Information processing apparatus and information processing system

Abstract

An information processing device mounted on a vehicle acquires power status data indicating how much residual power a server on the edge having a power generation device using a renewable energy source has, and, based on the power status data, entrusts the server on the edge with execution of at least part of a plurality of computing tasks generated in the vehicle.

Description

Technical Field

[0001] This disclosure pertains to vehicles. Background Technology

[0002] There are technologies that utilize edge servers associated with geographically dispersed regions to provide information about vehicles (e.g., Japanese Patent Application Publication No. 2022-032310). Summary of the Invention

[0003] The purpose of this disclosure is to allocate tasks based on power conditions.

[0004] One aspect of this disclosure is an information processing device mounted on a vehicle.

[0005] The information processing device has a control unit that performs the following actions: acquiring power status data, which is data indicating the amount of remaining power of an edge server equipped with power generation equipment utilizing renewable energy; and, based on the power status data, delegating the edge server to perform at least a portion of a plurality of computing tasks generated in the vehicle.

[0006] One aspect of this disclosure is an information processing system.

[0007] The information processing system includes one or more edge servers equipped with power generation equipment utilizing renewable energy and an information processing device mounted on a vehicle. The one or more edge servers respectively send data indicating the amount of remaining power, i.e., power status data, to the information processing device. When the power status data received from the one or more edge servers indicates that there are edge servers with remaining power, the information processing device entrusts the corresponding edge server to perform at least a portion of the multiple computing tasks.

[0008] Alternatively, other methods may include a method for causing the aforementioned apparatus or system to perform, a program for causing a computer to perform the method, or a computer-readable storage medium that non-temporarily stores the program.

[0009] According to this disclosure, tasks can be allocated based on power conditions. Attached Figure Description

[0010] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which the same reference numerals denote the same parts, wherein:

[0011] Figure 1 This is a schematic diagram illustrating the communication system involved in the implementation method;

[0012] Figure 2This is a configuration diagram of the vehicle-mounted device involved in the implementation method;

[0013] Figure 3 This is a structural diagram of the edge server and central server involved in the implementation method;

[0014] Figure 4 It is a diagram illustrating the processing flow performed by each device;

[0015] Figure 5A This is an example of the power status data and judgment data used by the vehicle-mounted device;

[0016] Figure 5B This is an example of the power status data and judgment data used by on-board devices; and

[0017] Figure 6 This is a flowchart of the processing performed by the on-board device. Detailed Implementation

[0018] There exists a system that aggregates data collected by various sensors mounted on a vehicle (sensor data) and processes it on a central server. This allows, for example, the automatic generation or updating of maps showing the roads the vehicle can travel on.

[0019] However, if the central server collects and processes all the sensor data, it will put a load on the central server's computing resources and communication bandwidth, resulting in a decrease in the overall efficiency and reliability of the system.

[0020] Therefore, a system was designed that deploys edge servers in multiple areas along the vehicle's route to perform data preprocessing. For example, the edge servers collect data from vehicles passing through designated areas, process it once, and send the results to the central server. For instance, the edge servers perform data statistics, filtering, outlier removal, and data compression, and send the results to the central server at predetermined times, thereby reducing the load on the central server.

[0021] In addition, in recent years, attempts have been made to set up power generation equipment that utilizes renewable energy sources such as sunlight together with edge servers, so that the power generated by the power generation equipment enables the edge servers to operate.

[0022] In this approach, the computing resources that the edge server can provide sometimes exceed its design value, depending on the amount of electricity generated. For example, in clear weather, as electricity generation increases, the power that the edge server can consume also increases. By allocating this power to processors and other components, the computing power of the edge server can exceed its design value.

[0023] In this situation, in addition to the data processing services that the edge server should perform, it can also provide services such as receiving tasks from external devices (e.g., vehicles traveling nearby) and performing those tasks on behalf of the external devices.

