Task scheduling method, device and equipment, computer storage medium and program product

Abstract

The invention discloses a task scheduling method and device, equipment, a computer storage medium and a program product, and relates to the technical field of big data. The method comprises the following steps: in response to a task execution request which is sent by a demand side and is used for requesting to execute a target task, calculating a first target computing power and a second target computing power; the first target computing power is the computing power consumed by the central node for executing the target task, and the second target computing power is the computing power provided by the central node for the target task; when the first target computing power and the second target computing power meet a preset computing power condition, calculating effective computing power resources of the multiple pieces of edge node equipment based on position information of the multiple pieces of edge node equipment under the center node; and based on the effective computing power resources, scheduling the edge node equipment in the multiple pieces of edge node equipment to participate in execution of the target task. According to the embodiment of the invention, the anti-pressure capability of the whole system of the central node is effectively improved, so that the execution performance and efficiency of the whole task can be improved.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and in particular relates to a task scheduling method, device, equipment, computer storage medium and program product. Background Art

[0002] Among the existing technologies, the development of 5G (5th-Generation Mobile Communication Technology) and Internet of Things technology provides better communication and connection capabilities for road edge computing. Edge computing nodes can communicate with vehicles, mobile devices, etc. at high speed and low latency through 5G networks, supporting the realization of more application scenarios.

[0003] In the prior art, since everything can be connected, when the computing power of the networked device is idle, it can be used as an edge node to provide excess computing power to the dispatch center for computing power scheduling to ensure that the center has enough computing power to meet the task execution of the demander. However, the prior art solution has the problem of uncontrolled use of edge node computing power or misuse of edge nodes, resulting in low overall system stress resistance. Summary of the invention

[0004] The embodiments of the present application provide a task scheduling method, apparatus, device, computer storage medium and program product, which effectively improve the pressure resistance of the overall system of the central node, thereby improving the execution performance and efficiency of the overall task.

[0005] In a first aspect, an embodiment of the present application provides a task scheduling method, which is applied to a central node. The task scheduling method includes:

[0006] In response to a task execution request sent by a demander for requesting to execute a target task, a first target computing power and a second target computing power are calculated; the first target computing power is the computing power required for the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task;

[0007] When the first target computing power and the second target computing power meet preset computing power conditions, the effective computing power resources of the plurality of edge node devices are calculated based on the location information of the plurality of edge node devices under the central node; the preset computing power conditions at least include that the first target computing power is greater than the second target computing power;

[0008] Based on the effective computing resources, edge node devices among multiple edge node devices are scheduled to participate in executing the target task.

[0009] In some possible implementations, calculating the first target computing power and the second target computing power includes:

[0010] Based on the data scale value of the target task, the resource requirement of the target task, and the number of parallelized tasks of the target task, the initial estimated capacity of the central node to execute the target task is determined; the number of parallelized tasks is the number of subtasks into which the target task is allowed to be split;

[0011] The initial estimated computing power is corrected based on the computing power fluctuation value to obtain a first target computing power;

[0012] The second target computing power is calculated based on the inherent computing power of the central node and the occupied computing power of the central node.

[0013] In some possible implementations, the preset computing power condition further includes: the second target computing power exceeds the computing power threshold; when the first target computing power and the second target computing power meet the preset computing power condition, based on the location information of the plurality of edge node devices under the central node, calculating the effective computing power resources of the plurality of edge node devices, including:

[0014] When the first target computing power is greater than the second target computing power and the second target computing power exceeds the computing power threshold, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node;

[0015] After calculating the first target computing power and the second target computing power, the task scheduling method further includes:

[0016] When the first target computing power is less than the second target computing power, executing the target task;

[0017] When the first target computing power is greater than the second target computing power and the second target computing power does not exceed the computing power threshold, the target task is executed by extending the execution time of the target task.

[0018] In some possible implementations, when the first target computing power is greater than the second target computing power, before the location information of the plurality of edge node devices under the central node is used, the task scheduling method further includes:

[0019] Obtain the first IP (Internet Protocol) address and network access type of X candidate devices, where X is a positive integer;

[0020] Based on the first IP address and the network access type, multiple edge node devices located within the control range of the central node are screened, and location information of the multiple edge node devices is determined.

[0021] In some possible implementations, based on the first IP address and the network access type, screening multiple edge node devices within the control range of the central node, and determining location information of the multiple edge node devices includes:

[0022] Based on the first IP addresses of the X candidate devices, K candidate devices within the control range of the central node are screened, where K and N are positive integers and K is less than or equal to N;

[0023] Determine the second IP addresses of the K candidate devices based on the network access types of the K candidate devices;

[0024] Based on the second IP addresses of the K candidate devices, multiple edge node devices are screened out from the K candidate devices, and the second IP addresses of the multiple edge node devices are determined as the location information of the multiple edge node devices.

[0025] In some possible implementations, each edge node device in the plurality of edge node devices corresponds to a type of node role label in the Y type of node role label type, where Y is a positive integer; based on the location information of the plurality of edge node devices under the central node, the effective computing resources of the plurality of edge node devices are calculated, including:

[0026] Based on the location information of multiple edge node devices, according to the computing power consumption calculation rules corresponding to each node role label type in the Y type node role label type, the computing power resources consumed by the operation of the edge node devices under the Y type node role label type are calculated respectively;

[0027] Based on the computing resources consumed by the edge node devices under the Y-type node role label type, calculate the effective computing resources of multiple edge node devices;

[0028] The Y-type node role label type includes at least one of a sensor node, an intermediate node, and an anchor node.

[0029] In some possible implementations, based on the computing resources consumed by the edge node devices under the Y-type node role label type, the effective computing resources of multiple edge node devices are calculated, including:

[0030] Based on the computing resources consumed by the edge node devices under the Y-type node role label type, the total computing power of multiple edge node devices is calculated;

[0031] Based on the total computing power, the number of edge node devices that need to participate in executing the target task is calculated;

[0032] Based on the number of participants and the second target computing power, the effective computing power resources of multiple edge node devices are calculated.

[0033] In some possible implementations, after calculating the effective computing resources of the plurality of edge node devices, the task scheduling method further includes:

[0034] Generate task execution evaluation information of the target task based on effective computing resources, and send the task execution evaluation information to the demander;

[0035] Based on the effective computing resources, multiple edge node devices are scheduled to participate in executing the target tasks, including:

[0036] When a confirmation message of the task execution evaluation information is received from the demander, an edge node device among multiple edge node devices is scheduled to participate in the execution of the target task based on the effective computing resources.

