Resource allocation method, apparatus, device, storage medium and computer program product

Abstract

The application discloses a resource allocation method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining a current computing task, a task attribute of the current computing task, a current load capacity of a computing device in an edge-cloud network, a historical computing task and a task attribute of the historical computing task; determining a target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing task; dividing computing resources required by the target historical computing task into a plurality of computing resource packages according to the target historical computing task and the current load capacity; and distributing the plurality of computing resource packages to the computing device in the edge-cloud network by using an iterative algorithm until a preset iteration stop condition is met, so as to obtain a target resource allocation strategy. According to the embodiment of the application, the speed of cloud computing resource allocation optimization can be improved, and the efficiency of resource allocation optimization can be improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of cloud computing, and particularly relates to a resource allocation method and device, equipment, a storage medium and a computer program product. BACKGROUND

[0002] With the popularization of 5G networks, cloud computing technology is gradually applied to all aspects of social life. Cloud computing usually relies on edge devices to perform computing work with small data volume and low computation requirements, and relies on central servers to perform computing work with large data volume and high computation requirements, thereby completing huge data computing work. However, since each computing device has different load characteristics, and the difficulty of different computing tasks and the time consumed by the computing tasks are different, it is necessary to optimize the above computing resource allocation method.

[0003] The existing cloud computing resource allocation method has the problems of slow cloud computing resource allocation optimization speed and low resource allocation optimization efficiency. SUMMARY

[0004] The embodiments of the present application provide a resource allocation method, device, equipment, storage medium and computer program product, which can improve the efficiency of cloud computing resource allocation optimization.

[0005] In a first aspect, the embodiments of the present application provide a resource allocation method, which comprises:

[0006] obtaining a current computing task, a task attribute of the current computing task, a current load capacity of a computing device in an edge-cloud network, a historical computing task and a task attribute of the historical computing task;

[0007] determining a target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing task;

[0008] dividing computing resources required by the target historical computing task into a plurality of computing resource packages according to the target historical computing task and the current load capacity;

[0009] allocating the plurality of computing resource packages to the computing device in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, to obtain a target resource allocation strategy.

[0010] In a second aspect, the embodiments of the present application provide a resource allocation device, which comprises:

[0011] an obtaining module configured to obtain a current computing task, a task attribute of the current computing task, a current load capacity of a computing device in an edge-cloud network, a historical computing task and a task attribute of the historical computing task;

[0012] determining a target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing task;

[0013] dividing the computing resources required by the target historical computing task into a plurality of computing resource packages according to the target historical computing task and the current load capacity;

[0014] allocating the plurality of computing resource packages to the computing devices in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, to obtain a target resource allocation strategy.

[0015] In a third aspect, an embodiment of the present application provides a resource allocation device, which comprises a processor and a memory storing computer program instructions; and the processor implements the resource allocation method of the first aspect when executing the computer program instructions.

[0016] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores computer program instructions; and the computer program instructions are executed by a processor to implement the resource allocation method of the first aspect.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, which comprises instructions executed by a processor of an electronic device to cause the electronic device to perform the resource allocation method of the first aspect.

[0018] The method, device, equipment, storage medium and computer program product for computing resource scheduling can obtain a target historical computing task with the highest similarity to a current computing task. Since the target historical computing task has high similarity to the current computing task, the computing resources required by the target historical computing task can be equivalent to the computing resources required by the current computing task. Therefore, dividing the computing resources required by the target historical computing task into a plurality of computing resource packages can be equivalent to dividing the computing resources of the current computing task into the computing resource packages. Therefore, the subsequent iterative algorithm based on the computing resource packages divided from the computing resources required by the target historical computing task can establish a relatively optimal resource allocation strategy in the early stage. Since the relatively optimal resource allocation strategy is established in the early stage, the number of iterations required to obtain the optimal resource allocation strategy is reduced, and the speed and efficiency of resource allocation optimization are improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced. Those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0020] Figure 1 is a flowchart of a resource allocation method provided by an embodiment of the present application;

[0021] Figure 2 is a flowchart of an iterative algorithm for allocating multiple computing resource packages to computing devices in an edge-cloud network provided by an embodiment of the present application;

[0022] Figure 3 is a structural diagram of a resource allocation apparatus provided by an embodiment of the present application;

[0023] Figure 4 is a structural diagram of a resource allocation apparatus provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] The features and exemplary embodiments of various aspects of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to explain the present application, but not to limit the present application. The present application can be implemented without some of the specific details described below. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.

[0025] It should be noted that, in this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the phrase "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0026] With the popularization of 5G networks, cloud computing technology is gradually applied to all aspects of social life. Commonly used cloud computing, such as edge-cloud network computing method, mainly relies on edge devices to perform computing work with small data volume and low computing requirements, and central servers to perform computing work with large data volume and high computing requirements, thereby completing large data computing work. Such allocation method not only enables high responsiveness in local area, but also significantly reduces the pressure of network communication.

[0027] However, due to the different load characteristics of each computing device itself, and the difficulty of different computing tasks and the time length consumed by the computing tasks cannot be directly known, the existing cloud computing resource allocation method cannot directly and efficiently optimize the allocation of cloud computing resources, and there is a problem of slow speed and low efficiency of resource allocation optimization.

