not have surplus power, the task control unit 1012 may decide not to request the edge server 20 to execute the task. In this case, the task control unit 1012 will execute the task on its own device (control unit 101).

[0038] The data transmission unit 1013 periodically collects and transmits data necessary for the center server 30 to generate a three-dimensional road map. For example, the data transmission unit 1013 periodically performs the process of transmitting images acquired by the on-board cameras included in the sensor group 11, and data obtained by analyzing those images, to the edge server 20 located near the vehicle. The data generated and transmitted by the data transmission unit 1013 is used by the driving control unit 1011. It is not directly related to sensor data.

[0039] The memory unit 102 is a means for storing information and is composed of storage media such as RAM, magnetic disks, and flash memory. The memory unit 102 stores programs executed by the control unit 101, data used by those programs, and so on.

[0040] The communication unit 103 is a wireless communication interface for sending and receiving wireless signals to and from the edge server 20. The communication unit 103 is configured to send and receive wireless signals conforming to standards such as wireless LAN or DSRC. The communication range of the wireless signals can be, for example, several hundred meters to several kilometers.

[0041] The input / output unit 104 is a unit that receives input from the vehicle occupants and presents information to them. Specifically, the input / output unit 104 consists of a touch panel and its control means, and a liquid crystal display and its control means. In this embodiment, the touch panel and liquid crystal display consist of a single touch panel display.

[0042] Furthermore, the in-vehicle device 10 is connected to a group of sensors (sensor group 11) for acquiring sensor data used during the driving of the vehicle 1. The sensors included in sensor group 11 may acquire physical quantities or image data, etc. For example, examples of sensors included in the sensor group include a sensor for detecting vehicle speed, an image sensor for acquiring visible light images and distance images of the area in front of the vehicle, a sensor for acquiring position information, a radar sensor, and a LiDAR.

[0043] Next, the configuration of the edge server 20 will be described. Figure 3 is a schematic diagram showing an example of the configuration of the edge server 20 and the central server 30.

[0044] The edge server 20 can be configured as a computer having a processor (CPU, GPU, etc.), main memory (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.), similar to the in-vehicle device 10.

[0045] The edge server 20 is comprised of a control unit 201, a storage unit 202, a communication unit 203A (203B), and a power receiving unit 204.

[0046] The control unit 201 is a computing unit that realizes various functions of the edge server 20 by executing a predetermined program. The control unit 201 can be implemented by a hardware processor such as a CPU. The control unit 201 may also be configured to include RAM, ROM (Read Only Memory), cache memory, etc.

[0047] In this embodiment, the control unit 201 of the edge server 20 is configured to include a task processing unit 2011 and a notification unit 2012 as software modules. These software modules may be implemented by the control unit 201 (CPU, etc.) executing a program stored in the storage unit 202.

[0048] The task processing unit 2011 executes predetermined tasks according to the role of the edge server 20. In this embodiment, the tasks executed by the task processing unit 2011 are of the following two types: (1) Task of performing data processing to generate a three-dimensional road map This task involves performing initial processing on sensor data collected from vehicle 1 and transmitting the processing results to the center server 30. This task is executed in response to the periodic transmission of sensor data from vehicle 1. The transmission of the processing results to the center server 30 may be performed at predetermined intervals. (2) Tasks requested to be performed by Vehicle 1 (Onboard device 10) As described above, the in-vehicle device 10 requests the edge server 20 to execute a task when the edge server 20 has surplus power. The edge server 20 (task processing unit 2011) responds to this request and executes the task sent from the in-vehicle device 10.

[0049] The notification unit 2012 generates data (power status data) regarding the power status of its own device and transmits it to the vehicle 1 (in-vehicle device 10) located within the communication area of ​​its own device. The power status data is, for example, data that notifies the real-time power being consumed by its own device (edge ​​server 20) and the real-time power that can be supplied by the power generator 21, which will be described later.

[0050] The memory unit 202 is a means for storing information and is composed of storage media such as RAM, magnetic disks, and flash memory. The memory unit 202 stores programs executed by the control unit 201, data used by those programs, and so on.

[0051] The communication unit 203A is a communication interface for sending and receiving data with the center server 30. The communication unit 203A is a communication interface that conforms to standards such as Ethernet (registered trademark). The communication unit 203B is a wireless communication interface for sending and receiving wireless signals to and from the in-vehicle device 10. The communication unit 203B is configured to send and receive wireless signals that conform to standards such as wireless LAN or DSRC.

[0052] The power receiving unit 204 is an interface for receiving power generated by the power generation device 21. The power receiving unit 204 is composed of, for example, a converter that stabilizes the output from the solar panels, and an inverter that converts DC to AC. The power receiving unit 204 can also acquire the real-time power generated by the power generation device 21 (power that can be supplied to its own device). The power generation device 21 is a device that generates electricity using renewable energy, and is typically an array of solar panels.