[0037] Based on the same inventive concept, in a second aspect, an embodiment of the present application provides a task scheduling device, which is applied to a central node. The task scheduling device includes:

[0038] A first computing module, configured to calculate a first target computing power and a second target computing power in response to a task execution request sent by a demander for requesting execution of a target task; the first target computing power is the computing power required for the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task;

[0039] A second calculation module is used to calculate the effective computing power resources of the plurality of edge node devices based on the location information of the plurality of edge node devices under the central node when the first target computing power and the second target computing power meet a preset computing power condition; the preset computing power condition at least includes that the first target computing power is greater than the second target computing power;

[0040] The first scheduling module is used to schedule edge node devices among multiple edge node devices to participate in executing target tasks based on effective computing resources.

[0041] In a third aspect, an embodiment of the present application provides a task scheduling device, the task scheduling device comprising:

[0042] a processor and a memory storing computer program instructions;

[0043] When the processor executes the computer program instructions, the task scheduling method provided in any one of the above embodiments of the present application is implemented.

[0044] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer readable storage medium is stored computer program instructions, and when the computer program instructions are executed by a processor, a task scheduling method provided in any one of the above-mentioned embodiments of the present application is implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a task scheduling method provided in any one of the above-mentioned embodiments of the present application.

[0046] It can be seen from the above description that a task scheduling method, device, equipment, computer storage medium and program product of an embodiment of the present application, after receiving a task execution request sent by the demander, will first calculate the first target computing power required for the central node to execute the target task, and the second target computing power that the central node can provide for the target task. Then, when the first target computing power and the second target computing power meet at least the preset computing power conditions including that the first target computing power is greater than the second target computing power, at least it is determined that there is a computing power gap when the central node executes the target task. In this case, the effective computing power resources of the edge node device are calculated specifically according to the location information of multiple edge node devices under the central node, so as to facilitate the edge node devices required for scheduling according to the effective computing power resources to participate in the execution of the target task.

[0047] The task scheduling method, device, equipment, computer storage medium and program product provided in the embodiment of the present application, after receiving the task execution request from the demander, calculates the first target and the second target computing power, and judges whether the first target computing power and the second target computing power meet the preset computing power condition that the first target computing power is greater than the second target computing power, so as to judge whether it is necessary to call the edge node device, which is equivalent to adding a judgment process for triggering the central node to call the hidden computing power, thereby effectively improving the pressure resistance of the overall system of the central node. In addition, the embodiment of the present application takes into account the network access of the edge node device with existing mobility. Therefore, when the first target computing power and the second target computing power meet the preset computing power conditions, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node. In this way, the mobility attributes of the edge node devices are fully combined to calculate the effective computing power resources, which is conducive to the accurate calculation and task scheduling of the edge computing power, and thus helps to effectively improve the execution performance and efficiency of the overall task. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 It is a flowchart of a task scheduling method provided by an embodiment of the present application;

[0050] Figure 2 This is a flowchart of a scenario implementation of a task scheduling method provided in an embodiment of the present application;

[0051] Figure 3 It is a flowchart of evaluating whether it is necessary to call hidden computing resources provided by an embodiment of the present application;

[0052] Figure 4 This is a schematic diagram of computing power distribution of edge node devices provided in one embodiment of the present application;

[0053] Figure 5 is a structural diagram of a task scheduling device provided in one embodiment of the present application;

[0054] Figure 6 It is a structural diagram of a task scheduling device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0057] As described in the background technology section, the existing technical solutions have the problem of uncontrolled use of edge node computing power, resulting in low overall system stress resistance. Specifically, in the prior art, the dispatch center usually only schedules according to the task priority in the fixed edge node, such as determining the execution order of tasks according to the priority of the tasks, and assigning different priorities to different types of tasks to ensure that important tasks can be executed in a timely manner, or based on time slice-based round-robin scheduling: tasks in the system are executed in turn according to certain time slices to ensure that each task has a chance to be executed, which is suitable for multi-task systems. For example, it is usually scheduling between a fixed cloud server and a fixed edge node.

[0058] However, at present, since traditional edge nodes are all fixed nodes (such as ground computer rooms), when scheduling computing power, there is no need to consider the dynamic change of distance during the movement process, which will cause the problem of changes in computing power transmission overhead. However, with the popularization of mobile terminals, when movable nodes with excess computing power are connected to the network (such as vehicles, drones, and mobile communication terminals), if the mobile properties of the device are not considered, the cost of providing computing power to the central server will be too high, or the location information of the edge device will be inaccurate, so that the edge device that does not belong to the center will be included in the service scope, causing the problem of misuse of computing power. At the same time, in the existing technical solutions, the uncontrolled use of the computing power of edge nodes makes the overall system less able to withstand pressure, and the ability to withstand pressure when dealing with sudden tasks is too weak, causing the system to crash frequently.

[0059] In view of the above, in order to solve the problems of the prior art, the embodiments of the present application provide a task scheduling method, apparatus, device, computer storage medium and program product. It should be noted that the embodiments provided in the present application are not intended to limit the scope of the present application.

[0060] The following first introduces the task scheduling method provided in the embodiment of the present application.

[0061] Figure 1 The flowchart of the task scheduling method provided by an embodiment of the present application is shown. The task scheduling method is applied to a central node, and the central node can be, for example, a central server, etc., which is not strictly limited in the present application. Figure 1 As shown, the task scheduling method includes the following steps:

[0062] S110, in response to a task execution request sent by a demander for requesting execution of a target task, calculating a first target computing power and a second target computing power; the first target computing power is the computing power required for the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task;

[0063] S120, when the first target computing power and the second target computing power meet a preset computing power condition, based on the location information of the plurality of edge node devices under the central node, calculating the effective computing power resources of the plurality of edge node devices; the preset computing power condition at least includes that the first target computing power is greater than the second target computing power;

[0064] S130, based on the effective computing resources, scheduling edge node devices among multiple edge node devices to participate in executing the target task.

[0065] It can be seen from the above description that a task scheduling method of an embodiment of the present application, after receiving a task execution request sent by the demander, will first calculate the first target computing power required for the central node to execute the target task, and the second target computing power that the central node can provide for the target task. Then, when the first target computing power and the second target computing power meet at least the preset computing power conditions including that the first target computing power is greater than the second target computing power, at least it is determined that there is a computing power gap when the central node executes the target task. In this case, the effective computing power resources of the edge node device are calculated specifically based on the location information of multiple edge node devices under the central node, so as to facilitate the edge node devices required for scheduling according to the effective computing power resources to participate in the execution of the target task.