[0024] However, since the generation of renewable energy is not constant, the amount of computing resources available to external devices may vary depending on the power generation status. Therefore, depending on the weather, there may be situations where tasks from external devices can or cannot be accepted. Furthermore, from the perspective of the external device, whether or not tasks can be delegated to the edge server varies depending on the weather, making it impossible to properly determine the task execution plan.

[0025] The information processing apparatus disclosed herein solves such a problem.

[0026] One aspect of this disclosure relates to an information processing apparatus mounted on a vehicle, the information processing apparatus having a control unit that performs: acquiring power status data, the power status data being data indicating the amount of remaining power of an edge server equipped with a power generation device utilizing renewable energy; and, based on the power status data, delegating the edge server to perform at least a portion of a plurality of computing tasks occurring in the vehicle.

[0027] Computational tasks refer to tasks generated within a vehicle. Typical examples include image recognition processing for autonomous driving, anomaly detection processing based on sensor data, and data encryption processing.

[0028] The control department obtains power status data related to edge servers equipped with power generation equipment that utilizes renewable energy.

[0029] Power status data indicates the amount of remaining power in the edge server. Power generation equipment utilizing renewable energy generates surplus power based on the load on the edge server due to fluctuations in available power. Power status data is used to report the amount of this surplus power. Power status data may include, for example, data indicating the power currently available to be supplied by the power generation equipment, data indicating the current power consumption of the edge server, or both. The control unit can determine whether there is surplus power in the edge server based on the power status data.

[0030] Based on power status data, the control unit delegates the execution of at least a portion of multiple computing tasks generated within the device to an edge server. For example, if the control unit determines, based on power status data, that there is residual power in the target edge server, it can delegate the execution of computing tasks generated within the vehicle to the corresponding edge server in order to utilize that residual power for processing the computing tasks.

[0031] Based on the aforementioned configuration, the remaining power in the edge server can be utilized efficiently and flexibly.

[0032] Furthermore, power status data can include any data, as long as it can estimate the amount of remaining power in the edge server.

[0033] Alternatively, the more remaining power the edge server has, the more computing tasks or computationally intensive tasks the control unit can delegate to the edge server.

[0034] This is because the more power available, the more computing resources the edge servers can provide.

[0035] Hereinafter, specific embodiments of the present disclosure will be described based on the accompanying drawings. Unless otherwise specified, the hardware configurations, module configurations, and functional configurations described in each embodiment are not intended to limit the scope of the disclosed technology to these configurations.

[0036] First Implementation Method

[0037] System Overview

[0038] Reference Figure 1 An overview of the communication system according to the first embodiment will be described. The communication system according to this embodiment is configured to include an on-board unit 10 mounted on a vehicle, a plurality of edge servers 20 set along the road, and a central server 30.

[0039] Vehicle 1 is a networked vehicle capable of wirelessly communicating with edge server 20. Vehicle 1 is equipped with an on-board unit 10. The on-board unit 10 has the function of collecting sensor data while the vehicle 1 is in motion and sending the collected sensor data to edge server 20.

[0040] Edge server 20 is a server device capable of communicating wirelessly with vehicle 1 (vehicle-mounted device 10) traveling within a defined communication area. Edge server 20 is configured to wirelessly communicate with vehicle 1 within a defined communication area centered on itself. Furthermore, edge server 20 has the function of processing sensor data collected from vehicle 1 and sending the results to central server 30.

[0041] The central server 30 is a server device that performs prescribed data processing based on sensor data collected from multiple vehicles 1. For example, the central server 30 can generate three-dimensional road map data based on image data (images taken by vehicle-mounted cameras) collected from multiple vehicles 1.

[0042] Edge server 20 is positioned between central server 30 and vehicle 1, performing processing to collect sensor data from vehicle 1. Additionally, edge server 20 performs one processing step on the collected sensor data and sends the result to central server 30. This one processing step could be, for example, converting sensor data into intermediate products. For instance, while central server 30 performs processing to generate a 3D road map based on sensor data, edge server 20 could also perform processing to estimate the 3D shape of buildings based on sensor data such as image data.