[0028] To solve the problems in the prior art, the embodiments of the present application provide a resource allocation method, device, equipment, storage medium and computer program product. The method, device, equipment, storage medium and computer program product for computing resource scheduling provided by the embodiments of the present application can obtain a target historical computing task with the highest similarity to the current computing task. Since the target historical computing task has high similarity to the current computing task, the computing resources required by the target historical computing task can be equivalent to the computing resources required by the current computing task. Therefore, dividing the computing resources required by the target historical computing task into multiple computing resource packages can be equivalent to dividing the computing resources of the current computing task into computing resource packages. Therefore, the subsequent iterative algorithm based on the computing resource packages divided according to the computing resources required by the target historical computing task can establish a relatively optimal resource allocation strategy at the initial stage. Since a relatively optimal resource allocation strategy is established at the initial stage, the number of iterations required to obtain the optimal resource allocation strategy is reduced, and the speed and efficiency of resource allocation optimization are improved.

[0029] First, the resource allocation method provided by the embodiments of the present application will be introduced.

[0030] Figure 1 A flowchart of a resource allocation method provided by an embodiment of the present application is shown. As shown in Figure 1 The method can include the following steps: S101-S104.

[0031] S101: obtaining a current computing task, a task attribute of the current computing task, a current load capacity of a computing device in an end-edge-cloud network, a historical computing task and a task attribute of the historical computing task.

[0032] In the existing cloud computing resource allocation method, a random and disordered iterative method is mostly used for the allocation and optimization of computing resources, and the attribute differences between different computing tasks and the capability differences of different computing devices in the end-edge-cloud network are not considered, and the efficiency of resource allocation and iterative optimization is not high.

[0033] In the embodiments of the present application, the attribute differences between different computing tasks and the capability differences of different computing devices in the end-edge-cloud network are considered, and the resource allocation optimization is performed by referring to the historical computing task.

[0034] Based on the differences in attributes between different computing tasks, the differences in capabilities of different computing devices in the edge-cloud network, and the consideration of historical computing tasks, in this step, by obtaining the current computing task to be calculated, the task attributes of the current computing task, the current load capacity of the computing devices in the edge-cloud network, and the historical computing tasks and their task attributes, a subsequent resource allocation optimization iteration process is further performed.

[0035] By considering the differences in attributes between different computing tasks, the differences in capabilities of different computing devices in the edge-cloud network, and the historical computing tasks participating in the resource allocation optimization process in the resource allocation iteration optimization process, the number of iterations of the resource allocation optimization process is reduced, and the efficiency of the resource allocation optimization is improved.

[0036] In one embodiment, the current computing task to be calculated can be a computing service requirement from a total server, which can include multiple computing subtasks, each having a corresponding task type and data volume.

[0037] S102: Determine the target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing task.

[0038] Based on the above consideration of historical computing tasks, in order to improve the availability of historical computing tasks, in this step, the historical computing task with the highest similarity to the current computing task is selected as the target historical computing task to participate in the resource allocation optimization process.

[0039] Among them, the historical computing task with the highest similarity to the current computing task is determined by judging the similarity between the task attributes of the current computing task and the task attributes of the historical computing task.

[0040] By taking the historical computing task with the highest similarity to the current computing task as the target historical computing task, the target historical computing task can represent the current computing task to some extent, so the optimal resource allocation strategy obtained based on the target historical computing task can be better applied to the current computing task to be calculated.

[0041] S103: Divide the computing resources required by the target historical computing task into multiple computing resource packs according to the target historical computing task and the current load capacity;

[0042] The prior art randomly divides the computing resources required by the current computing task to be calculated, which may result in the situation that the divided computing resources cannot be completely loaded by the computing devices to which the computing resources are allocated, causing waste of the load capacity of the computing devices.

[0043] Therefore, in this step, the computing resources required by the target historical computing task are divided into multiple computing resource packages according to the current load accommodation capacity of the computing devices in the edge-cloud network.

[0044] By dividing the computing resources required by the target historical computing task into multiple computing resource packages according to the current load accommodation capacity of the computing devices in the edge-cloud network, the redundancy or deficiency of the load accommodation capacity of the computing devices can be effectively avoided, the utilization rate of the computing devices is improved, so that the subsequent process of allocating the computing resource packages is more efficient, and the efficiency of the computing resource allocation optimization is improved.

[0045] S104: The multiple computing resource packages are allocated to the computing devices in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, and a target resource allocation strategy is obtained.

[0046] In order to obtain an optimal resource allocation strategy, in this step, based on the divided computing resource packages, the computing resource packages are continuously allocated to the computing devices in the edge-cloud network according to a preset iteration stopping condition by using an iterative algorithm, and finally a target resource allocation strategy is obtained, which is used as an optimal resource allocation strategy. The preset iteration stopping condition is used to optimize the computing resource allocation strategy in the direction of gradually tending to balance.

[0047] The computing resource allocation optimization method in this step can establish a relatively optimal resource allocation strategy in the early stage by using an iterative algorithm based on the divided computing resource packages, so that the number of iterations is reduced, the speed of resource allocation optimization is improved, and the efficiency of resource allocation optimization is improved.

[0048] In the embodiments of the present application, the current computing task, the task attribute of the current computing task, the current load accommodation capacity of the computing devices in the edge-cloud network, the historical computing task and the task attribute of the historical computing task are obtained, the target historical computing task with the highest similarity to the current computing task is determined according to the task attribute of the current computing task and the task attribute of the historical computing task, the computing resources required by the target historical computing task are divided into multiple computing resource packages according to the target historical computing task and the current load accommodation capacity, and the multiple computing resource packages are allocated to the computing devices in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, and a target resource allocation strategy is obtained. In the embodiments of the present application, the computing resources required by the target historical computing task are divided into multiple computing resource packages, and the subsequent iterative algorithm is performed based on the divided computing resource packages, so that a relatively optimal resource allocation strategy can be established in the early stage, the number of iterations is reduced, the speed of resource allocation optimization is improved, and the efficiency of resource allocation optimization is improved.