[0066] The task scheduling method provided in the embodiment of the present application, after receiving the task execution request from the demander, calculates the first target and the second target computing power, and determines whether the first target computing power and the second target computing power meet the preset computing power condition that the first target computing power is greater than the second target computing power, so as to determine whether it is necessary to call the edge node device, which is equivalent to adding a judgment process for triggering the central node to call the hidden computing power, thereby effectively improving the pressure resistance of the overall system of the central node. In addition, the embodiment of the present application takes into account the network access of the edge node device with existing mobility. Therefore, when the first target computing power and the second target computing power meet the preset computing power conditions, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node. In this way, the mobility attributes of the edge node devices are fully combined to calculate the effective computing power resources, which is conducive to the accurate calculation and task scheduling of the edge computing power, and thus helps to effectively improve the execution performance and efficiency of the overall task.

[0067] The specific implementation of the above steps 110 to 130 is described in detail below.

[0068] In S110, during specific implementation, the demander sends a task execution request to the central node, and the central node calculates the first target computing power and the second target computing power respectively in response to the task execution request sent by the demander.

[0069] Among them, the first target computing power is the computing power required by the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task.

[0070] The task execution request is used to instruct the execution of the target task. More specifically, the task execution request may include at least one of the task type, task content, task cost, and estimated task execution time of the target task, which is not strictly limited in this embodiment.

[0071] When calculating the first target computing power and the second target computing power, the central node can evaluate the first target computing power required for task execution and the second target computing power that can be provided for the task based on the task type and task content of the target task and the task execution fee that the demander can pay. The specific calculation method can be determined based on actual computing power calculation experience, etc., and is not strictly limited here.

[0072] According to some embodiments of the present application, optionally, more specifically, the calculating the first target computing power and the second target computing power may include:

[0073] Based on the data size value of the target task, the resource requirements of the target task, and the number of parallelized tasks of the target task, determine the initial estimated capacity of the central node to execute the target task;

[0074] The initial estimated computing power is corrected based on the computing power fluctuation value to obtain a first target computing power;

[0075] The second target computing power is calculated based on the inherent computing power of the central node and the occupied computing power of the central node.

[0076] In specific implementation, the central node may first calculate the initial estimated power required to execute the target task, and the resource requirement of the target task may include a specific processor, memory or other hardware resources that the target task may require. The number of parallelized tasks may be, for example, the number of subtasks that the target task is allowed to be split into.

[0077] In some other possible embodiments, other parameters may be introduced: for example, the number of times other central nodes are rejected in order to execute the target task, a preset error correction coefficient, etc. This embodiment does not impose strict restrictions on this.

[0078] After the first target computing power is calculated, the computing power fluctuation value is introduced to correct the initial estimated computing power, taking into account the inaccurate estimated computing power caused by factors such as the network environment and the actual location of the user. Furthermore, the computing power value required for the operation of the central node itself can also be introduced to jointly calculate the first target computing power.

[0079] The inherent computing power can be the total computing power inherent to the computing network managed by the central node, and the occupied computing power can be the computing power actually used by the central node. When calculating the second target computing power, the difference between the inherent computing power and the occupied computing power can be calculated to obtain the second target computing power, which is not strictly limited here.

[0080] In S120, when the first target computing power and the second target computing power meet the preset computing power conditions, the effective computing power resources of the multiple edge node devices are calculated based on the location information of the multiple edge node devices under the central node. The above-mentioned preset computing power conditions at least include that the first target computing power is greater than the second target computing power. The above-mentioned edge node device can be, for example, a vehicle, a drone, or a mobile communication terminal, etc., and this embodiment does not impose strict restrictions on this.

[0081] Among them, when the first target computing power and the second target computing power meet the preset computing power conditions and the first target computing power is greater than the second target computing power, it means that there is a computing power gap in the central node to execute the target task, and it is necessary to mobilize the computing power of the edge nodes in addition to the inherent computing power in the computing network to meet the needs of the demander. In this case, based on the location information of multiple edge node devices under the central node, the effective computing power resources of multiple edge node devices are calculated.

[0082] At the same time, since there are many potential nodes with certain hidden computing resources under the central node, when using and scheduling the hidden computing power, it is necessary to accurately determine the location information of the edge node devices and calculate the effective computing resources.

[0083] Correspondingly, when the above-mentioned first target computing power is less than or equal to the second target computing power, it proves that the central node can provide the demander with computing power that meets the demander's needs, that is, it can meet the demander's needs and complete the execution of the task, and there is no computing power gap at this time.

[0084] It should be noted that the above-mentioned preset computing power conditions in this embodiment may also include other restrictions on the first target computing power, restrictions on the second target computing power, or restrictions on the relationship between the first target computing power and the second target computing power, which will not be elaborated in this embodiment.

[0085] According to some embodiments of the present application, optionally, more specifically, the preset computing power condition further includes: the second target computing power exceeds the computing power threshold; the above step S120, when the first target computing power and the second target computing power meet the preset computing power condition, based on the location information of the multiple edge node devices under the central node, calculating the effective computing power resources of the multiple edge node devices, may include:

[0086] When the first target computing power is greater than the second target computing power and the second target computing power exceeds the computing power threshold, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node;

[0087] After calculating the first target computing power and the second target computing power, the task scheduling method may further include:

[0088] When the first target computing power is less than the second target computing power, executing the target task;

[0089] When the first target computing power is greater than the second target computing power and the second target computing power does not exceed the computing power threshold, the target task is executed by extending the execution time of the target task.

[0090] In this embodiment, the computing power threshold is set in advance based on history or empirical value. When it is determined that the first target computing power is greater than the second target computing power, the magnitude relationship between the second target computing power and the computing power threshold is further compared.

[0091] If the second target computing power does not exceed the computing power threshold, it proves that the computing power gap of the central node is large, and it is necessary to subsequently calculate the effective computing power resources of multiple edge node devices in order to call the edge node devices to participate in the execution of the target task.

[0092] If the second target computing power is greater than the computing power threshold, it proves that the computing power gap of the central node is small. The central node can make up for the gap by appropriately extending the execution time of the target task. The lack of computing power is not easily perceived by the user. In this case, the central node does not need to further coordinate the hidden computing power of the edge node devices.

[0093] According to some embodiments of the present application, optionally, when the first target computing power is greater than the second target computing power, before the location information of multiple edge node devices under the central node, the task scheduling method may further include:

[0094] Obtain the first Internet Protocol IP addresses and network access types of X candidate devices, where X is a positive integer;

[0095] Based on the first IP address and the network access type, multiple edge node devices located within the control range of the central node are screened, and location information of the multiple edge node devices is determined.