[0043] Edge server 20 reduces the load on central server 30 and the amount of data flowing in the network by processing information in a geographically close location to vehicle 1.

[0044] In this embodiment, the edge server 20 has a renewable energy-based power generation device, enabling it to operate using electricity generated from renewable energy sources (typically sunlight). The edge server 20 can secure a minimum amount of power from commercial power supplies and also operates using power supplied from the power generation device. That is, if the power generation capacity of the power generation device increases, the amount of power available in the edge server 20 increases, and therefore the computing resources available in the edge server 20 also increase.

[0045] In this embodiment, when the computing resources of the edge server 20 increase to a predetermined value (in the case of generating computing resources exceeding the amount of services that could originally be provided), the edge server 20 uses the increased computing resources to provide services to external devices (e.g., vehicle-mounted devices 10) to perform entrusted computing tasks.

[0046] In this embodiment, the edge server 20 sends data related to its power status to the vehicle 1 traveling within a defined communication area. This data may also include data indicating the power available from the power generation device and data indicating the power consumption of the edge server itself. Based on this data, the vehicle-mounted device 10 in the vehicle 1 determines whether there is any remaining power in the target edge server 20. If there is remaining power in the target edge server 20, the vehicle-mounted device 10 delegates the execution of at least a portion of the computational tasks generated in the vehicle to the edge server 20. This allows for efficient utilization of the remaining power generated in the edge server 20.

[0047] In this embodiment, the edge server 20 performs data processing for generating a 3D road map, namely, periodically collecting sensor data from vehicle 1 and sending it to the central server 30 after each processing step. This processing can be considered the inherent function of the edge server 20. Additionally, during periods when it has surplus power, the edge server 20 responds to requests from vehicle 1 and processes tasks sent from vehicle 1. These tasks can be, for example, computational tasks that analyze data required for autonomous driving by vehicle 1.

[0048] System Composition

[0049] Next, the hardware and software configurations of the various devices that make up the system will be described.

[0050] Figure 2 This is a diagram schematically illustrating an example of the configuration of an on-board device 10 that can be mounted on a vehicle 1.

[0051] The vehicle-mounted device 10 can be configured as a computer with a processor (CPU, GPU, etc.), main storage (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.). The auxiliary storage contains the operating system (OS), various programs, various tables, etc. By executing the programs stored therein, various functions (software modules) consistent with the specified purpose can be achieved, as described later. However, some or all of the functions can also be implemented as hardware modules using hardware circuits such as ASICs or FPGAs.

[0052] The vehicle-mounted device 10 is configured to include a control unit 101, a storage unit 102, a communication unit 103, and an input / output unit 104.

[0053] The control unit 101 is a computing unit that executes a predetermined program to realize various functions of the vehicle-mounted device 10. The control unit 101 can be implemented, for example, by a hardware processor such as a CPU. Alternatively, the control unit 101 may be configured to include RAM, ROM, buffer memory, etc.

[0054] In this embodiment, the control unit 101 of the vehicle-mounted device 10 is configured to include a driving control unit 1011, a task control unit 1012, and a data transmission unit 1013 as software modules. These software modules can also be implemented by the control unit 101 (CPU, etc.) executing programs stored in the storage unit 102.

[0055] The driving control unit 1011 controls the autonomous driving of the vehicle 1. The driving control unit 1011 extracts the information required for autonomous driving by parsing the sensor data obtained from the sensor group 11 (described later), and controls the driving of the vehicle 1 based on this information.

[0056] Specifically, the driving control unit 1011 performs tasks such as analyzing sensor data to identify targets like other vehicles, road signs, lane boundaries, and traffic signals, and determining the vehicle's trajectory and acceleration / deceleration based on the analysis results. The analysis of sensor data can be performed, for example, using a machine learning model. This machine learning model can be segmented into models corresponding to functions such as obstacle detection, traffic signal detection, and lane detection.