[0049] In some embodiments, in the step S101 of acquiring the current computing task, the task attribute of the current computing task, the current load accommodation capability of the computing device in the end-to-edge-to-cloud network, the historical computing task and the task attribute thereof, the task attribute comprises: the task type, the data volume and the number of splittable computing resource packages.

[0050] In some embodiments, the step S102 of determining the target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing task can comprise:

[0051] obtaining the difference degree between the current computing task and the historical computing task according to the task type, the data volume and the number of splittable computing resource packages of the current computing task and the task type, the data volume and the number of splittable computing resource packages of the historical computing task;

[0052] determining the historical computing task with the minimum difference degree to the current computing task as the target historical computing task with the highest similarity to the current computing task.

[0053] In this step, since the task type belongs to the category of nouns and cannot be directly quantified into a numerical value, it can be marked as an integer numerical value starting from 0 according to the similarity level of the task type by a preset manner.

[0054] For example, the logic of the encryption algorithm and the decryption algorithm is similar, so the level difference of the encryption algorithm and the decryption algorithm can be marked as 1; the convolution operation and the statistical operation are both based on matrix operation, so the level difference of the convolution operation and the statistical operation can also be marked as 1; and the operation logic of the encryption operation and the convolution operation is completely different, so the level difference of the encryption operation and the convolution operation can be marked as ≥2.

[0055] Of course, the numerical values shown above are exemplary representations of the present application and do not limit the protection scope of the present application. For the specific numerical value, it can be determined according to the number of task types contained in the current computing task.

[0056] The task type, the data volume and the number of splittable computing resource packages of the computing task are all key parameters participating in the computing resource allocation optimization process, and the difference degree between the current computing task and the historical computing task is calculated based on the task type, the data volume and the number of splittable computing resource packages of the current computing task and the historical computing task, and then the similarity between the two is judged, so that the similarity judgment has higher accuracy.

[0057] In one embodiment, the difference degree between the current computing task and the historical computing task can be calculated by the following formula according to the task type, the data volume and the number of splittable computing resource packages of the current computing task and the historical computing task:

[0058] Δ i = α1|type0-type i |+ α2|data0-data i |+ α3|number0-number i |(1)

[0059] wherein, Δ i is the difference degree of the i-th historical computing task and the current computing task, α1, α2 and α3 are correction parameters, type0, data0 and number0 are the task type, data volume and number of splittable computing resource packages of the current computing task respectively, type i , data i and number i are the task type, data volume and number of splittable computing resource packages of the i-th historical computing task respectively.

[0060] In some embodiments, in the step S101 of obtaining the current computing task, the task attribute of the current computing task, the current load accommodation capacity of the computing device in the edge-cloud network, the historical computing task and the task attribute thereof, the current load accommodation capacity of the computing device in the edge-cloud network can comprise the following steps:

[0061] For each computing device:

[0062] S111: obtaining the initial computing capability, the initial network transmission speed and the initial load bearing capacity of the computing device;

[0063] S112: performing standardization calculation on the initial computing capability, the initial network transmission speed and the initial load bearing capacity of the computing device respectively to obtain the standardized computing capability, the standardized network transmission speed and the standardized load bearing capacity;

[0064] S113: obtaining the current load accommodation capacity of the computing device according to the standardized computing capability, the standardized network transmission speed and the standardized load bearing capacity.

[0065] Wherein, the standardization calculation can be to preset a maximum value for the above-mentioned initial computing capability, initial network transmission speed and initial load bearing capacity respectively, to determine the percentage of the above-mentioned initial computing capability, initial network transmission speed or initial load bearing capacity relative to the respective corresponding preset maximum value, to obtain the standardized computing capability, the standardized network transmission speed and the standardized load bearing capacity.

[0066] The current load capacity of the computing device is calculated according to the normalized computing capacity, network transmission speed and load bearing capacity, thereby improving the accuracy of the calculation result of the current load capacity.

[0067] In one embodiment, the step S113 can be calculated by the following formula:

[0068]

[0069] wherein rate' t is the normalized computing capacity of the tth computing device, speed' t is the normalized network transmission speed of the tth computing device, load t is the normalized load bearing capacity of the tth computing device.

[0070] In some embodiments, the step S103 of dividing the computing resources required by the target historical computing task into a plurality of computing resource packages according to the target historical computing task and the current load capacity can include:

[0071] According to the greatest common divisor of the current load capacity, the computing capacity of each computing resource package is divided;

[0072] According to the data volume of the target historical computing task, the number N of the divided computing resource packages is calculated, wherein N is a positive integer;

[0073] The computing resources required by the target historical computing task are divided into N computing resource packages.

[0074] The prior art divides the computing resources iteratively by using a traditional genetic algorithm, and the initial resource allocation strategy generated is poor, thereby resulting in a large number of iterations required to obtain the optimal resource allocation strategy, and leading to a low efficiency of generating the optimal resource allocation strategy.

[0075] Therefore, the embodiments of the present application divide the computing capacity of each computing resource package according to the greatest common divisor of the current load capacity, and further combine the data volume of the historical computing task to calculate the number of the divided computing resource packages.

[0076] According to the greatest common divisor of the current load capacity, the computing capacity of each computing resource package is divided, which can effectively avoid the redundancy or deficiency of the load capacity of the computing device, improve the utilization rate of the computing device, and thereby make the subsequent process of allocating the computing resource package more efficient, and further improve the efficiency of the optimization of the computing resource allocation.