[0053] Next, we will explain the configuration of the central server 30. The center server 30 can be configured as a computer having a processor (CPU, GPU, etc.), main memory (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.), similar to the edge server 20.

[0054] The center server 30 is comprised of a control unit 301, a storage unit 302, and a communication unit 303.

[0055] The control unit 301 is a computing unit that realizes various functions of the center server 30 by executing a predetermined program. The control unit 301 can be implemented by a hardware processor such as a CPU. The control unit 301 may also be configured to include RAM, ROM (Read Only Memory), cache memory, etc.

[0056] In this embodiment, the control unit 301 of the central server 30 executes a process to generate a three-dimensional road map based on information collected from the edge server 20.

[0057] The memory unit 302 is a means for storing information and is composed of storage media such as RAM, magnetic disks, and flash memory. The memory unit 302 stores programs executed by the control unit 301, data used by those programs, and so on.

[0058] The communication unit 303 is a communication interface for communicating with the edge server 20. This communication interface may be a wired interface or a wireless interface. - is fine.

[0059] [Process Overview] Next, we will explain the processing flow performed by the edge server 20 and the in-vehicle device 10. Figure 4 is a diagram illustrating the data flow when a task occurs in the in-vehicle device 10.

[0060] In this embodiment, vehicle 1 is an autonomously driven vehicle. As described above, the driving control unit 1011 analyzes the sensor data acquired from the sensor group 11 to extract information necessary for autonomous driving, and controls the driving of vehicle 1 based on that information.

[0061] Here, the driving control unit 1011 generates and executes tasks in real time during driving in order to analyze the road environment based on sensor data. Examples of tasks generated by the driving control unit 1011 include tasks to determine the position of lane boundary lines, tasks to detect other vehicles and determine their type and position, tasks to detect pedestrians and bicycles and determine their position, and tasks to determine the indication of traffic lights. In addition, there are tasks to determine the acceleration / deceleration and trajectory of the vehicle itself based on the results of analyzing these.

[0062] The task generated by the driving control unit 1011 is, for example, the task of recognizing an object using a neural network. The neural network consists of multiple layers, and the nodes placed in each layer receive multiple inputs and combine them to generate an output. The task generated by the driving control unit 1011 is passed to the task control unit 1012. Since the inference task using the neural network is executed layer by layer, the task generated by the driving control unit 1011 is a task that can be divided into layers.

[0063] Next, the operation of the task control unit 1012 will be described. The task control unit 1012 receives power status data from the notification unit 2012 of the edge server 20. Figure 5(A) shows an example of power status data. As shown, the power status data includes the edge server identifier (edge ​​server ID), the amount of power generated by the power generator 21 attached to the target edge server 20, the power consumption of the edge server 20, and data on surplus power. This data may be generated by the notification unit 2012 based on information obtained from the power receiving unit 204 of the edge server 20. For example, if the amount of power generated by the power generator exceeds the power consumption of the edge server, the difference is the surplus power. Conversely, if the amount of power generated by the power generator does not reach the power consumption of the edge server, the surplus power will be 0 (none). The task control unit 1012 may periodically receive power status data from the edge server 20.

[0064] Furthermore, the task control unit 1012 controls the ECU (Electric Control Unit) of the vehicle 1. Then, data regarding the power status of vehicle 1 (for example, the remaining charge of the drive battery) is acquired, and the entity that will execute the task is determined based on the power status of vehicle 1 and the power status data received from edge server 20. For example, if there is insufficient power supplied from vehicle 1 to execute the task (for example, if the remaining charge of the drive battery falls below a threshold), it may be preferable to request edge server 20 to execute the task. On the other hand, even in such a case, if there is no surplus power on edge server 20, it may not be possible to request the execution of the task. Therefore, the task control unit 1012 decides whether to execute the task generated by the driving control unit 1011 on the vehicle itself or on the edge server 20, based on the power status of the vehicle 1 and the power status of the edge server 20.

[0065] The following shows the differences between the power status of vehicle 1 and the power status of edge server 20.

[0066] (1) When the vehicle can supply sufficient power for the task. If vehicle 1 can supply sufficient power to perform the task, the task control unit 1012 decides to perform the task on its own vehicle. In this case, the task control unit 1012 issues an instruction to the driving control unit 1011 to perform the task.

[0067] (2) When the vehicle itself cannot supply sufficient power for the task, and there is surplus power on the edge server. For example, if the vehicle's power supply is insufficient (e.g., the remaining charge of the drive battery is below a threshold) and the edge server 20 has surplus power, the task control unit 1012 decides to request the edge server 20 to execute the target task. In this case, the task control unit 1012 sends a request to the edge server 20's task processing unit 2011 to execute the target task. Once the task execution is complete, the result is returned from the edge server 20 to the task control unit 1012, which then forwards it to the driving control unit 1011.

