Resource allocation method, device and non-volatile computer-readable storage medium

Abstract

The present disclosure relates to a resource allocation method, device and non-volatile computer-readable storage medium, and relates to the field of network technology. The method includes: searching for a resource pool that can meet the business needs of a user as a candidate resource pool, wherein the business needs include resource needs; judging whether there is a candidate resource pool whose difference between available resources and the resource needs is greater than a threshold; if there is a candidate resource pool whose difference is greater than the threshold, allocating available resources in the candidate resource pool with the least available resources in the candidate resource pool to the user to complete this resource allocation; if there is no candidate resource pool whose difference is greater than the threshold, allocating available resources in the candidate resource pool with the most available resources in the candidate resource pool to the user to complete this resource allocation.

Description

Technical Field

[0001] The present disclosure relates to the field of network technology, and in particular to a resource allocation method, a resource allocation device and a non-volatile computer-readable storage medium. Background Art

[0002] CPN (Computing Power Network) is located above the network layer and can publish the current computing power status and network status as routing information to the network. The network routes computing task messages to the corresponding computing nodes to optimize user experience, computing resource utilization, and network efficiency. Therefore, it is particularly important to allocate resources to the computing power network.

[0003] In the related art, the smallest idle resource that can meet the requirements is always allocated to the service; or the largest idle resource is always allocated to the service. Summary of the invention

[0004] The inventors of the present disclosure have discovered that the above-mentioned related technologies have the following problems: causing resource pool fragmentation, or being unable to meet greater computing power requirements, resulting in poor resource allocation effects.

[0005] In view of this, the present disclosure proposes a resource allocation technical solution that can improve the resource allocation effect.

[0006] According to some embodiments of the present disclosure, a resource allocation method is provided, including: searching for a resource pool that can meet the business needs of a user as a candidate resource pool, wherein the business needs include resource needs; judging whether there is a candidate resource pool whose difference between available resources and the resource needs is greater than a threshold; in the case that there is a candidate resource pool whose difference is greater than the threshold, allocating the available resources in the candidate resource pool with the least available resources among the candidate resource pools to the user to complete this resource allocation; in the case that there is no candidate resource pool whose difference is greater than the threshold, allocating the available resources in the candidate resource pool with the most available resources among the candidate resource pools to the user to complete this resource allocation.

[0007] In some embodiments, the threshold is determined based on an average value of current resource demands of each user and an adjustment parameter, where the adjustment parameter is an integer greater than or equal to 0.

[0008] In some embodiments, the allocation method further includes: after completing the current resource allocation, adjusting the adjustment parameters according to the change trend of the historical resource demand of each user, and the adjusted adjustment parameters are used for the next resource allocation.

[0009] In some embodiments, adjusting the adjustment parameter according to the changing trend of the historical resource demand of each user includes: increasing the adjustment parameter when the historical resource demand increases; and decreasing the adjustment parameter when the historical resource demand decreases.

[0010] In some embodiments, before determining whether there is a candidate resource pool in which the difference between the available resources and the resource demand is greater than a threshold, the allocation method further includes: determining whether there is a candidate resource pool in which the available resources are equal to the resource demand; if there are equal candidate resource pools, allocating the available resources in the candidate resource pool with the highest latency among the candidate resource pools to the user to complete this resource allocation; if there are no equal candidate resource pools, determining whether there is a candidate resource pool in which the difference between the available resources and the resource demand is greater than a threshold to complete this resource allocation.

[0011] In some embodiments, the business requirements include latency requirements; the searching for a resource pool that can meet the user's business requirements as a candidate resource pool includes: searching for a resource pool that can meet the user's resource requirements and latency requirements as the candidate resource pool.

[0012] According to some other embodiments of the present disclosure, a resource allocation device is provided, comprising: a searching unit, used for searching for a resource pool that can meet the business needs of a user as a candidate resource pool, wherein the business needs include resource needs; a judging unit, used for judging whether there is a candidate resource pool whose difference between available resources and the resource needs is greater than a threshold; an allocating unit, used for allocating available resources from a candidate resource pool with the least available resources among the candidate resource pools to the user to complete this resource allocation if there is a candidate resource pool with a difference greater than the threshold, and for allocating available resources from a candidate resource pool with the most available resources among the candidate resource pools to the user to complete this resource allocation if there is a candidate resource pool with a difference greater than the threshold, and for allocating available resources from a candidate resource pool with the most available resources among the candidate resource pools to the user to complete this resource allocation if there is no candidate resource pool with a difference greater than the threshold.