[0096] According to some embodiments of the present application, optionally, based on the first IP address and the network access type, screening multiple edge node devices within the control range of the central node, and determining the location information of the multiple edge node devices may include:

[0097] Based on the first IP addresses of the X candidate devices, K candidate devices within the control range of the central node are screened, where K and N are positive integers and K is less than or equal to N;

[0098] Determine the second IP addresses of the K candidate devices based on the network access types of the K candidate devices;

[0099] Based on the second IP addresses of the K candidate devices, multiple edge node devices are screened out from the K candidate devices, and the second IP addresses of the multiple edge node devices are determined as the location information of the multiple edge node devices.

[0100] Exemplarily, the central node can obtain the first IP address and network access type of the candidate device. The first IP address can be the address information provided by the device itself when it accesses the network. The central node first determines whether these edge devices are within the control range of the central node based on the first IP addresses screened by the X candidate devices, thereby screening K candidate devices within the control range of the central node. Then, based on the network access type, the network operator information is determined, and the accurate second IP address is further obtained from the network operator.

[0101] By comparing the first IP address and the second IP address of the above K candidate devices, the inaccurate first IP address is corrected to the accurate second IP address, and then based on the corrected IP addresses of the K candidate devices, the above multiple edge node devices are finally screened and determined, thereby ensuring the reliability of subsequent calls to computing power.

[0102] Furthermore, this embodiment determines the second IP addresses of multiple edge node devices as the location information of multiple edge node devices, so as to realize the calculation of effective computing power resources of edge node devices in combination with the location information, thereby fully ensuring the accuracy and effectiveness of edge node computing power evaluation.

[0103] According to some embodiments of the present application, optionally, each edge node device in the plurality of edge node devices corresponds to a type of node role label in a type of Y node role label, where Y is a positive integer; and based on the location information of the plurality of edge node devices under the central node, calculating the effective computing power resources of the plurality of edge node devices may include:

[0104] Based on the location information of multiple edge node devices, according to the computing power consumption calculation rules corresponding to each node role label type in the Y type node role label type, the computing power resources consumed by the operation of the edge node devices under the Y type node role label type are calculated respectively;

[0105] Based on the computing resources consumed by the edge node devices under the Y-type node role label type, calculate the effective computing resources of multiple edge node devices;

[0106] The Y-type node role label type may include at least one of a sensor node, an intermediate node, and an anchor node.

[0107] In this embodiment, different node role label types can be determined according to the computing power content that the central node needs to provide, or different edge node devices can carry the above node role labels by default. The above node role label types can include sensor nodes, intermediate nodes, anchor nodes, etc., that is, edge node devices can be, for example, sensor nodes, intermediate nodes, or anchor nodes.

[0108] Based on the location information of multiple edge node devices, according to the computing power consumption calculation rules corresponding to each node role label type in the Y type node role label type, the computing power resources consumed by the edge node device under the Y type node role label type are calculated respectively, which may include:

[0109] More specifically, based on the computing resources consumed by the edge node devices under the Y-type node role label type, calculating the effective computing resources of multiple edge node devices may include:

[0110] Based on the computing resources consumed by the edge node devices under the Y-type node role label type, the total computing power of multiple edge node devices is calculated;

[0111] Based on the total computing power, the number of edge node devices that need to participate in executing the target task is calculated;

[0112] Based on the number of participants and the second target computing power, the effective computing power resources of multiple edge node devices are calculated.

[0113] In this embodiment, the total computing power may be calculated based on the computing power resources consumed by the operation of edge node devices with different node role labels and the number of devices with different node role labels in the above-mentioned multiple edge node devices.

[0114] In this way, the number of edge node devices that need to participate in the execution can be determined based on the total computing power, and then based on the number of participants and the second target computing power of the central node, the effective computing power resources that can be provided to execute the target task can be calculated.

[0115] In S130, when specifically implemented, based on the effective computing power resources, the edge node devices in the plurality of edge node devices are scheduled to participate in the execution of the target task. When scheduling, all or part of the plurality of edge node devices may be scheduled to participate in the execution of the target task, which may be flexibly set according to the actual computing power requirements and device scheduling experience, and is not strictly limited here.

[0116] More specifically, in order to improve the satisfaction of the demand side's task request, after calculating the effective computing resources of multiple edge node devices, the task scheduling method may further include:

[0117] Generate task execution evaluation information of the target task based on effective computing resources, and send the task execution evaluation information to the demander;

[0118] Based on the effective computing resources, scheduling edge node devices among multiple edge node devices to participate in executing the target task may include:

[0119] When a confirmation message of the task execution evaluation information is received from the demander, an edge node device among multiple edge node devices is scheduled to participate in the execution of the target task based on the effective computing resources.

[0120] In order to facilitate understanding of the task scheduling method provided in the above embodiment, the above method is described below using a specific scenario embodiment. Figure 2 A flowchart of a scenario implementation of a task scheduling method provided in one embodiment of the present application.

[0121] In this scenario embodiment, if Figure 2 As shown, the implementation scheme of this scenario may specifically include the following steps: Step 1: Initiate a request to execute the task to the central node in the direction of demand; Step 2: The central node receives the request, and preliminarily evaluates the task computing power in the execution request, and at the same time, calculates the computing power gap for executing the task; Step 3: If there is a computing power gap required to execute the task, the central node coordinates the available hidden effective computing power resources in the computing network; Step 4: Based on the effective computing power resources obtained in step 3, re-evaluate the execution parameters of the task initiated by the user, and feed back to the task initiator; Step 5: After the user confirms that the task execution information is acceptable, the system receives and executes the task initiated by the user.

[0122] Specifically, step one: the demand direction initiates a task execution request to the central node; the task execution request is used to request the execution of the target task.

[0123] The task execution request includes the task type, task content, task cost and estimated task execution time.

[0124] Step 2: The central node receives the task execution request and preliminarily evaluates the computing power required to execute the task in the request. At the same time, it calculates the computing power gap for executing the task. Figure 3 , Figure 3 FIG. 1 is a flow chart of evaluating whether hidden computing resources need to be called, provided in an embodiment of the present application. Figure 3 As shown:

[0125] 1. Based on the task type and content, as well as the task execution fee that the demander can pay, the central node evaluates the second target computing power that can be provided for the task and the first target computing power required for task execution.