[0057] As a machine learning model, deep neural networks (DNNs) can be used, for example. The number of layers in a DNN can also be arbitrarily set according to the object being analyzed. For example, shallow neural networks are sometimes used when analyzing simple features such as lane boundary detection, while deep neural networks are sometimes used when analyzing higher-order concepts such as object identification.

[0058] These tasks can be performed in the control unit 101 or in the edge server 20 (described later).

[0059] The task control unit 1012 determines whether the task generated by the driving control unit 1011 is executed in the device or delegated to the edge server 20.

[0060] Specifically, the task control unit 1012 receives data related to the power status of the edge server 20 (hereinafter referred to as power status data) from the edge server 20 that is capable of communication, and determines, based on the power status data and the power status of the vehicle, whether the task generated by the driving control unit 1011 is executed in the vehicle or the edge server 20.

[0061] For example, if the vehicle's power is insufficient while the edge server 20 has surplus power, the task control unit 1012 can decide to delegate the execution of the target task to the edge server 20. 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.

[0062] Furthermore, if the vehicle has surplus power or the edge server 20 has no surplus power, the task control unit 1012 may decide not to delegate the execution of the object task to the edge server 20. In this case, the task control unit 1012 executes the task within the device (control unit 101).

[0063] The data transmission unit 1013 periodically collects and transmits the data required by the central server 30 to generate a three-dimensional road map. For example, the data transmission unit 1013 periodically performs the process of transmitting the data obtained by parsing the images acquired by the vehicle-mounted camera included in the sensor group 11 to the edge server 20 located near the vehicle.

[0064] The data generated and transmitted by the data transmission unit 1013 is not directly related to the sensor data used by the driving control unit 1011.

[0065] Storage unit 102 is a unit for storing information and is composed of storage media such as RAM, disk, and flash memory. Storage unit 102 stores programs executed by control unit 101, data used by those programs, etc.

[0066] The communication unit 103 is a wireless communication interface used for transmitting and receiving wireless signals between the communication unit 103 and the edge server 20. The communication unit 103 is configured, for example, to transmit and receive wireless signals conforming to standards such as wireless LAN and DSRC. The communication range of the wireless signals can be set, for example, from several hundred meters to several kilometers.

[0067] The input / output unit 104 is a unit that receives input from the occupants of the vehicle and provides them with information. Specifically, the input / output unit 104 consists of a touch panel and its control unit, and a liquid crystal display and its control unit. In this embodiment, the touch panel and the liquid crystal display are configured as a single touch panel display.

[0068] In addition, the vehicle-mounted device 10 is connected to a collection of multiple sensors (sensor group 11) used to acquire sensor data during the driving of the vehicle 1.

[0069] The sensors included in sensor group 11 can be sensors that acquire physical quantities or sensors that acquire image data, etc. Examples of sensors included in the sensor group include sensors that detect vehicle speed, image sensors that acquire visible light images or distance images in front of the vehicle, sensors that acquire position information, radar sensors, LiDAR, etc.

[0070] Next, the composition of edge server 20 will be explained. Figure 3 This is a diagram that schematically illustrates an example of the configuration of an edge server 20 and a central server 30.

[0071] Like the vehicle-mounted device 10, the edge server 20 can be configured as a computer with a processor (CPU, GPU, etc.), main storage device (RAM, ROM, etc.), and auxiliary storage device (EPROM, hard disk drive, removable media, etc.).

[0072] The edge server 20 is configured to include a control unit 201, a storage unit 202, a communication unit 203A (203B) and a power receiving unit 204.

[0073] The control unit 201 is a computing unit that executes prescribed programs to implement various functions of the edge server 20. The control unit 201 can be implemented, for example, using a hardware processor such as a CPU. Alternatively, the control unit 201 may be configured to include RAM, ROM, buffer memory, etc.

[0074] In this embodiment, the control unit 201 of the edge server 20 is configured as a software module, comprising a task processing unit 2011 and a notification unit 2012. These software modules can also be implemented by the control unit 201 (CPU, etc.) executing a program stored in the storage unit 202.