[0077] In some embodiments, as Figure 2As shown, step S104: a plurality of computing resource packages are allocated to computing devices in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, and a target resource allocation strategy is obtained, which can include the following steps:

[0078] S1041: a plurality of computing resource packages are allocated to a first computing device in the edge-cloud network to obtain an initial resource allocation strategy, and the first computing device is a computing device with the largest current load accommodation capacity in the edge-cloud network;

[0079] S1042: a first computing resource package allocated to the first computing device is taken out and allocated to a second computing device to obtain an updated resource allocation strategy, and the second computing device is a computing device with the smallest current load accommodation capacity in the edge-cloud network;

[0080] S1043: the energy consumption indexes of the initial resource allocation strategy and the updated resource allocation strategy are calculated according to an energy consumption index calculation formula to obtain a first energy consumption index and a second energy consumption index;

[0081] S1044: whether the updated resource allocation strategy is better than the initial resource allocation strategy is determined according to the first energy consumption index and the second energy consumption index;

[0082] S1045: in the case where the updated resource allocation strategy is not better than the initial resource allocation strategy, it is determined whether there is a third computing device with a current load accommodation capacity greater than that of the second computing device in the edge-cloud network;

[0083] S1046: in the case where there is no third computing device, the initial resource allocation strategy is determined as the target resource allocation strategy.

[0084] In order to determine the optimal resource allocation strategy, the initial resource allocation strategy of the initial extreme allocation mode is gradually iterated in the balanced direction by steps S1041 to S1046.

[0085] Firstly, in step S1041, all the divided computing resource packages are allocated to the computing device with the largest current load accommodation capacity to obtain the initial resource allocation strategy, and the initial resource allocation strategy is a relatively extreme allocation strategy.

[0086] In step S1042, on the basis of the initial resource allocation strategy, in order to make the resource allocation strategy gradually tend to be balanced, the computing resource package allocated to the computing device with the largest current load accommodation capacity is taken out and allocated to the computing device with the smallest current load accommodation capacity, so that the resource allocation strategy is optimized in the direction of gradually tending to be balanced.

[0087] In this step, the process of calculating the allocation of resource packages is an ordered process. Compared with the traditional disordered iterative process of resource allocation, this step can reduce the redundancy of the number of iterations and improve the speed of iterative optimization of the resource allocation process.

[0088] The computing resource package taken from and allocated from the computing device with the largest current load capacity can be one or more.

[0089] In steps S1043 to S1044, since computing resource packages allocated to the computing device with the largest current load capacity are continuously taken out and allocated to the computing device with the smallest current load capacity, if no conditions are imposed, the updated resource allocation strategy will tend to another extreme allocation strategy after reaching a balance.

[0090] Therefore, this application defines an energy consumption index for resource allocation strategies. The energy consumption index is used to evaluate the merits of the initial and updated resource allocation strategies. The energy consumption index of the initial and updated resource allocation strategies is used as a limiting condition for continuing or stopping resource allocation optimization, thereby making the resource allocation optimization process directional and reducing the number of iterations in the resource allocation optimization process.

[0091] In step S1045, when the updated resource allocation strategy is no longer better than the initial resource allocation strategy based on the energy consumption index, it indicates that the computing device with the smaller current load capacity has exceeded its load. In this case, the update can be withdrawn, and another computing device with the smallest current load capacity can be selected. Alternatively, the process can proceed to step S1046, where if there is no other computing device with the smallest current load capacity, the iteration process ends, and the last resource allocation strategy before the update is withdrawn is determined as the target resource allocation strategy, thus obtaining the optimal resource allocation strategy.

[0092] The absence of other computing devices with the lowest current load capacity indicates that all computing devices are nearing saturation, and the resource allocation strategy has reached maximum balance. Therefore, the iteration process can be terminated, and the optimal resource allocation strategy can be obtained.

[0093] In one embodiment, in step S1042, the first computing resource package allocated to the first computing device is retrieved and allocated to the second computing device. The first computing resource package can be a single computing resource package.

[0094] In some embodiments, such as Figure 2 As shown, step S104: Using an iterative algorithm to allocate multiple computing resource packages to computing devices in the edge-cloud network until a preset iteration stop condition is met, the target resource allocation strategy is obtained, which may include the following steps:

[0095] S1047: In the presence of the third computing device, updating the target third computing device to the second computing device, and updating the updated resource allocation strategy to the initial resource allocation strategy; the target third computing device is the computing device with the minimum current load capacity among the third devices;

[0096] S1048: returning to step S1042.

[0097] In order to gradually iterate the initial resource allocation strategy of the initially formed extreme allocation mode in the balanced direction, in the case that the computing device with the minimum current load capacity has been saturated, then the computing device with the minimum current load capacity among other computing devices is found, the found computing device with the minimum current load capacity among other computing devices is updated to the second computing device, and the resource allocation optimization iteration is continued, thereby ensuring the reliability of the iteration of the initial resource allocation strategy in the balanced direction.

[0098] In some embodiments, the multiple computing resource packages are allocated to the computing devices in the end-to-edge cloud network by using the iterative algorithm until the preset iteration stopping condition is met, and the target resource allocation strategy is obtained, which can include the following steps:

[0099] S1049: In the case that the updated resource allocation strategy is better than the initial resource allocation strategy, updating the updated resource allocation strategy to the initial resource allocation strategy, and returning to taking out the first computing resource package allocated to the first computing device and allocating it to the second computing device.

[0100] In the case that the updated resource allocation strategy is better than the updated resource allocation strategy, at this time, step S1042 can be returned to continue to execute the process of taking out the first computing resource package allocated to the first computing device and allocating it to the second computing device, thereby ensuring that the resource allocation strategy is gradually iterated in the balanced direction.