[0126] (1) The initial estimated capacity of the central node to perform the task is CB:

[0127]

[0128] Where Nt = Nt1 + Nt2 + Nt3, where Nt1 is the number of operations of the task, Nt2 is the complexity of the algorithm, and Nt3 is the number of computational steps;

[0129] Among them, L is the data scale value of the task;

[0130] Wherein, Esend is the resource requirement based on the task, including that the task may require specific processor, memory or other hardware resources;

[0131] Where Cb is the number of parallel tasks of the task (parallelization condition). The number of parallel tasks is the number of subtasks that the target task is allowed to be split into. If the task is allowed to be split into multiple independent subtasks for execution, the number of parallel tasks of the task is high, otherwise it is low. Wherein, the number of subtasks that the task is allowed to be split into is recorded as Cb.

[0132] Wherein, Dr is the number of times other central nodes are rejected when executing the task, and α is a preset error correction coefficient, which is greater than or equal to 1 and less than 2.

[0133] (2) Among them, the actual computing power consumed when the central node task is executed is CN (first target computing power):

[0134] CN=CB*TP+SE

[0135] TP is the fluctuation value of computing power, indicating that the estimated computing power is inaccurate due to factors such as the network environment and the actual location of the user. Therefore, the computing power needs to be corrected. SE is the computing power required for the operation of the central node itself.

[0136] (3) The computing power value CE (second target computing power) that the computing center node can provide for the task is calculated as;

[0137] CE=FULL-CI

[0138] FULL is the total computing power inherent in the computing network managed by the central node (inherent computing power), and CI is the actual computing power used (occupied computing power).

[0139] (4) When the CE calculated in (3) is greater than or equal to CN, it proves that the center can provide the demander with computing power that meets the demander's needs, that is, it can meet the demander's needs and complete the task. At this time, there is no computing power gap; when the CE calculated in (3) is less than CN, it proves that the central node needs to mobilize the computing power of the edge nodes in addition to the inherent computing power in the computing network in order to meet the demander's needs and complete the corresponding task. At this time, it proves that there is a computing power gap.

[0140] 2. Calculate the computing power gap for executing tasks based on the current available computing power of the central node to determine whether the central node needs to coordinate hidden computing power resources in the computing network;

[0141] (1) Evaluate whether the CE value in 1 is greater than the threshold CC (computing power threshold). If it is less than CC, it means that the computing power gap is large. The lack of computing power will be directly reflected in the task execution process and results, and users can perceive it. In this case, the system needs to further coordinate hidden computing power in the computing power network.

[0142] The threshold CC is preset based on historical or human experience.

[0143] (2) If it is greater than , it proves that the computing power gap is small. The system can make up for the gap by appropriately extending the task execution time. At the same time, the computing power gap is not perceived by the user. At this time, the system does not need to further coordinate hidden computing power.

[0144] Step 3: If there is a gap in the computing power required to perform the task, the central node coordinates the available hidden effective computing power resources ET within the computing network;

[0145] In this section, since there are many potential nodes with certain hidden computing resources in the system, when using and scheduling the hidden computing power, it is necessary to accurately determine the location of the edge node device, the resources available to the edge node device, and finally determine the effective computing resources ET that the edge node device can provide.

[0146] 1. Determine the precise location information of all edge node devices within the control range of the central node;

[0147] Obtain the IP address and network access type of the edge node device. Based on IP address 1 (first IP address), determine whether the edge devices are within the range controlled by the central node, determine the network operator information based on the network access type, and further obtain the accurate IP address 2 (second IP address) from the network operator, compare IP address 1 and IP address 2, and correct the specific location information of the edge node device based on IP address 2.

[0148] This step is mainly to correct the inaccurate IP address 1 to the accurate IP address 2 based on the network access type.

[0149] According to the range controlled by the central node, it is determined whether IP address 2 is within the control range of the central node, and finally a plurality of edge node devices within the control range are obtained.

[0150] 2. Based on the specific location of the edge node device, calculate the call ratio of the call computing power and obtain the call computing power value given to the central node;

[0151] Among them, the edge node device needs to provide computing power for the central node to assist the central node in completing the corresponding tasks, which requires the transmission of computing power, and the transmission of computing power needs to rely on each routing node. Therefore, there is a computing power difference between the computing power actually provided by the edge node device and the computing power that can reach the central node. The edge node device must provide more computing power than required based on the computing power required by the central node to support the central node to complete the corresponding tasks. Then, the edge node device needs to calculate the final computing power call ratio based on the computing power content that the center needs to provide, combined with the computing power loss. Among them, different edge node devices may carry the above-mentioned node role labels by default. The above-mentioned node role label types may include sensor nodes, intermediate nodes, and anchor nodes, that is, edge node devices may be devices such as sensor nodes, intermediate nodes, or anchor nodes. The computing power consumption calculation rules corresponding to sensor nodes, intermediate nodes, or anchor nodes are different, as follows:

[0152] See below Figure 4 , Figure 4 This is a schematic diagram of the computing power distribution of an edge node device provided in one embodiment of the present application.

[0153] (1) Calculate the computing power loss during transmission based on the energy consumption of sensor nodes Es, intermediate nodes Ef and anchor nodes Ea under the edge nodes;

[0154] 1) Computing resources consumed by sensor node operation E s ;

[0155] Among them, the sensor node is responsible for sensing the environmental information of the area, periodically collecting data, and uploading the sampled data as the starting point of data transmission. The energy consumption of the sensor node includes generating l bits of data and transmitting the data to the node at a distance Ds.

[0156] The calculation formula for the sensor computing power resource consumption is:

[0157] E s =N t l(E send +C r D s 2 )

[0158] Among them, N t represents the number of nodes that the sensor node needs to send, l represents the amount of data transmitted, and E send represents the energy consumption of sending 1 bit of data, C r Denotes the energy consumption coefficient, D s Indicates the distance between the sensor node and the target node.

[0159] 2) Computing resources consumed by the intermediate node operation Ef ;

[0160] As a medium for multi-hop transmission, the intermediate node is responsible for transferring data and does not generate new data. The energy consumption of the intermediate node includes receiving data from other nodes and transmitting data to the node at a distance D. f The node sends data.

[0161] The calculation formula for the computing power resources consumed by the intermediate node operation is:

[0162] E f =N f,r oeLh rece +N f,s l(E send +C r D f 2 )

[0163] Where N f,r Indicates the number of nodes receiving data at the intermediate node, E rece Indicates the resource consumption of receiving 1 bit of data, E send N is the resource consumption for sending 1 bit of data. f,s Indicates the number of nodes that the intermediate node needs to send, C r Denotes the energy consumption coefficient, D f Indicates the distance between the forwarding node and the target node.