[0075] The task processing unit 2011 executes the prescribed tasks corresponding to the function of the edge server 20. In this embodiment, the tasks executed by the task processing unit 2011 are of the following two types.

[0076] (1) Performing data processing tasks for generating three-dimensional road maps

[0077] This task involves processing the sensor data collected from vehicle 1 and sending the processing result to the central server 30. This task is executed in response to the periodic transmission of sensor data from vehicle 1. The transmission of the processing result to the central server 30 can also be performed at predetermined intervals.

[0078] (2) Tasks delegated from vehicle 1 (onboard device 10)

[0079] As described above, when the vehicle-mounted device 10 has surplus power, it delegates the task to the edge server 20. In response, the edge server 20 (task processing unit 2011) executes the task sent from the vehicle-mounted device 10.

[0080] The notification unit 2012 generates data related to the power status of this device (power status data) and sends it to vehicle 1 (vehicle-mounted device 10) located within the communication area of ​​this device. The power status data is, for example, data that notifies the real-time power consumed by this device (edge ​​server 20) and the real-time power that can be supplied by the power generation device 21 described later.

[0081] Storage unit 202 is a unit for storing information and is composed of storage media such as RAM, disk, and flash memory. Storage unit 202 stores programs executed by control unit 201, data used by those programs, etc.

[0082] Communication Unit 203A is a communication interface used for sending and receiving data between the central server 30 and the communication unit. Communication Unit 203A is, for example, a communication interface conforming to standards such as Ethernet (registered trademark).

[0083] The communication unit 203B is a wireless communication interface for transmitting and receiving wireless signals between itself and the vehicle-mounted device 10. The communication unit 203B is configured, for example, to transmit and receive wireless signals conforming to standards such as Wireless LAN and DSRC.

[0084] The power receiving unit 204 is an interface for receiving power generated by the power generation device 21. The power receiving unit 204 may be configured to include, for example, a converter that constants the output voltage from the solar panel, a converter that converts DC to AC, etc. Furthermore, the power receiving unit 204 can acquire real-time generated power (power that can be supplied to this device) generated by the power generation device 21.

[0085] The power generation device 21 is a device that generates electricity using renewable energy sources, typically an array of solar panels.

[0086] Next, the composition of the central server 30 will be explained.

[0087] Like the edge server 20, the central server 30 can be configured as a computer with a processor (CPU, GPU, etc.), main storage device (RAM, ROM, etc.), and auxiliary storage device (EPROM, hard disk drive, removable media, etc.).

[0088] The central server 30 is configured to include a control unit 301, a storage unit 302, and a communication unit 303.

[0089] The control unit 301 is a computing unit that executes prescribed programs to perform various functions of the central server 30. The control unit 301 can be implemented, for example, using a hardware processor such as a CPU. Alternatively, the control unit 301 may be configured to include RAM, ROM, buffer memory, etc.

[0090] In this embodiment, the control unit 301 of the central server 30 performs the process of generating a three-dimensional road map based on the information collected from the edge server 20.

[0091] Storage unit 302 is a unit for storing information and is composed of storage media such as RAM, disk, and flash memory. Storage unit 302 stores programs executed by control unit 301, data used by those programs, etc.

[0092] The communication unit 303 is a communication interface used for communication with the edge server 20. This communication interface can be a wired interface or a wireless interface.

[0093] Summary of the process

[0094] Next, the processing flow of the edge server 20 and the vehicle-mounted device 10 will be explained. Figure 4 This is a diagram illustrating the flow of data when a task is generated in the vehicle-mounted device 10.

[0095] In this embodiment, vehicle 1 is a vehicle capable of autonomous driving. As described above, the driving control unit 1011 extracts the information required for autonomous driving by parsing the sensor data obtained from the sensor group 11, and controls the driving of vehicle 1 based on this information.

[0096] 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 determining the position of lane boundary lines, detecting other vehicles and determining their type and position, detecting pedestrians or bicycles and determining their position, and determining the display status of traffic signals. Additionally, tasks include determining the vehicle's acceleration / deceleration and trajectory based on the results of analyzing the above information.