[0101] In some embodiments, step S1043: calculating the energy consumption index of the initial resource allocation strategy and the updated resource allocation strategy according to the energy consumption index calculation formula, to obtain a first energy consumption index and a second energy consumption index, can include the following steps:

[0102] Obtaining the computing cost, computing duration and computing amount of each computing device in the initial resource allocation strategy, and obtaining the computing cost, computing duration and computing amount of each computing device in the updated resource allocation strategy;

[0103] According to the computing cost of each computing device in the initial resource allocation strategy, a comprehensive computing cost of the initial resource allocation strategy is calculated to obtain a first comprehensive computing cost; according to the computing cost of each computing device in the updated resource allocation strategy, a comprehensive computing cost of the updated resource allocation strategy is calculated to obtain a second comprehensive computing cost;

[0104] According to the computing duration of each computing device in the initial resource allocation strategy, a comprehensive computing duration of the initial resource allocation strategy is calculated to obtain a first comprehensive computing duration; according to the computing duration of each computing device in the updated resource allocation strategy, a comprehensive computing duration of the updated resource allocation strategy is calculated to obtain a second comprehensive computing duration;

[0105] According to the computing amount of each computing device in the initial resource allocation strategy, a balance degree of the initial resource allocation strategy is calculated to obtain a first balance degree; according to the computing amount of each computing device in the updated resource allocation strategy, a balance degree of the updated resource allocation strategy is calculated to obtain a second balance degree;

[0106] The first comprehensive computing cost, the first comprehensive computing duration and the first balance degree are weighted and summed to obtain a first energy consumption index; the second comprehensive computing cost, the second comprehensive computing duration and the second balance degree are weighted and summed to obtain a second energy consumption index.

[0107] Since the computing resource package allocated to the computing device with the largest current load accommodation capacity is continuously taken out and allocated to the computing device with the smallest current load accommodation capacity, if no condition is limited, the updated resource allocation strategy will tend to another extreme allocation strategy after tending to balance.

[0108] Therefore, the energy consumption index of the resource allocation strategy is defined, the advantages and disadvantages of the initial resource allocation strategy and the updated resource allocation strategy are evaluated through the energy consumption index, and the limitation condition for continuing and stopping the resource allocation optimization is determined by judging the high and low of the energy consumption index of the initial resource allocation strategy and the updated resource allocation strategy, so that the process of resource allocation optimization has directionality, and the number of iterations in the process of resource allocation optimization is reduced.

[0109] The first comprehensive computing cost, the first comprehensive computing duration, the first balance degree of the initial resource allocation strategy and the second comprehensive computing cost, the second comprehensive computing duration, the second balance degree of the updated resource allocation strategy are calculated by obtaining the computing cost, the computing duration and the computing amount of each computing device in the initial resource allocation strategy and the updated resource allocation strategy, so as to obtain the first energy consumption index and the second energy consumption index.

[0110] The computing cost, the computing duration, and the computing amount of each computing device in the resource allocation strategy can well represent the energy consumption of the computing device. Based on the computing cost, the computing duration, and the computing amount of each computing device, the energy consumption index of the resource allocation strategy is calculated, which can ensure the accuracy of the energy consumption index result of the resource allocation strategy.

[0111] The balance degree indicates the balance degree of the load of each computing device in the resource allocation strategy to accommodate the computing resource package, and the percentage of the computing resource package occupying each computing device can be used to represent the balance degree.

[0112] In one embodiment, the energy consumption index calculation formula can include:

[0113]

[0114] Wherein, E is the energy consumption index, θ1, θ2, θ3 are weight values, x n is an indication vector of whether the nth computing device is called, x n = 0 indicates that the computing device is not called, x n = 1 indicates that the computing device is called, C n is the computing cost of the nth computing device, T max is the maximum computing time of all computing devices to complete the current computing task, B is the balance degree of the resource allocation strategy, and N is the number of computing devices actually called by the resource allocation strategy.

[0115] In some embodiments, on the basis of any of the above embodiments, the resource allocation method can further include the following steps:

[0116] a. obtaining the iteration number of steps S1041 to S1049, and comparing the iteration number with a preset number threshold;

[0117] b. in the case where the iteration number is less than the preset number threshold, returning to step S1041.

[0118] Although each computing resource package is divided according to the current load accommodation capacity of the computing device in the end-to-edge cloud network, in fact, for different computing tasks, the processing speed of different computing devices is different. Therefore, randomly selecting a computing resource package from the first computing device and allocating it to the second computing device can achieve a certain degree of balance degree division, but there is still a certain randomness. Therefore, the embodiment of the application judges the iteration number of the iteration process of step S104. In the case where the iteration number is less than the preset number threshold, the optimal resource allocation strategy obtained in the current iteration is abandoned, and step S104 is implemented again to obtain a new optimal resource allocation strategy, thereby avoiding the randomness of the above-mentioned target resource allocation strategy.

[0119] In some embodiments, on the basis of any of the above embodiments, the resource allocation method can further include the following steps:

[0120] A. obtaining a set of similar historical computing tasks; wherein the set of similar historical computing tasks includes a plurality of historical computing tasks that have a similarity to the current computing task satisfying a preset similarity threshold condition;

[0121] B. selecting a historical computing task from the set of historical computing tasks as a target historical computing task;

[0122] C. for each target historical computing task:

[0123] dividing the computing resources required by the target historical computing task into a plurality of computing resource packs according to the target historical computing task and the current load capacity of the computing devices in the edge-cloud network;

[0124] using an iterative algorithm to allocate the plurality of computing resource packs to the computing devices in the edge-cloud network until a preset iteration stopping condition is met to obtain a target resource allocation strategy;

[0125] D. among the target resource allocation strategies obtained for each target historical computing task, determining the target resource allocation strategy with the lowest energy consumption index as the final target resource allocation strategy.

[0126] Although the historical computing task with the highest similarity can represent the current computing task to some extent, there is inevitably some difference between the two, so the resource allocation strategy determined by the corresponding historical computing task naturally also has some uncertainty.

