A network resource scheduling method, device, apparatus and storage medium

Abstract

The present disclosure relates to a network resource scheduling method and device, equipment and storage medium, and relates to the technical field of Internet, which can optimize the total target resource corresponding to the number of network resources used by all content distribution networks. The method comprises: obtaining the used resource quantity and target range of each content distribution network in the current period; determining the estimated resource usage of each content distribution network in the current period according to the used resource quantity of each content distribution network; determining a second content distribution network from the content distribution networks except the first content distribution network according to the estimated resource usage and target range of each content distribution network; increasing the proportion of the task amount handled by the first content distribution network and reducing the proportion of the task amount handled by the second content distribution network, so that the number of network resources consumed by the cumulative task amount handled by the first content distribution network at the end of the current period is within the target range of the first content distribution network.

Description

Technical Field

[0001] This disclosure relates to the field of Internet technology, and in particular to a network resource scheduling method, apparatus, device and storage medium. Background Technology

[0002] A Content Delivery Network (CDN) is a distributed content delivery network built on a data network. CDNs can distribute and cache data based on the user's location, reducing the load on the origin server and lowering latency, which is crucial for live audio and video streaming services. Audio and video companies typically rent large amounts of CDN resources from multiple providers to support and meet their business needs. Therefore, managing the target resources corresponding to the network resources consumed by the CDN is a very critical part of optimizing live audio and video streaming.

[0003] Currently, audio and video companies predict the target range of network resources used by each CDN within a given period at the beginning of the period, based on historical data on each CDN's network resource usage. However, due to potential scheduling issues or service disruptions during the period, there may be discrepancies between the predicted network resource usage and the actual situation. This could result in some CDNs using fewer network resources than their target range. Since different target ranges correspond to different target resource quantities, a CDN using fewer network resources than its target range could ultimately increase the total target resource usage across all CDNs.

[0004] Therefore, how to schedule the workload of each CDN within a cycle and optimize the total target resources corresponding to the number of network resources used by all CDNs is a problem that needs to be solved. Summary of the Invention

[0005] This disclosure provides a network resource scheduling method, apparatus, device, and storage medium that can optimize the total target resources corresponding to the number of network resources used by a content distribution network.

[0006] The technical solution of this disclosure is as follows:

[0007] According to a first aspect of the present disclosure, a network resource scheduling method is provided, comprising: obtaining the amount of resources used by each content delivery network (CDN) in a current period and a target range, wherein the target range is a preset numerical range to which the amount of network resources planned to be used by the CDN in the current period belongs; determining the estimated resource usage of each CDN in the current period based on the amount of resources used by each CDN; determining a second CDN from content delivery networks other than a first CDN based on the estimated resource usage and the target range of each content delivery network, wherein the first CDN includes one or more content delivery networks whose estimated resource usage is lower than the target range; increasing the proportion of tasks processed by the first CDN and decreasing the proportion of tasks processed by the second CDN, such that at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the first CDN is within the target range of the first CDN; and at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the second CDN is higher than the minimum value in the target range, or higher than the minimum value in the preset numerical range to which the estimated resource usage actually belongs.

[0008] Optionally, determining the second content distribution network from content distribution networks other than the first content distribution network includes: generating multiple content distribution network combinations based on content distribution networks other than the first content distribution network, each content distribution network combination containing one or more content distribution networks other than the first content distribution network; determining one of the multiple content distribution network combinations as the target optimization combination, and using the content distribution network in the target optimization combination as the second content distribution network.

[0009] Optionally, one of the multiple content delivery network combinations is selected as the target optimized combination, including: determining a first resource quantity based on estimated resource usage and a target range, wherein the first resource quantity indicates the difference between the estimated resource usage of all first content delivery networks and the minimum value in the target range; determining a second resource quantity for each content delivery network combination, wherein the second resource quantity indicates the cumulative amount of network resources that can be reduced in the consumption of all content delivery networks within the content delivery network combination; determining candidate combinations from the multiple content delivery network combinations based on the second resource quantity of each content delivery network combination, wherein the second resource quantity of the candidate combinations is greater than or equal to the first resource quantity; selecting one of the candidate combinations as the target optimized combination, and using the content delivery network in the target optimized combination as the second content delivery network corresponding to the first content delivery network.

[0010] Optionally, based on the second resource quantity of each content distribution network combination, candidate combinations are determined from multiple content distribution network combinations, including: rounding up the first resource quantity according to a preset minimum adjustment granularity, and rounding down the second resource quantity of each content distribution network combination, wherein the first resource quantity after rounding up is a positive integer multiple of the minimum adjustment granularity, and the second resource quantity after rounding down is a positive integer multiple of the minimum adjustment granularity; content distribution network combinations whose second resource quantity after rounding down is greater than or equal to the first resource quantity after rounding up are determined as candidate combinations.

[0011] Optionally, determining the second resource quantity for each content distribution network combination includes: determining the amount of resources that can be reduced for each content distribution network in each content distribution network combination; wherein, for content distribution networks whose estimated resource usage is lower than the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs; for content distribution networks whose estimated resource usage is higher than the minimum value in the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the target range of the content distribution network; and obtaining the second resource quantity for each content distribution network combination based on the amount of resources that can be reduced for each content distribution network in each content distribution network combination.