[0097] The task generated by the driving control unit 1011 is, for example, object recognition using a neural network. The neural network consists of multiple layers, with nodes in each layer receiving multiple inputs and combining them to generate an output.

[0098] The task generated by the driving control unit 1011 is transferred to the task control unit 1012. Since the task is executed layer by layer by using the inference of the neural network, the task generated by the driving control unit 1011 is a task that can be divided into layers.

[0099] Next, the operation of the mission control unit 1012 will be explained.

[0100] The task control unit 1012 receives power status data from the notification unit 2012 of the edge server 20. Figure 5A This is an example of power status data. As shown in the figure, the power status data includes data related to the edge server's identifier (edge ​​server ID), the power generation of the power generation device 21 attached to the edge server 20, the power consumption of the edge server 20, and the remaining power. This data can also 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 power generation of the power generation device exceeds the power consumption of the edge server, the difference becomes the remaining power. Conversely, if the power generation of the power generation device does not reach the power consumption of the edge server, the remaining power is 0 (none).

[0101] The task control unit 1012 can also periodically receive power status data from the edge server 20.

[0102] Furthermore, the task control unit 1012 obtains data related to the electrical status of the vehicle 1 (e.g., the remaining amount of the drive battery) from the ECU (Electric Control Unit) of the vehicle 1, and determines the subject to perform the task based on the electrical status of the vehicle 1 and the electrical status data received from the edge server 20. For example, if there is no surplus power supplied from the vehicle 1 for performing the task (e.g., if the remaining amount of the drive battery is below a threshold), it is sometimes preferable to delegate the execution of the task to the edge server 20. On the other hand, even in such a case, it is sometimes impossible to delegate the execution of the task if there is no surplus power in the edge server 20.

[0103] Therefore, based on the power status of the vehicle 1 and the power status of the edge server 20, the task control unit 1012 decides whether to execute the task generated by the driving control unit 1011 in the vehicle or in the edge server 20.

[0104] The power status of vehicle 1 and edge server 20 are classified as follows.

[0105] (1) The vehicle is capable of supplying sufficient power for the mission.

[0106] If vehicle 1 is supplied with sufficient power to perform the task, the mission control unit 1012 decides to perform the target task within the vehicle. In this case, the mission control unit 1012 issues an instruction to the driving control unit 1011 to perform the target task.

[0107] (2) When the vehicle is unable to supply enough power for the mission, and the edge server has surplus power.

[0108] For example, if the vehicle's power condition is poor (e.g., the remaining power of the drive battery is below a threshold) but the edge server 20 has remaining power, the task control unit 1012 decides to delegate the execution of the target task to the edge server 20. In this case, the task control unit 1012 sends a delegation to the task processing unit 2011 of the edge server 20 to execute the target task. If the task is completed, the result is returned from the edge server 20 to the task control unit 1012, which then transmits the result to the driving control unit 1011.

[0109] (3) The vehicle is unable to supply enough power for the mission, and the edge server has no power remaining.

[0110] For example, if the vehicle's power condition is poor (e.g., the remaining power of the drive battery is below a threshold) and there is also no remaining power in the edge server 20, the task control unit 1012 decides to execute the target task in the vehicle. In this case, the task control unit 1012 instructs the driving control unit 1011 to execute the target task. Alternatively, the task control unit 1012 may determine that the target task cannot be executed. In this case, the task control unit 1012 may return a message to the driving control unit 1011 stating that the task cannot be executed due to poor power condition, and the driving control unit 1011 may stop autonomous driving as a result.

[0111] Furthermore, under the conditions described in (2) above, the task control unit 1012 can also adjust the amount of tasks to be delegated based on the amount of remaining power in the edge server 20.

[0112] For example, sometimes the driving control unit 1011 generates multiple tasks at the same time. If the amount of tasks to be performed is not taken into account, sometimes the execution of tasks exceeding the amount of remaining power will be delegated.