[0164] 3) Computing resources consumed by anchor node operation E a

[0165] The anchor node is responsible for receiving data from nodes in the coverage area and temporarily storing it, waiting for access from the mobile receiver and uploading all data to the receiver. The energy consumption of the anchor node includes receiving data from internal nodes and transmitting data to the mobile receiver within a distance D. toSE Mobile receiver.

[0166] The calculation formula for the computing power resources consumed by anchor node operation is:

[0167] E a =N sub oeLh rece +R total (E send +C r D toSC 2 )

[0168] Among them, N sub represents the number of internal network nodes covered by the anchor node, l represents the amount of data transmitted, and E rece Represents the energy consumption of receiving 1 bit of data, R total represents the total amount of data received from internal nodes, Esend To represent the resource consumption of sending 1 bit of data, C r Indicates energy consumption coefficient D toSC , represents the distance between the intermediate node and the anchor node.

[0169] (1) Calculate the total amount of computing power that needs to be provided based on the computing power loss of edge node devices and the computing power required by the central node;

[0170] According to the above calculation method of computing power consumption of nodes under different edge devices, the total computing power consumption model of edge node devices can be obtained:

[0171] E total =Q s E s +Q f E f +Q a E a , further decomposed to get the following formula;

[0172]

[0173] Part 1: Q s represents the number of sensor nodes, N t represents the number of nodes that the sensor node needs to send, l represents the amount of data transmitted, Q f Represents the number of intermediate nodes, N f,r Indicates the number of nodes receiving data at the intermediate node, N f,s Indicates the number of nodes that the intermediate node needs to send, E f The computing resources consumed by the intermediate nodes, E s For E send As described above, Q a Represents the number of anchor nodes, N sub represents the number of internal network nodes covered by the anchor point, E rece Indicates the resource consumption of receiving 1 bit of data.

[0174] The area where the wireless sensor network is located is approximately a square, M represents the side length of the square area, and h represents the average number of hops from other nodes to the anchor node.

[0175] (2) Based on the total computing power of the edge node devices, the central node calculates the number of edge node devices that need to participate in this task;

[0176] Central node calculation Make its derivative equal to 0, that is, we can get the optimal number N of edge node devices participating in this task:

[0177]

[0178] (3) The central node calculates the computing power P that the edge node devices are expected to provide based on the number of participating edge device nodes;

[0179]

[0180] Among them, CL(i) is the pre-computation power that each edge node device can provide, ɑ is the proportional loss coefficient, i is a different edge node device, CE is the computing power value that the computing center node can provide for the task, and E total It is the total computing power consumption of edge node devices.

[0181] 1. Further evaluate the available edge nodes and calculate the effective computing resources that can be provided at present;

[0182] Since the computing power of edge device nodes is affected by a series of conditions such as hardware performance, energy management method, operating environment, network delay, etc., the effective computing power resources provided by the edge devices may be lost. In order to accurately provide computing power data, it is necessary to calculate the effective computing power resources here.

[0183] E T =ɑ*P

[0184] Among them, ɑ is the proportional loss coefficient.

[0185] 2. Summarize the effective computing resources ET that can be provided by all edge node devices.

[0186] Step 4: Based on the effective computing resources ET obtained in step 3, the execution parameters of the task initiated by the user are evaluated again and fed back to the task initiator;

[0187] The central node evaluates the time required to execute the demander's task and the task cost information based on the effective computing power resources ET, and generates task execution evaluation information, and feeds back the task execution evaluation information to the task initiator, i.e. the demander, so that the demander can confirm the task execution parameters.

[0188] Step 5: After the user confirms that the task execution evaluation information is acceptable, the system receives and executes the task initiated by the user.

[0189] In the embodiment of this scenario, the central node provided in this solution receives the request and preliminarily evaluates the task computing power in the execution request. At the same time, a specific method for calculating the computing power gap of the execution task is provided to effectively evaluate whether it is necessary to call the overall process steps of hidden computing power resources, which makes up for the lack of corresponding computing power scheduling and evaluation solutions in the prior art. Improve performance and efficiency. And the solution can dynamically allocate and manage computing power according to real-time computing needs and resource utilization, thereby improving overall performance and efficiency. This will enable enterprises to better cope with high-load and large-scale computing tasks, complete tasks faster, and improve business processing speed and capabilities.

[0190] The judgment process for triggering the call of hidden computing power provided in this embodiment provides innovations in specific technical implementations, provides a judgment process for triggering the call of hidden computing power, and effectively improves the trigger accuracy. In addition, when the total computing power is lost, this embodiment combines multiple data dimension features, and then provides a method for calculating the total amount of computing power in a mobile scenario, which solves the problem of mis-scheduling of computing power and uncontrolled use of hidden computing power in the prior art, resulting in too low pressure resistance of the central node, and provides a new idea for computing power scheduling in the field of edge computing. Through this embodiment, the computing resources of different edge servers can be reasonably allocated and utilized, reducing idleness and waste of resources and reducing the operating costs of enterprises. By completing some computing tasks on edge servers, the dependence on cloud computing resources can be reduced, thereby saving the cost of cloud computing services.

[0191] Furthermore, in some embodiments, computing tasks can also be automatically assigned to the best edge server based on the real-time network status and server load. This will improve the reliability and stability of the system, reduce the risk of failure or interruption, and ensure the continuity and stable operation of the business. In addition, some computing tasks can be completed on the edge server, and sensitive data and personal privacy data can be processed and stored at the edge to reduce the risk of data transmission during the network. This helps to improve data security and privacy protection, comply with the requirements of data protection regulations, and increase user trust. In addition, computing tasks can also be assigned to the nearest edge server during task scheduling to achieve low-latency real-time computing. This is particularly important for scenarios with high real-time requirements such as IoT applications, smart transportation, and video surveillance. With this capability, enterprises can provide more efficient and accurate services to meet user needs.

[0192] Based on the task scheduling method provided in the above embodiment, out of the same inventive concept, the present application also provides a task scheduling device corresponding to the above task scheduling method. Figure 5 A detailed introduction to the task scheduling device is given.