[0013] In some embodiments, the threshold is determined based on an average value of current resource demands of each user and an adjustment parameter, where the adjustment parameter is an integer greater than or equal to 0.

[0014] In some embodiments, the allocation device further includes: an adjustment unit, which is used to adjust the adjustment parameters according to the change trend of the historical resource demand of each user after completing the current resource allocation, and the adjusted adjustment parameters are used for the next resource allocation.

[0015] In some embodiments, the adjustment unit increases the adjustment parameter when the historical resource demand increases, and decreases the adjustment parameter when the historical resource demand decreases.

[0016] In some embodiments, the judgment unit judges whether there is a candidate resource pool whose available resources are equal to the resource demand before judging whether there is a candidate resource pool whose difference between available resources and the resource demand is greater than a threshold value; the allocation unit allocates the available resources in the candidate resource pool with the highest latency among the candidate resource pools to the user to complete this resource allocation if there are equal candidate resource pools; and judges whether there is a candidate resource pool whose difference between available resources and the resource demand is greater than the threshold value to complete this resource allocation if there are no equal candidate resource pools.

[0017] In some embodiments, the service demand includes a latency demand; the searching unit searches for a resource pool that can meet the user's resource demand and latency demand as the candidate resource pool.

[0018] According to some further embodiments of the present disclosure, a resource allocation device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the resource allocation method in any one of the above embodiments based on instructions stored in the memory device.

[0019] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the resource allocation method in any of the above embodiments is implemented.

[0020] In the above embodiment, the resource pool allocated to the user is determined based on the amount of remaining resources in the resource pool after the resource demand is met. In this way, when there are many remaining resources, available resource pools can be reserved for the possible high computing power demand; when there are few remaining resources, many small resource pools that are extremely difficult to use can be prevented from appearing, thereby improving the effect of resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0022] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0023] Figure 1 A flowchart showing some embodiments of the resource allocation method of the present disclosure;

[0024] Figure 2 Flowcharts showing other embodiments of the resource allocation method of the present disclosure;

[0025] Figure 3 Flowcharts showing some further embodiments of the resource allocation method of the present disclosure;

[0026] Figure 4 A block diagram showing some embodiments of the resource allocation apparatus of the present disclosure;

[0027] Figure 5 A block diagram showing some other embodiments of the resource allocation device of the present disclosure;

[0028] Figure 6 A block diagram showing some further embodiments of the apparatus for allocating resources of the present disclosure. DETAILED DESCRIPTION

[0029] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0030] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0031] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0032] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0033] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0034] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0035] As mentioned earlier, the computing power network collects resource pool information and network status information (such as latency) in a centralized or distributed manner. Based on the user's requirements for latency and network, the ultimate goal is to provide customers with the most optimized computing power allocation and network connection solutions.

[0036] If the smallest idle resources that can meet the requirements are always allocated to the business, the remaining part after each allocation will always be the smallest, which will result in many small idle resources that are extremely difficult to use; if the largest idle resources are always allocated to the business, this will lead to a lack of larger idle resources, making it impossible to meet larger resource demands.

[0037] In view of the above technical problems, the technical solution disclosed in the present invention can select a suitable resource pool for customers according to the business needs after the computing power and latency information of each node in the network is collected by the computing power network. It avoids the technical problems of resource pool fragmentation and the inability to meet the needs of large computing power businesses, and maximizes the utilization of resource pools. For example, the technical solution disclosed in the present invention can be implemented through the following embodiments.

[0038] Figure 1 A flow chart showing some embodiments of the resource allocation method of the present disclosure.

[0039] like Figure 1 As shown, the method includes: step 110, searching for candidate resource pools; step 120, determining whether the resource difference is greater than a threshold; step 130, allocating the resource pool with the least resources; and step 140, allocating the resource pool with the most resources.

[0040] In step 110, a resource pool that can meet the user's business requirements is searched as a candidate resource pool. Business requirements include resource requirements.

[0041] In some embodiments, the service requirement includes a latency requirement. A resource pool that can meet the user's resource requirement and latency requirement is searched as a candidate resource pool.