[0113] Therefore, the task control unit 1012 can acquire data (hereinafter referred to as decision data) that defines the relationship between the remaining power status and the task to be performed, and decide on the task to be performed based on the data.

[0114] Figure 5B This is an example of decision data. This data can also be pre-stored in storage unit 102. In this example, the decision data defines the relationship between the content of classifying the remaining power in edge server 20 and the tasks to be performed. For example, in the case of a "large" remaining power level, all layers of the object recognition task using a neural network are executed in edge server 20. In the case of a "medium" remaining power level, some (or more) layers of the object recognition task are executed in edge server 20. In the case of a "small" remaining power level, only one layer of the object recognition task is executed in edge server 20.

[0115] Furthermore, the illustrated example illustrates the segmentation of processing within each layer of the neural network. However, if the driving control unit 1011 generates multiple tasks, the task control unit 1012 can also determine which task to delegate to the edge server 20 based on the scale of each task (the amount of computation required, etc.).

[0116] In this way, the task control unit 1012 can adjust the number of tasks or the amount of computation to be delegated to the edge server 20 based on the remaining power in the edge server 20. For example, the more power remaining, the more tasks or tasks with a higher computational load can be delegated to the edge server 20.

[0117] Processing flowchart

[0118] Figure 6 This is a flowchart of the processing performed by the vehicle-mounted device 10. This processing is performed when the driving control unit 1011 generates a new task.

[0119] First, in step S11, the task control unit 1012 obtains the latest power status data from the edge server 20. Alternatively, if the task control unit 1012 periodically obtains power status data from the edge server 20, this step can be omitted.

[0120] Next, in step S12, the task control unit 1012 acquires data related to the vehicle's electrical status. This data may include, for example, data indicating the remaining amount of the drive battery, but it is not limited to anything that allows determining whether a new task can be performed in the vehicle. For example, in this step, data related to the current power consumption in the vehicle for performing the task may also be acquired. This data related to the vehicle's electrical status may also be acquired from, for example, an ECU that manages the drive battery.

[0121] Next, in step S13, the task control unit 1012 determines whether the vehicle's power supply for performing the task is strained. For example, if the remaining amount of the vehicle's drive battery is below a specified value, but the current power consumption for performing the task is above a specified value, it can be determined that the power supply for performing the task is strained.

[0122] If the decision in this step is positive, the process jumps to step S14 to determine whether the task execution can be delegated to edge server 20. If the decision in this step is negative, the process jumps to step S16.

[0123] In step S14, the task control unit 1012 determines whether there is any remaining power in the edge server 20 based on the power status data obtained from the edge server 20. The remaining power can be calculated, for example, based on the power generation of the power generation device 21 as represented by the power status data and the power consumption of the edge server 20.

[0124] If the determination is positive in step S14, the process proceeds to step S15. If the determination is negative in step S14, the process proceeds to step S16.

[0125] In step S15, the task control unit 1012 decides to delegate the execution of at least a portion of the generated task to the edge server 20 within a specified range.

[0126] Furthermore, when multiple tasks are executed simultaneously on the edge server 20 by delegating the execution of object tasks to the edge server 20, the task control unit 1012 selects the tasks to be delegated for execution based on the number of object tasks and the computational load. For example, as referred to Figure 5B As explained, the task control unit 1012 can also determine the extent of tasks to be performed by the edge server 20 based on the remaining power in the edge server 20.

[0127] As described above, the edge server 20 according to the first embodiment has a power generation device that utilizes renewable energy and has the function of notifying the power status of the device to the vehicle-mounted device 10.

[0128] In addition, when the power supply in the vehicle is strained, the on-board device 10, referring to the power supply status of the edge server 20, delegates the execution of tasks to the edge server 20 to the extent possible.

[0129] According to this configuration, when there is surplus power generated in the edge server 20, the edge server 20 can be used to handle the tasks generated in the vehicle 1. In power generation equipment that utilizes renewable energy, when there is surplus power that cannot be fully consumed, it cannot be used flexibly. However, according to this embodiment, surplus power can be used effectively and flexibly.