[0068] (3) When the vehicle itself cannot supply sufficient power for the task and there is no surplus power on the edge server. For example, if the vehicle's power supply is poor (e.g., the remaining charge of the drive battery is below a threshold) and the edge server 20 also has no surplus power, the task control unit 1012 decides to execute the target task on the vehicle itself. In this case, the task control unit 1012 instructs the driving control unit 1011 to execute the target task. The task control unit 1012 may also determine that the target task is unexecutable. In this case, the task control unit 1012 returns a response to the driving control unit 1011 indicating that the task cannot be executed due to poor power supply, and the driving control unit 1011 may, as a result, stop autonomous driving or take other actions.

[0069] In the case of (2) described above, the task control unit 1012 may adjust the number of tasks to be requested to be executed according to the amount of surplus power in the edge server 20.

[0070] For example, the driving control unit 1011 may generate multiple tasks at the same time, but if the amount of tasks to be executed is not considered, it may end up being requested to execute more tasks than the surplus power can handle. Therefore, the task control unit 1012 may acquire data (hereinafter referred to as "determination data") that defines the relationship between the status of surplus power and the task to be requested to be executed, and determine which task to request to be executed based on this data.

[0071] Figure 5(B) shows an example of judgment data. This data may be pre-stored in the memory unit 102. In this example, the judgment data defines the relationship between the classification of surplus power at the edge server 20 and the task to be requested to be executed. In this example, for example, if the surplus power class is "large," all layers of the object recognition task, which is performed using a neural network, are executed at the edge server 20. If the surplus power class is "medium," some (multiple) layers of the object recognition task are executed at the edge server 20. If the surplus power class is "small," only a single layer of the object recognition task is executed at the edge server 20.

[0072] In the illustrated example, the processing in each layer of the neural network is divided. However, if the driving control unit 1011 generates multiple tasks, the task control unit 1012 may decide which task to request the edge server 20 to execute, depending on the scale of each task (e.g., the amount of computation required).

[0073] Thus, the task control unit 1012 may adjust the number of tasks or the amount of computation it requests the edge server 20 to execute based on the surplus power situation. For example, the more surplus power the task control unit 1012 has, the more tasks or tasks requiring more computation can it request the edge server 20 to execute.

[0074] [Processing flowchart] Figure 6 is a flowchart of the process performed by the in-vehicle device 10. This process is executed when the driving control unit 1011 generates a new task. First, in step S11, the task control unit 1012 obtains the latest power status data from the edge server 20. Note that if the task control unit 1012 periodically obtains power status data from the edge server 20, this step may be omitted.

[0075] Next, in step S12, the task control unit 1012 acquires data regarding the vehicle's power status. This data may include, for example, data indicating the remaining charge of the drive battery, but is not limited to this, as long as it can determine whether or not a new task can be executed on the vehicle. For example, in this step, data regarding the power currently being consumed by the vehicle to execute the task may be acquired. This data regarding the vehicle's power status may be acquired, for example, from an ECU that manages the drive battery.

[0076] Next, in step S13, the task control unit 1012 determines whether the vehicle's power supply is insufficient for executing the task. For example, if the remaining charge of the vehicle's drive battery is below a predetermined value, or if the power currently consumed for executing the task is above a predetermined value, it can be determined that the power supply is insufficient for executing the task.

[0077] If the result in this step is positive, the process proceeds to step S14 to determine whether it is possible to request the edge server 20 to execute the task. If the result in this step is negative, the process proceeds to step S16.

[0078] In step S14, the task control unit 1012 determines whether or not there is a power surplus at the edge server 20 based on the power status data acquired from the edge server 20. The surplus power can be calculated, for example, based on the amount of power generated by the power generator 21 and the power consumption of the edge server 20, as indicated by the power status data.

[0079] If the result in step S14 is positive, the process proceeds to step S15. If the result in step S14 is negative, the process proceeds to step S16.

[0080] In step S15, the task control unit 1012 decides to request the edge server 20 to execute at least a portion of the tasks that have occurred, within a specified range. Furthermore, if requesting the edge server 20 to execute the target task results in multiple tasks being executed simultaneously on the edge server 20, the task control unit 1012 may select which tasks to request to execute based on the number of target tasks and their computational complexity. For example, as explained with reference to Figure 5(B), the task control unit 1012 may decide how many tasks to request the edge server 20 to execute based on the power surplus situation on the edge server 20.

[0081] As described above, the edge server 20 according to the first embodiment has a renewable energy power generation facility and has a function to notify the in-vehicle device 10 of the power status of its own device. Furthermore, the in-vehicle device 10, when the power situation in the vehicle is critical, The power status of the edge server 20 is checked, and tasks are requested to be executed by the edge server 20 to the extent possible.