[0042] For example, the service demand sent by the user is r(m,l), where m is the computing power demand (resource demand) and l is the latency demand. The set of resource pools in the network is R = {R1, R2, ... R i ,……R I}, the i-th resource pool can be represented as R i (M i ,L i ), M i is the available resources, L i For delay.

[0043] Find all resource pools that can meet business needs in R i (M i ,L i ), namely M i ≥m,L i ≤l). If there is no resource pool that can meet the business requirements, it means that all current resource pools cannot meet the business requirements, and the search ends.

[0044] In step 120, it is determined whether there is a candidate resource pool whose difference between available resources and resource requirements is greater than a threshold. If there is a candidate resource pool whose difference is greater than the threshold, step 130 is executed; if there is no candidate resource pool whose difference is greater than the threshold, step 140 is executed.

[0045] In some embodiments, the threshold is determined based on the average value of the current resource demand of each user and an adjustment parameter. The adjustment parameter is an integer greater than or equal to 0. For example, the initial value of the adjustment parameter can be set to 1, and adjusted according to the changing trend of the user resource demand after each resource allocation.

[0046] For example, you can calculate the average service demand m' of each user and view all R i Is there M in i ≥m+k×m' resource pool.

[0047] In step 130, the available resources in the candidate resource pool with the least available resources in the candidate resource pool are allocated to the user to complete the resource allocation. i The smallest resource pool, the search ends.

[0048] In step 140, the available resources in the candidate resource pool with the most available resources are allocated to the user to complete the resource allocation. i The largest resource pool, the search ends.

[0049] In some embodiments, Figure 2 The embodiments in the present invention implement the technical solution of the present invention.

[0050] Figure 2 Flowcharts showing other embodiments of the resource allocation method of the present disclosure.

[0051] like Figure 2 As shown, Figure 1 Compared with the embodiment in, this embodiment also includes: step 210, determining whether there are equal resource pools; and step 220, allocating the resource pool with the highest latency.

[0052] In step 210, it is determined whether there is a candidate resource pool whose available resources are equal to the resource demand. If there is no equal candidate resource pool, step 120 is executed to determine whether there is a candidate resource pool whose difference between the available resources and the resource demand is greater than a threshold value, so as to complete the resource allocation. If there is an equal candidate resource pool, step 220 is executed.

[0053] In step 220, available resources in the candidate resource pool with the highest latency in the candidate resource pool are allocated to the user to complete this resource allocation.

[0054] For example, to view all R i Is there M in i = m, if it exists, then the resource pool is selected and allocated to the user. If there are multiple matching resource pools, the resource pool with the highest latency is selected, and the search ends.

[0055] In some embodiments, after completing the current resource allocation, the adjustment parameter is adjusted according to the change trend of the historical resource demand of each user, and the adjusted adjustment parameter is used for the next resource allocation. For example, if the historical resource demand increases, the adjustment parameter is increased; if the historical resource demand decreases, the adjustment parameter is decreased.

[0056] In some embodiments, adjustment parameters for the next resource allocation may be determined based on each historical resource demand and its corresponding historical allocation result.

[0057] For example, the adjustment parameters can be adjusted through algorithms such as data fitting and machine learning. For example, taking each historical resource demand and its corresponding historical allocation result as input, a machine learning model is used to output the adjustment parameters for the next resource allocation.

[0058] Figure 3 Flowcharts showing still other embodiments of the resource allocation method of the present disclosure.

[0059] like Figure 3 As shown, obtain a resource pool set R in the network and its available resource set M and corresponding delay set L. Receive the service demand r(m,l) sent by the user, and calculate the average resource demand m'.

[0060] Determine whether there is a resource pool (computing power pool) that meets business needs i (M i ,L i ), M i ≥m,L i ≤l. If there is no M i ≥m,L i ≤l, then according to the statistical trend of historical resource demand changes and the corresponding resource allocation results (the matching of computing power pools), adjust the size of k and feedback k, and the search ends. i ≥m,L i ≤l resource pool, judge R i Is there M in i =m resource pool.

[0061] If there is M i = m, then select that resource pool. If there are multiple matching resource pools, select the one with the highest latency. According to the statistical trend of historical resource demand changes and the corresponding resource allocation results, adjust the size of k and feedback k, and the search ends. If there is no M i =m resource pool, obtain the k value of this resource allocation (k is a global variable, the initial value can be 1), and then determine R i Is there M ini ≥m+k×m' resource pool.