[0127] Therefore, a plurality of historical computing tasks satisfying the preset similarity threshold condition can be formed into a set of similar historical computing tasks, and then the resource allocation method is performed on each historical computing task in the set of similar historical computing tasks to obtain an optimal resource allocation strategy. After matching the similar historical computing tasks, the optimal resource allocation strategy can be obtained faster, thereby improving the efficiency of resource allocation optimization.

[0128] Figure 3 is a structural schematic diagram of a resource allocation apparatus 300 provided by an embodiment of the present application. As shown in the figure, the apparatus can include a data acquisition module 310, a determination module 320, a division module 330, and an allocation module 340. Figure 3

[0129] The acquisition module 310 is configured to acquire the current computing task, the task attributes of the current computing task, the current load capacity of the computing devices in the edge-cloud network, historical computing tasks, and their task attributes. ​

[0130] The determining module 320 is configured to determine a target historical computing task with the highest similarity to the current computing task according to the task attributes of the current computing task and the historical computing tasks.

[0131] The dividing module 330 is configured to divide the computing resources required by the target historical computing task into a plurality of computing resource packages according to the target historical computing task and the current load capacity.

[0132] The allocating module 340 is configured to allocate the plurality of computing resource packages to the computing devices in the edge-cloud network by using an iterative algorithm until a preset iteration stopping condition is met, to obtain a target resource allocation strategy.

[0133] The method, device, equipment, storage medium and computer program product for computing resource scheduling can obtain a target historical computing task with the highest similarity to the current computing task. Since the target historical computing task has high similarity to the current computing task, the computing resources required by the target historical computing task can be equivalent to the computing resources required by the current computing task. Therefore, dividing the computing resources required by the target historical computing task into a plurality of computing resource packages can be equivalent to dividing the computing resources of the current computing task into computing resource packages. Therefore, the subsequent iterative algorithm based on the computing resource packages divided from the computing resources required by the target historical computing task can establish a relatively optimal resource allocation strategy at the initial stage. Since a relatively optimal resource allocation strategy is established at the initial stage, the number of iterations required to obtain the optimal resource allocation strategy is reduced, and the speed and efficiency of resource allocation optimization are improved.

[0134] In some embodiments, the determining module 320 is further configured to obtain the difference degree between the current computing task and the historical computing tasks according to the task type, data volume and number of splittable computing resource packages of the current computing task, and the task type, data volume and number of splittable computing resource packages of the historical computing tasks.

[0135] The historical computing task with the smallest difference degree to the current computing task is determined as the target historical computing task with the highest similarity to the current computing task.

[0136] In some embodiments, the resource allocation apparatus 300 further includes a computing module.

[0137] The computing module is configured to, for each computing device:

[0138] obtain the initial computing capability, initial network transmission speed and initial load capacity of the computing device;

[0139] The initial computing capability, the initial network transmission speed and the initial load bearing capacity of the computing device are normalized respectively to obtain normalized computing capability, normalized network transmission speed and normalized load bearing capacity;

[0140] The current load accommodation capability of the computing device is obtained according to the normalized computing capability, the normalized network transmission speed and the normalized load bearing capacity.

[0141] In some embodiments, the dividing module 330 is further configured to divide the computing capability of each computing resource package according to the greatest common divisor of the current load accommodation capability; calculate the number N of the divided computing resource packages according to the data volume of the target historical computing task, wherein N is a positive integer; and divide the computing resource required by the target historical computing task into N computing resource packages.

[0142] In some embodiments, the allocating module 340 is further configured to allocate the plurality of computing resource packages to a first computing device in the edge-cloud network to obtain an initial resource allocation strategy, the first computing device being a computing device with the largest current load accommodation capability in the edge-cloud network.

[0143] The first computing resource package allocated to the first computing device is removed and allocated to a second computing device to obtain an updated resource allocation strategy, the second computing device being a computing device with the smallest current load accommodation capability in the edge-cloud network.

[0144] The energy consumption indexes of the initial resource allocation strategy and the updated resource allocation strategy are calculated according to an energy consumption index calculation formula to obtain a first energy consumption index and a second energy consumption index.

[0145] The updated resource allocation strategy is determined to be superior to the initial resource allocation strategy according to the first energy consumption index and the second energy consumption index.

[0146] In a case where the updated resource allocation strategy is not superior to the initial resource allocation strategy, it is determined whether there is a third computing device with a current load accommodation capability greater than that of the second computing device in the edge-cloud network.

[0147] In a case where there is no third computing device, the initial resource allocation strategy is determined as a target resource allocation strategy.

[0148] In some embodiments, the allocating module 340 is further configured to, in a case where there is a third computing device, update the target third computing device to the second computing device and update the updated resource allocation strategy to the initial resource allocation strategy, the target third computing device being a computing device with the smallest current load accommodation capability among the third computing devices.

[0149] The first computing resource package allocated to the first computing device is removed and allocated to the second computing device.

[0150] In some embodiments, the distribution module 340 is further configured to update the updated resource allocation strategy to the initial resource allocation strategy and return to distribute the first computing resource package in the first computing device to the second computing device if the updated resource allocation strategy is better than the initial resource allocation strategy.

[0151] In some embodiments, the computing module is further configured to obtain the computing cost, the computing duration and the computing amount of each computing device in the initial resource allocation strategy, and obtain the computing cost, the computing duration and the computing amount of each computing device in the updated resource allocation strategy.

[0152] According to the computing cost of each computing device in the initial resource allocation strategy, the comprehensive computing cost of the initial resource allocation strategy is calculated to obtain a first comprehensive computing cost. According to the computing cost of each computing device in the updated resource allocation strategy, the comprehensive computing cost of the updated resource allocation strategy is calculated to obtain a second comprehensive computing cost.