[0082] With this configuration, when surplus power is generated at the edge server 20, it becomes possible to have the edge server 20 process tasks generated at the vehicle 1 instead. In power generation facilities using renewable energy, it was not possible to utilize the surplus power that could not be consumed, but with this embodiment, surplus power can be effectively utilized.

[0083] (modified version) The embodiments described above are merely examples, and this disclosure may be modified as appropriate without departing from its essence. For example, the processes and means described in this disclosure can be freely combined and implemented, as long as no technical inconsistencies arise.

[0084] Furthermore, in the embodiment, an example was given in which multiple edge servers 20 have a predetermined communication area (for example, a radius of several hundred meters) and communicate with a vehicle 1 within that range. However, the in-vehicle device 10 may communicate with edge servers 20 located in remote locations via a cellular network or the like. In this case, the in-vehicle device 10 may receive power status data from each of the multiple edge servers 20 and determine whether it is possible to request a task from each edge server 20.

[0085] Furthermore, while the embodiment illustrates the power status data in the form shown in Figure 5(A), it is not limited to this form as long as it is possible to determine whether or not there is a power surplus at the edge server 20.

[0086] Furthermore, in this embodiment, the amount of tasks to request execution was determined based on the surplus power in the edge server 20. However, if there is still surplus power in the edge server 20 even after requesting execution of all tasks, the in-vehicle device 10 may generate new tasks.

[0087] For example, increasing the number of layers in a neural network can sometimes improve the accuracy of object recognition. For instance, if the task control unit 1012 determines that there is still surplus power on the edge server 20 even after requesting the edge server 20 to execute all tasks that have occurred, it may notify the driving control unit 1011 of this fact. In response to this notification, the driving control unit 1011 may increase the number of layers in the neural network.

[0088] With this configuration, for example, it is possible to obtain the effect of improving the accuracy of autonomous driving during periods when there is a surplus of power. The task control unit 1012 may also instruct the driving control unit 1011 to revert the increased number of neural network layers to their original value when there is no longer any surplus power on the edge server 20 side.

[0089] Furthermore, a process described as being performed by a single device may be divided and executed by multiple devices. Conversely, a process described as being performed by different devices may be executed by a single device. In a computer system, the hardware configuration (server configuration) by which each function is implemented can be flexibly changed.

[0090] Furthermore, while the embodiment illustrates a task utilizing a neural network, other tasks may occur in vehicle 1. For example, if multiple microservices are running in the in-vehicle device 10, the entity executing the microservices may be changed from the in-vehicle device 10 to the edge server 20 based on the surplus power of the edge server 20.

[0091] The present disclosure can also be realized by supplying a computer program implementing the functions described in the embodiments above to a computer, and having one or more processors in the computer read and execute the program. Such a computer program may be provided to the computer by a non-temporary computer-readable storage medium that can be connected to the computer's system bus, or it may be provided to the computer via a network. Non-temporary computer-readable storage mediums include, for example, any type of disk such as magnetic disks (floppy disks, hard disk drives (HDDs), etc.), optical disks (CD-ROMs, DVDs, Blu-ray discs, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic instructions. [Explanation of Symbols]

[0092] 10...In-vehicle equipment 11. Sensor group 20. Edge Server 21... Power generation equipment 30... Center Server 101,201...Control Unit 102,202...Storage section 103,203A,203B...Communication Department 104...Input / output section 204... Power receiving section

Claims

1. An information processing device installed in a vehicle, To acquire power status data, which indicates the amount of surplus power, from edge servers equipped with renewable energy power generation facilities, Based on the aforementioned power status data, the edge server is requested to perform at least some of the multiple calculation tasks that occurred in the vehicle. An information processing device having a control unit that performs the following.

2. The aforementioned power status data includes data indicating the power that can be supplied by the power generation equipment and data indicating the power consumption by the edge server. The information processing apparatus according to claim 1.

3. The control unit determines the amount of surplus power in the edge server based on the power status data, and if there is surplus power, requests the edge server to execute at least some of the calculation tasks. The information processing apparatus according to claim 2.

4. The control unit requests the edge server to perform more computing tasks as the surplus power available in the edge server increases. The information processing apparatus according to claim 3.

5. One or more edge servers equipped with renewable energy power generation facilities, Information processing equipment installed in the vehicle, An information processing system including, Each of the one or more edge servers transmits power status data, which is data indicating the amount of surplus power, to the information processing device. The aforementioned information processing device is If the power status data received from one or more edge servers indicates that there is an edge server with surplus power, the system requests the corresponding edge server to execute at least some of the computation tasks among the multiple computation tasks. Information processing system.

Images