[0193] Figure 5A structural schematic diagram of a task scheduling device provided in an embodiment of the present application is shown, which is applied to a central node. Figure 5 The task scheduling device 500 shown includes:

[0194] The first calculation module 510 is used to calculate the first target computing power and the second target computing power in response to the task execution request sent by the demander for requesting to execute the target task; the first target computing power is the computing power consumed by the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task;

[0195] A second calculation module 520 is used to calculate the effective computing power resources of the plurality of edge node devices based on the location information of the plurality of edge node devices under the central node when the first target computing power and the second target computing power meet a preset computing power condition; the preset computing power condition at least includes that the first target computing power is greater than the second target computing power;

[0196] The first scheduling module 530 is used to schedule edge node devices among multiple edge node devices to participate in executing the target task based on effective computing resources.

[0197] It can be seen from the above description that a task scheduling device in an embodiment of the present application, by setting corresponding functional modules, will first calculate the first target computing power required for the central node to execute the target task and the second target computing power that the central node can provide for the target task after receiving the task execution request sent by the demander. Then, when the first target computing power and the second target computing power meet at least the preset computing power conditions including that the first target computing power is greater than the second target computing power, at least it is determined that there is a computing power gap when the central node executes the target task. In this case, the effective computing power resources of the edge node device are calculated specifically according to the location information of the multiple edge node devices under the central node, so as to facilitate the edge node devices required for scheduling according to the effective computing power resources to participate in the execution of the target task.

[0198] The task scheduling device provided in the embodiment of the present application, after receiving the task execution request from the demander, calculates the first target and the second target computing power, and determines whether the first target computing power and the second target computing power meet the preset computing power condition that the first target computing power is greater than the second target computing power, so as to determine whether it is necessary to call the edge node device, which is equivalent to adding a judgment process for triggering the central node to call the hidden computing power, thereby effectively improving the pressure resistance of the overall system of the central node. In addition, the embodiment of the present application takes into account the network access of the edge node device with existing mobility. Therefore, when the first target computing power and the second target computing power meet the preset computing power conditions, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node. In this way, the mobility attributes of the edge node devices are fully combined to calculate the effective computing power resources, which is conducive to the accurate calculation and task scheduling of the edge computing power, and thus helps to effectively improve the execution performance and efficiency of the overall task.

[0199] According to some embodiments of the present application, optionally, the first calculation module 510 calculates the first target computing power and the second target computing power, which may include:

[0200] The first determination submodule can be used to determine the initial estimated capacity of the central node to execute the target task based on the data scale value of the target task, the resource requirement of the target task, and the number of parallelized tasks of the target task; the number of parallelized tasks is the number of subtasks into which the target task is allowed to be split;

[0201] A first correction submodule may be used to correct the initial estimated computing power based on the computing power fluctuation value to obtain a first target computing power;

[0202] The first calculation submodule can be used to calculate the second target computing power according to the inherent computing power of the central node and the occupied computing power of the central node.

[0203] According to some embodiments of the present application, optionally, the preset computing power condition further includes that the second target computing power exceeds the computing power threshold; the second calculation module 520, when the first target computing power and the second target computing power meet the preset conditions, calculates the effective computing power resources of the plurality of edge node devices based on the location information of the plurality of edge node devices under the central node, which may include:

[0204] When the first target computing power is greater than the second target computing power and the second target computing power exceeds the computing power threshold, the effective computing power resources are calculated based on the location information of multiple edge node devices under the central node;

[0205] After calculating the first target computing power and the second target computing power, the task scheduling device may further include:

[0206] The first execution module may be used to execute the target task when the first target computing power is less than the second target computing power;

[0207] The second execution module can be used to execute the target task by extending the execution time of the target task when the first target computing power is greater than the second target computing power and the second target computing power does not exceed the computing power threshold.

[0208] According to some embodiments of the present application, optionally, when the first target computing power is greater than the second target computing power, before the location information of multiple edge node devices under the central node is determined, the task scheduling device may further include:

[0209] A first acquisition module may be used to acquire first Internet Protocol IP addresses and network access types of X candidate devices, where X is a positive integer;

[0210] The first screening module can be used to screen multiple edge node devices within the control range of the central node based on the first IP address and the network access type, and determine the location information of the multiple edge node devices.

[0211] According to some embodiments of the present application, optionally, the first screening module screening multiple edge node devices within the control range of the central node based on the first IP address and the network access type, and determining the location information of the multiple edge node devices may include:

[0212] The first screening submodule may be used to screen K candidate devices within the control range of the central node based on the first IP addresses of the X candidate devices, where K and N are positive integers and K is less than or equal to N;

[0213] The second determination submodule may be used to determine the second IP addresses of the K candidate devices based on the network access types of the K candidate devices;

[0214] The second screening submodule may be used to screen out multiple edge node devices from the K candidate devices based on the second IP addresses of the K candidate devices, and determine the second IP addresses of the multiple edge node devices as the location information of the multiple edge node devices.

[0215] According to some embodiments of the present application, optionally, each edge node device in the above-mentioned multiple edge node devices corresponds to a type of node role label in Y type of node role label type, where Y is a positive integer; based on the location information of the multiple edge node devices under the central node, calculating the effective computing power resources of the multiple edge node devices may include:

[0216] The second calculation submodule can be used to calculate the computing power resources consumed by the operation of the edge node devices under the Y type of node role label type based on the location information of multiple edge node devices and according to the computing power consumption calculation rules corresponding to each type of node role label type in the Y type of node role label type;

[0217] The third calculation submodule can be used to calculate the effective computing resources of multiple edge node devices based on the computing resources consumed by the edge node devices under the Y type node role label type;

[0218] The Y-type node role label type may include at least one of a sensor node, an intermediate node, and an anchor node.

[0219] According to some embodiments of the present application, optionally, the third computing submodule calculates the effective computing resources of multiple edge node devices based on the computing resources consumed by the edge node device under the Y-type node role label type, and may include:

[0220] The first calculation unit may be used to calculate the total amount of computing power of multiple edge node devices based on the computing power resources consumed by the edge node devices under the Y type node role label type;

[0221] The second calculation unit may be used to calculate the number of edge node devices that need to participate in executing the target task based on the total computing power;

[0222] The third computing unit may be used to calculate effective computing resources of multiple edge node devices based on the number of participants and the second target computing power.

[0223] According to some embodiments of the present application, optionally, after calculating the effective computing resources of the plurality of edge node devices, the task scheduling apparatus may further include:

[0224] The first sending module may be used to generate task execution evaluation information of the target task based on the effective computing resources, and send the task execution evaluation information to the demander;

[0225] The first scheduling module 530, based on the effective computing resources, scheduling edge node devices among the plurality of edge node devices to participate in executing the target task, may include:

[0226] When a confirmation message of the task execution evaluation information is received from the demander, the edge node devices among the multiple edge node devices are scheduled to participate in the execution of the target task based on the effective computing resources.