[0153] According to the computing duration of each computing device in the initial resource allocation strategy, the comprehensive computing duration of the initial resource allocation strategy is calculated to obtain a first comprehensive computing duration. According to the computing duration of each computing device in the updated resource allocation strategy, the comprehensive computing duration of the updated resource allocation strategy is calculated to obtain a second comprehensive computing duration.

[0154] According to the computing amount of each computing device in the initial resource allocation strategy, the balance degree of the initial resource allocation strategy is calculated to obtain a first balance degree. According to the computing amount of each computing device in the updated resource allocation strategy, the balance degree of the updated resource allocation strategy is calculated to obtain a second balance degree.

[0155] The first comprehensive computing cost, the first comprehensive computing duration and the first balance degree are weighted and summed to obtain a first energy consumption index. The second comprehensive computing cost, the second comprehensive computing duration and the second balance degree are weighted and summed to obtain a second energy consumption index.

[0156] Figure 3 Each module in the apparatus shown can implement each step in the method and achieve the corresponding technical effects. For brevity, the description is not repeated here. Figure 1 Each module in the apparatus shown can implement each step in the method and achieve the corresponding technical effects. For brevity, the description is not repeated here.

[0157] Figure 4 A hardware structure schematic diagram of a resource allocation device provided by an embodiment of the present application is shown.

[0158] The resource allocation device can include a processor 401 and a memory 402 storing computer program instructions.

[0159] In particular, the processor 401 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits that embody the embodiments of the present application.

[0160] The memory 402 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 402 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 402 can include removable or non-removable (or fixed) media, where appropriate. Where appropriate, the memory 402 can be internal or external to the integrated gateway disaster recovery device. In particular embodiments, the memory 402 is non-volatile, solid-state memory.

[0161] In particular embodiments, the memory can include read-only memory (ROM), random access memory (RAM), a magnetic disk storage medium, an optical storage medium, a flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to perform operations described with reference to the methods according to an aspect of the present application.

[0162] The processor 401 implements any of the resource allocation methods in the above embodiments by reading and executing computer program instructions stored in the memory 402.

[0163] In one example, the resource allocation device can further include a communication interface 403 and a bus 410. Wherein, as shown, the processor 401, the memory 402, the communication interface 403 are connected through the bus 410 and complete the communication between each other. Figure 4

[0164] The communication interface 403 is mainly used to realize the communication between each module, device, unit and / or equipment in the embodiments of the present application.

[0165] ​Bus 410 includes a hardware, software, or both that couples components of the online data traffic metering device to each other. As an example without limitation, bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 410 can include one or more buses. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0166] In addition, in combination with the resource allocation method in the above embodiments, the embodiments of the present application can provide a computer storage medium for implementation. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement any of the resource allocation methods in the above embodiments.

[0167] The embodiments of the present application also provide a computer program product, comprising a computer program, the computer program being executed by a processor to implement any of the resource allocation methods in the above embodiments.

[0168] It needs to be clear that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are 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 steps, after understanding the spirit of the present application.

[0169] The functional blocks shown in the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, functional cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0170] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0171] The above-described aspects of the present application can be implemented in hardware, software, firmware or any combination thereof. The above-described aspects of the present application can be implemented using a computer program product comprising a computer readable storage medium having computer program code embodied therewith. The computer program product can be executed on a processor of a computer, a mobile device, a personal computer, a server, a network device, or any other device capable of executing computer program code. The computer program code comprises instructions for implementing the above-described aspects of the present application. The computer program code can be executed on a processor of a computer, a mobile device, a personal computer, a server, a network device, or any other device capable of executing computer program code.

[0172] The above is merely a specific implementation of the present application. As can be clearly understood by a person skilled in the art from the above description, for the convenience and brevity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited in this way, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application.

Claims

1. A resource allocation method, characterized in that, include: Obtain the current computing task, the task attributes of the current computing task, the current load capacity of computing devices in the edge-cloud network, and historical computing tasks and their task attributes; Based on the task attributes of the current computing task and the historical computing task, determine the target historical computing task with the highest similarity to the current computing task; Based on the target historical computing task and the current load capacity, the computing resources required by the target historical computing task are divided into multiple computing resource packages; An iterative algorithm is used to allocate the multiple computing resource packages to computing devices in the edge-cloud network until a preset iteration stop condition is met, thereby obtaining the target resource allocation strategy. The method of allocating the multiple computing resource packages to computing devices in the edge-cloud network using an iterative algorithm until a preset iteration stop condition is met, thereby obtaining the target resource allocation strategy, includes: The multiple computing resource packages are allocated to the first computing device in the edge-cloud network to obtain an initial resource allocation strategy. The first computing device is the computing device with the largest current load capacity in the edge-cloud network. The first computing resource package allocated to the first computing device is extracted and allocated to the second computing device to obtain an updated resource allocation strategy; the second computing device is the computing device with the smallest current load capacity in the edge-cloud network; The energy consumption indices of the initial resource allocation strategy and the updated resource allocation strategy are calculated according to the energy consumption index calculation formula to obtain the first energy consumption index and the second energy consumption index. Based on the first energy consumption index and the second energy consumption index, determine whether the updated resource allocation strategy is better than the initial resource allocation strategy; If the updated resource allocation strategy is not better than the initial resource allocation strategy, determine whether there is a third computing device in the edge-cloud network with a larger current load capacity than the second computing device. In the absence of a third computing device, the initial resource allocation strategy is determined as the target resource allocation strategy.