[0062] If there is M i ≥m+k×m' resource pool, select M i Then, according to the statistical trend of historical resource demand changes and the corresponding resource allocation results, the size of k is adjusted and k is fed back, and the search ends.

[0063] If there is no M i ≥m+k×m' resource pool, select M i Then, according to the statistical trend of historical resource demand changes and the corresponding resource allocation results, the size of k is adjusted and k is fed back, and the search ends.

[0064] In the above embodiment, whether the remaining computing power of the resource pool after processing the business with computing power requirement m reaches the average computing power requirement estimate k×m' can be set as the standard for determining whether a resource pool is a larger resource pool or a smaller resource pool.

[0065] When there are resource pools with large computing power, select relatively smaller resource pools to reserve available resource pools for possible high-computing power services; when there are no large computing power resource pools, select larger resource pools to avoid the emergence of many small resource pools that are extremely difficult to use.

[0066] In the above embodiment, the initial value of the adjustment parameter k is 1, and the demand change trend is fitted according to the historical computing power demand. When the trend increases, the k value increases, and vice versa. i The degree greater than k×m'+m determines the matching degree of resource allocation. When the matching degree is too low, the k value is reduced.

[0067] In this way, when the demand for business computing power tends to increase, k will increase, and the size of the reserved resources will increase, so that it can better serve the next business. This will prevent the computing power resource pool from becoming a small resource pool that is extremely difficult to use, and better avoid resource pool fragmentation.

[0068] Figure 4 A block diagram showing some embodiments of the resource allocation apparatus of the present disclosure.

[0069] like Figure 4 As shown, the resource allocation device 4 includes a searching unit 41 , a judging unit 42 and an allocation unit 43 .

[0070] The searching unit 41 searches for a resource pool that can meet the user's business requirements as a candidate resource pool. Business requirements include resource requirements.

[0071] In some embodiments, the service demand includes a latency demand; the search unit 41 searches for a resource pool that can meet the user's resource demand and latency demand as a candidate resource pool.

[0072] The determination unit 42 determines whether there is a candidate resource pool in which the difference between the available resources and the resource requirement is greater than a threshold.

[0073] In some embodiments, the threshold is determined based on an average value of current resource demands of each user and an adjustment parameter, where the adjustment parameter is an integer greater than or equal to zero.

[0074] In some embodiments, the allocation device 4 further includes: an adjustment unit 44, which is used to adjust the adjustment parameters according to the change trend of the historical resource demand of each user after completing the current resource allocation, and the adjusted adjustment parameters are used for the next resource allocation.

[0075] In some embodiments, the adjustment unit 44 increases the adjustment parameter when the historical resource demand increases, and decreases the adjustment parameter when the historical resource demand decreases.

[0076] When there are candidate resource pools with a number greater than the threshold, the allocation unit 43 allocates the available resources in the candidate resource pool with the least available resources among the candidate resource pools to the user to complete this resource allocation; when there are no candidate resource pools with a number greater than the threshold, the available resources in the candidate resource pool with the most available resources among the candidate resource pools are allocated to the user to complete this resource allocation.

[0077] In some embodiments, the judgment unit 42 judges whether there is a candidate resource pool with equal available resources and resource requirements before judging whether there is a candidate resource pool with a difference between available resources and resource requirements greater than a threshold. The allocation unit 43 allocates the available resources in the candidate resource pool with the highest latency among the candidate resource pools to the user in the case that there are equal candidate resource pools, and again judges whether there is a candidate resource pool with a difference between available resources and resource requirements greater than a threshold in the case that there are no equal candidate resource pools, to complete the current resource allocation.

[0078] Figure 5 A block diagram showing some other embodiments of the resource allocation device of the present disclosure.

[0079] like Figure 5 As shown, the resource allocation device 5 of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51, and the processor 52 is configured to execute the resource allocation method in any one of the embodiments of the present disclosure based on the instructions stored in the memory 51.

[0080] The memory 51 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0081] Figure 6 A block diagram showing some further embodiments of the apparatus for allocating resources of the present disclosure.

[0082] like Figure 6 As shown, the resource allocation device 6 of this embodiment includes: a memory 610 and a processor 620 coupled to the memory 610 , and the processor 620 is configured to execute the resource allocation method in any one of the aforementioned embodiments based on instructions stored in the memory 610 .