[0227] Based on the task scheduling method provided in the above embodiment, out of the same inventive concept, the present application also provides a task scheduling device corresponding to the above task scheduling method. Figure 6 A detailed introduction to the task scheduling equipment is given.

[0228] See below Figure 6 , Figure 6 It is a structural diagram of a task scheduling device provided in one embodiment of the present application.

[0229] The task scheduling device may include a processor 601 and a memory 602 storing computer program instructions.

[0230] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0231] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0232] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0233] The processor 601 implements any one of the task scheduling methods in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0234] In one example, the data task scheduling device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0235] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0236] Bus 610 includes hardware, software or both, and the parts of task scheduling equipment are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0237] The task scheduling device executes the task scheduling method in the embodiment of the present application, thereby realizing the task scheduling method described in the embodiment of the present application.

[0238] In addition, in combination with the task scheduling method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the task scheduling methods in the above embodiment is implemented.

[0239] Based on the task scheduling method in the above embodiments, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the task scheduling method provided in any one of the above embodiments of the present application.

[0240] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0241] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0242] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0243] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0244] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A task scheduling method, characterized in that: Applied to the central node, the method includes: In response to a task execution request sent by a demander for requesting to execute a target task, a first target computing power and a second target computing power are calculated; the first target computing power is the computing power required for the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task; When the first target computing power and the second target computing power meet a preset computing power condition, based on the location information of the plurality of edge node devices under the central node, the effective computing power resources of the plurality of edge node devices are calculated; the preset computing power condition at least includes that the first target computing power is greater than the second target computing power; Based on the effective computing resources, an edge node device among the multiple edge node devices is scheduled to participate in executing the target task.

2. The method according to claim 1, characterized in that The calculating the first target computing power and the second target computing power includes: Determine the initial estimated capacity of the central node to execute the target task based on the data scale value of the target task, the resource requirement of the target task, and the number of parallelized tasks of the target task; the number of parallelized tasks is the number of subtasks into which the target task is allowed to be split; Correcting the initial estimated computing power based on the computing power fluctuation value to obtain the first target computing power; The second target computing power is calculated according to the inherent computing power of the central node and the occupied computing power of the central node.

3. The method according to claim 1, characterized in that The preset computing power condition also includes: the second target computing power exceeds a computing power threshold; when the first target computing power and the second target computing power meet the preset computing power condition, based on the location information of the multiple edge node devices under the central node, calculating the effective computing power resources of the multiple edge node devices, including: When the first target computing power is greater than the second target computing power and the second target computing power exceeds a computing power threshold, the effective computing power resources are calculated based on location information of a plurality of edge node devices under the central node; After calculating the first target computing power and the second target computing power, the method further includes: When the first target computing power is less than the second target computing power, executing the target task; When the first target computing power is greater than the second target computing power and the second target computing power does not exceed the computing power threshold, the target task is executed by extending the execution time of the target task.

4. The method according to claim 1, characterized in that In the case where the first target computing power is greater than the second target computing power, before based on the location information of a plurality of edge node devices under the central node, the method further includes: Obtain the first Internet Protocol IP addresses and network access types of X candidate devices, where X is a positive integer; Based on the first IP address and the network access type, the plurality of edge node devices located within the control range of the central node are screened, and location information of the plurality of edge node devices is determined.

5. The method according to claim 4, characterized in that The screening of the plurality of edge node devices within the control range of the central node based on the first IP address and the network access type, and determining the location information of the plurality of edge node devices, includes: Based on the first IP addresses of the X candidate devices, K candidate devices located within the control range of the central node are screened, where K and N are positive integers and K is less than or equal to N; Determine the second IP addresses of the K candidate devices based on the network access types of the K candidate devices; Based on the second IP addresses of the K candidate devices, the multiple edge node devices are screened out from the K candidate devices, and the second IP addresses of the multiple edge node devices are determined as the location information of the multiple edge node devices.

6. The method according to claim 1, characterized in that Each edge node device in the plurality of edge node devices corresponds to a type of node role label in a type of Y node role label, where Y is a positive integer; and calculating effective computing resources of the plurality of edge node devices based on location information of the plurality of edge node devices under the central node includes: Based on the location information of the multiple edge node devices, and according to the computing power consumption calculation rules corresponding to each type of node role label type in the Y type of node role label type, respectively calculate the computing power resources consumed by the operation of the edge node devices under the Y type of node role label type; Calculate the effective computing resources of the plurality of edge node devices based on the computing resources consumed by the edge node devices under the Y type node role label type; The Y-type node role label type includes at least one of a sensor node, an intermediate node and an anchor node.

7. The method according to claim 6, characterized in that The calculating the effective computing resources of the plurality of edge node devices based on the computing resources consumed by the edge node devices under the Y-type node role label type includes: Based on the computing resources consumed by the edge node devices under the Y-type node role label type, the total computing power of the multiple edge node devices is calculated; Based on the total computing power, the number of edge node devices required to participate in executing the target task is calculated; Based on the number of participants and the second target computing power, effective computing power resources of the multiple edge node devices are calculated.

8. The method according to any one of claims 1 to 7, characterized in that: After calculating the effective computing resources of the plurality of edge node devices, the method further includes: Based on the effective computing resources, generating task execution evaluation information of the target task, and sending the task execution evaluation information to the demander; The step of scheduling edge node devices among the plurality of edge node devices to participate in executing the target task based on the effective computing power resources includes: Upon receiving a confirmation message from the demander regarding the task execution evaluation information, an edge node device among the plurality of edge node devices is scheduled to participate in executing the target task based on the effective computing resources.

9. A task scheduling device, characterized in that: Applied to a central node, the device comprises: A first computing module, configured to calculate a first target computing power and a second target computing power in response to a task execution request sent by a demander for requesting execution of a target task; the first target computing power is the computing power required for the central node to execute the target task, and the second target computing power is the computing power that the central node can provide for the target task; a second calculation module, configured to calculate effective computing resources of the plurality of edge node devices based on location information of the plurality of edge node devices under the central node when the first target computing power and the second target computing power meet a preset computing power condition; the preset computing power condition at least includes that the first target computing power is greater than the second target computing power; The first scheduling module is used to schedule edge node devices among the multiple edge node devices to participate in executing the target task based on the effective computing power resources.

10. A task scheduling device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the task scheduling method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the task scheduling method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the task scheduling method according to any one of claims 1 to 8.

Images