2. The resource allocation method according to claim 1, characterized in that, The task attributes include: task type, data volume, and number of splittable computing resource packages. The step of determining the target historical computing task with the highest similarity to the current computing task based on the task attributes of the current computing task and the historical computing tasks includes: Based on the task type, data volume, and number of splittable computing resource packages of the current computing task, and the task type, data volume, and number of splittable computing resource packages of the historical computing task, the degree of difference between the current computing task and the historical computing task is obtained. The historical computing task with the smallest difference from the current computing task is identified as the target historical computing task with the highest similarity to the current computing task.

3. The resource allocation method according to claim 1, characterized in that, The process of obtaining the current load capacity of computing devices in the edge-cloud network includes: For each computing device: Obtain the initial computing power, initial network transmission speed, and initial load capacity of the computing device; The initial computing power, initial network transmission speed, and initial load capacity of the computing device are standardized to obtain the standardized computing power, standardized network transmission speed, and standardized load capacity. The current load capacity of the computing device is obtained based on the standardized computing power, the standardized network transmission speed, and the standardized load capacity.

4. The resource allocation method according to claim 3, characterized in that, The step of dividing the computing resources required by the target historical computing task into multiple computing resource packages based on the target historical computing task and the current load capacity includes: The computing power of each computing resource package is allocated based on the greatest common divisor of the current load capacity. Based on the data volume of the target historical computing task, the number N of the divided computing resource packages is calculated, where N is a positive integer; The computing resources required for the target historical computing task are divided into N computing resource packages.

5. The resource allocation method according to claim 1, characterized in that, The iterative algorithm is used to allocate the multiple computing resource packages to computing devices in the edge-cloud network until a preset iteration stopping condition is met, resulting in a target resource allocation strategy, including: In the presence of a third computing device, the target third computing device is updated to the second computing device, and the updated resource allocation strategy is updated to the initial resource allocation strategy; the target third computing device is the computing device with the smallest current load capacity among the third computing devices. The first computing resource package allocated to the first computing device is retrieved and allocated to the second computing device.

6. The resource allocation method according to claim 1, characterized in that, The iterative algorithm is used to allocate the multiple computing resource packages to computing devices in the edge-cloud network until a preset iteration stopping condition is met, resulting in a target resource allocation strategy, including: If the updated resource allocation strategy is superior to the initial resource allocation strategy, the updated resource allocation strategy is updated to the initial resource allocation strategy, and the process of retrieving the first computing resource package allocated to the first computing device and allocating it to the second computing device is resumed.

7. The resource allocation method according to claim 1, characterized in that, The step of calculating the energy consumption index of the initial resource allocation strategy and the updated resource allocation strategy according to the energy consumption index calculation formula to obtain the first energy consumption index and the second energy consumption index includes: Obtain the computing cost, computing time, and computing load of each computing device in the initial resource allocation strategy, and obtain the computing cost, computing time, and computing load of each computing device in the updated resource allocation strategy; Based on the computing cost of each computing device in the initial resource allocation strategy, the comprehensive computing cost of the initial resource allocation strategy is calculated to obtain a first comprehensive computing cost; based on the computing cost of each computing device in the updated resource allocation strategy, the comprehensive computing cost of the updated resource allocation strategy is calculated to obtain a second comprehensive computing cost. Based on the computation time of each computing device in the initial resource allocation strategy, the overall computation time of the initial resource allocation strategy is calculated to obtain a first overall computation time; based on the computation time of each computing device in the updated resource allocation strategy, the overall computation time of the updated resource allocation strategy is calculated to obtain a second overall computation time. Based on the computational load of each computing device in the initial resource allocation strategy, the balance of the initial resource allocation strategy is calculated to obtain a first balance; based on the computational load of each computing device in the updated resource allocation strategy, the balance of the updated resource allocation strategy is calculated to obtain a second balance. The first energy consumption index is obtained by weighted summing of the first comprehensive calculation cost, the first comprehensive calculation time, and the first balance degree; the second energy consumption index is obtained by weighted summing of the second comprehensive calculation cost, the second comprehensive calculation time, and the second balance degree.

8. A resource allocation device, characterized in that, The device includes: The acquisition module is used to acquire the current computing task, the task attributes of the current computing task, the current load capacity of computing devices in the edge-cloud network, and historical computing tasks and their task attributes. The determination module is used to determine the target historical computing task with the highest similarity to the current computing task based on the task attributes of the current computing task and the historical computing tasks; The partitioning module is used to divide the computing resources required by the target historical computing task into multiple computing resource packages based on the target historical computing task and the current load capacity. The allocation module is used to allocate the multiple computing resource packages to computing devices in the edge-cloud network using an iterative algorithm until a preset iteration stop condition is met, thereby obtaining the target resource allocation strategy. Specifically, the allocation module is used for: The multiple computing resource packages are allocated to the first computing device in the edge-cloud network to obtain an initial resource allocation strategy. The first computing device is the computing device with the largest current load capacity in the edge-cloud network. The first computing resource package allocated to the first computing device is extracted and allocated to the second computing device to obtain an updated resource allocation strategy; the second computing device is the computing device with the smallest current load capacity in the edge-cloud network; The energy consumption indices of the initial resource allocation strategy and the updated resource allocation strategy are calculated according to the energy consumption index calculation formula to obtain the first energy consumption index and the second energy consumption index. Based on the first energy consumption index and the second energy consumption index, determine whether the updated resource allocation strategy is better than the initial resource allocation strategy; If the updated resource allocation strategy is not better than the initial resource allocation strategy, determine whether there is a third computing device in the edge-cloud network with a larger current load capacity than the second computing device. In the absence of a third computing device, the initial resource allocation strategy is determined as the target resource allocation strategy.

9. A resource allocation device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the resource allocation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the resource allocation method as described in any one of claims 1-7.

11. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the resource allocation method as described in any one of claims 1-7.

Images