[0083] The memory 610 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0084] The resource allocation device 6 may also include an input / output interface 630, a network interface 640, a storage interface 650, etc. These interfaces 630, 640, 650, the memory 610, and the processor 620 may be connected, for example, via a bus 660. The input / output interface 630 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 640 provides a connection interface for various networked devices. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a USB flash drive.

[0085] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] So far, the resource allocation method, resource allocation device and non-volatile computer-readable storage medium according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed herein.

[0087] The method and system of the present disclosure may be implemented in many ways. For example, the method and system of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0088] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for allocating resources, comprising: Find a resource pool that can meet the user's business needs as a candidate resource pool, where the business needs include resource needs; Determine whether there is a candidate resource pool with available resources equal to the resource demand; In the case where there are equal candidate resource pools, allocating available resources in the candidate resource pool with the highest latency among the candidate resource pools to the user to complete this resource allocation; In the case that there are no equal candidate resource pools, determining whether there is a candidate resource pool whose difference between available resources and the resource demand is greater than a threshold; In the case where there are candidate resource pools with a number greater than the threshold, available resources in a candidate resource pool with the least available resources among the candidate resource pools are allocated to the user to complete this resource allocation; In the case that there is no candidate resource pool with a resource greater than the threshold, the available resources in the candidate resource pool with the most available resources in the candidate resource pool are allocated to the user to complete the current resource allocation; After completing the current resource allocation, the adjustment parameters of the current resource demand of each user are adjusted according to the change trend of the historical resource demand of each user, and the adjusted adjustment parameters are used for the next resource allocation.

2. The distribution method according to claim 1, wherein: The threshold is determined according to an average value of current resource demands of each user and an adjustment parameter, where the adjustment parameter is an integer greater than or equal to 0.

3. The distribution method according to claim 1, wherein: The adjusting the adjustment parameter according to the change trend of the historical resource demand of each user includes: In case the historical resource demand increases, increasing the adjustment parameter; In case the historical resource demand decreases, the adjustment parameter is decreased.

4. The distribution method according to any one of claims 1 to 3, wherein: The business requirements include latency requirements; The resource pool that can meet the business needs of the user is searched, and the candidate resource pool includes: A resource pool that can meet the user's resource requirements and latency requirements is searched as the candidate resource pool.

5. A resource allocation device, comprising: A searching unit, used to search for a resource pool that can meet the business requirements of the user as a candidate resource pool, wherein the business requirements include resource requirements; A judging unit, configured to judge whether there is a candidate resource pool in which the difference between the available resources and the resource demand is greater than a threshold; an allocation unit, configured to allocate available resources in a candidate resource pool with the least available resources among the candidate resource pools to the user to complete this resource allocation if there is a candidate resource pool with more available resources than the threshold, and to allocate available resources in a candidate resource pool with the most available resources among the candidate resource pools to the user to complete this resource allocation if there is no candidate resource pool with more available resources than the threshold; The adjustment unit is used to adjust the adjustment parameters of the current resource demand of each user according to the change trend of the historical resource demand of each user after completing the current resource allocation, and the adjusted adjustment parameters are used for the next resource allocation, wherein: The judging unit judges whether there is a candidate resource pool whose available resources are equal to the resource demand before judging whether there is a candidate resource pool whose difference between the available resources and the resource demand is greater than a threshold; When there are equal candidate resource pools, the allocation unit allocates the available resources in the candidate resource pool with the highest latency among the candidate resource pools to the user to complete this resource allocation. When there are no equal candidate resource pools, it is determined whether there is a candidate resource pool in which the difference between the available resources and the resource demand is greater than a threshold to complete this resource allocation.

6. The dispensing device according to claim 5, wherein: The threshold is determined according to an average value of current resource demands of each user and an adjustment parameter, where the adjustment parameter is an integer greater than or equal to 0.

7. The dispensing device according to claim 5, wherein: The adjustment unit increases the adjustment parameter when the historical resource demand increases, and decreases the adjustment parameter when the historical resource demand decreases.

8. The dispensing device according to any one of claims 5 to 7, wherein: The business requirements include latency requirements; The searching unit searches for a resource pool that can meet the resource requirements and latency requirements of the user as the candidate resource pool.

9. A resource allocation device, comprising: Memory; and A processor coupled to the memory, wherein the processor is configured to execute the resource allocation method according to any one of claims 1 to 4 based on instructions stored in the memory.

10. A non-volatile computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the resource allocation method according to any one of claims 1 to 4 is implemented.

Images