[0130] Variations

[0131] The above-described embodiments are merely an example, and this disclosure can be appropriately modified and implemented without departing from its spirit.

[0132] For example, the processing and methods described in this disclosure can be freely combined and implemented as long as they do not create technical contradictions.

[0133] Furthermore, in the embodiment, an example is given where multiple edge servers 20 have a defined communication area (e.g., a radius of several hundred meters) and communicate with the vehicle 1 within that area. However, the vehicle-mounted device 10 can also communicate with the edge servers 20 located remotely via a cellular network or the like. In this case, the vehicle-mounted device 10 can also receive power status data from the multiple edge servers 20 respectively and determine whether a task can be delegated to each edge server 20.

[0134] Furthermore, in the implementation method, power status data is exemplified as follows: Figure 5AThat method is acceptable, but it is not limited to the method that can determine whether there is any remaining power in the edge server 20.

[0135] In addition, in the implementation, the amount of tasks to be delegated is determined based on the remaining power in the edge server 20, but even if all tasks are delegated and there is still remaining power in the edge server 20, the vehicle device 10 can generate new tasks.

[0136] For example, sometimes increasing the number of layers in a neural network can improve the accuracy of object recognition. For instance, if the task control unit 1012 determines that there is still remaining power on the edge server 20 side even if all tasks generated are delegated to it, it may notify the driving control unit 1011 of this. The driving control unit 1011 may also increase the number of layers in the neural network in response to this notification.

[0137] Based on this configuration, for example, it is possible to achieve improved accuracy in autonomous driving during periods when there is surplus power.

[0138] In addition, the task control unit 1012 can also instruct the driving control unit 1011 to restore the number of layers of the increased neural network when there is no remaining power on the edge server 20 side.

[0139] Furthermore, a process described as being performed by one device can also be executed by multiple devices. Alternatively, a process described as being performed by different devices can be executed by a single device. In a computer system, it is possible to flexibly change the hardware configuration (server configuration) used to implement various functions.

[0140] Furthermore, while the implementation example illustrates a task utilizing a neural network, the task generated in vehicle 1 could also be something else entirely. For instance, if multiple microservices are executed in the vehicle-mounted device 10, the execution entity of the microservices could be changed from the vehicle-mounted device 10 to the edge server 20 based on the remaining power of the edge server 20.

[0141] This disclosure can also be implemented by providing a computer with a computer that has the functions described in the above embodiments, and having one or more processors read and execute the program. Such a computer program can be provided to the computer via a non-transitory computer-readable storage medium that can be connected to the computer's system bus, or via a network. Non-transitory computer-readable storage media 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.

Claims

1. An information processing device mounted on a vehicle, The information processing device has a control unit. The control unit performs: Acquire power status data, which represents the amount of remaining power on edge servers equipped with renewable energy generation devices; and Based on the power status data, the edge server is entrusted to execute at least a portion of the multiple computing tasks generated in the vehicle.

2. The information processing apparatus according to claim 1, wherein, The power status data includes data representing the power that the power generation equipment can supply and data representing the power consumption of the edge server.

3. The information processing apparatus according to claim 2, wherein, The control unit determines the amount of remaining power in the edge server based on the power status data, and if the remaining power exists, it entrusts the edge server to perform at least a portion of the computing tasks.

4. The information processing apparatus according to claim 3, wherein, The more power the edge server has remaining, the more computing tasks the control unit will delegate to the edge server.

5. An information processing system comprising: One or more edge servers equipped with power generation equipment utilizing renewable energy; and Information processing unit mounted on the vehicle The one or more edge servers respectively send data indicating the remaining power, i.e., power status data, to the information processing device. If the power status data received from one or more edge servers indicates that there are edge servers with remaining power, the information processing device delegates the execution of at least a portion of the multiple computing tasks to the corresponding edge server.

Images