[0012] Optionally, different preset numerical ranges correspond to different numbers of target resources; one of the candidate combinations is determined as the target optimized combination, including: determining the adjustment strategy corresponding to each candidate combination, the adjustment strategy indicating the reduction of the number of resources used by one or more content delivery networks in the candidate combination; based on the adjustment strategy corresponding to each candidate combination and the target resources corresponding to each preset numerical range, determining the total target resources corresponding to each candidate combination, the total target resources representing the total number of target resources required for the cumulative number of network resources used by all content delivery networks at the end of the current period after reducing the number of network resources used by the content delivery networks in the candidate combination according to the corresponding adjustment strategy; and determining the candidate combination that produces the minimum total target resources as the target optimized combination.

[0013] Optionally, the network resource scheduling method further includes: if there are multiple candidate combinations that generate the minimum total target resource, the candidate combination with the highest network quality and the minimum total target resource is determined as the target optimal combination.

[0014] Optionally, the network resource scheduling method further includes: when a second content distribution network cannot be determined from content distribution networks other than the first content distribution network based on the estimated resource usage and target range of each content distribution network, determining a third resource quantity for each content distribution network, wherein the third resource quantity indicates the difference between the estimated resource usage of the content distribution network and the maximum value in the actual range of the content distribution network, and the actual range is a preset numerical range to which the estimated resource usage belongs; determining a preset number of content distribution networks with larger third resource quantities as the third content distribution network; modifying the target range of the third content distribution network to a preset numerical range one level above the actual range corresponding to the third content distribution network; determining a fourth content distribution network from content distribution networks other than the third content distribution network based on the estimated resource usage and target range; increasing the proportion of tasks processed by the third content distribution network and decreasing the proportion of tasks processed by the fourth content distribution network. The proportion is determined so that the cumulative network resource consumption of the tasks processed by the third content delivery network at the end of the current period is within the target range of the third content delivery network; wherein, if the estimated resource usage of the fourth content delivery network is higher than the minimum value in the target range before reducing the proportion of the tasks processed by the fourth content delivery network, the cumulative network resource consumption of the tasks processed by the fourth content delivery network at the end of the current period is higher than the minimum value in the target range after reducing the proportion of the tasks processed by the fourth content delivery network; if the actual estimated resource usage of the fourth content delivery network is lower than the target range before reducing the proportion of the tasks processed by the fourth content delivery network, the cumulative network resource consumption of the tasks processed by the fourth content delivery network at the end of the current period is higher than the minimum value in the preset range to which the estimated resource usage actually belongs.

[0015] Optionally, based on the estimated resource usage and target range, a fourth content distribution network is determined from content distribution networks other than the third content distribution network. This includes: determining a fourth resource quantity based on the estimated resource usage and target range, where the fourth resource quantity indicates the sum of the differences between the estimated resource usage of all third content distribution networks and the minimum value in the target range; generating multiple content distribution network combinations, each combination containing one or more content distribution networks other than the third content distribution network; determining a fifth resource quantity for each content distribution network combination, where the fifth resource quantity indicates the cumulative amount of resources that can be reduced by all content distribution networks within the combination; determining candidate combinations from the multiple content distribution network combinations based on the fifth resource quantity for each combination, where the fifth resource quantity of the candidate combinations is greater than or equal to the fourth resource quantity; and selecting one of the candidate combinations as the target optimized combination, and using the content distribution network in the target optimized combination as the fourth content distribution network corresponding to the third content distribution network.

[0016] Optionally, determining the fifth resource quantity for each content distribution network combination includes: for each content distribution network combination, determining one or more adjustment schemes corresponding to the content distribution network combination, wherein an adjustment scheme indicates the amount of resources that can be reduced for one or more content distribution networks in the content distribution network combination, and the amount of resources that can be reduced for each content distribution network is the difference between the estimated resource usage of the content distribution network and the minimum value in a preset numerical range corresponding to the content distribution network; and determining one or more fifth resource quantities corresponding to each adjustment scheme based on the content distribution network combination.

[0017] Optionally, increasing the proportion of tasks processed by the third content distribution network and decreasing the proportion of tasks processed by the fourth content distribution network includes: according to the target adjustment scheme corresponding to the candidate combination that generates the minimum total target resources, sorting the various content distribution networks in the target optimization combination in descending order according to the target resources within the preset numerical range corresponding to each content distribution network in the target optimization combination; and decreasing the proportion of tasks corresponding to the amount of resources that each content distribution network can reduce in descending order according to the preset numerical range of target resources corresponding to each content distribution network in the target optimization combination, until the cumulative amount of network resources consumed by the third content distribution network at the end of the current period is within the modified target range of the third content distribution network.

[0018] According to a second aspect of the present disclosure, a network resource scheduling apparatus is provided, comprising: an acquisition unit and a processing unit; the acquisition unit is configured to acquire the amount of resources used by each content delivery network in a current period and a target range, wherein the target range is a preset numerical range to which the amount of network resources planned to be used by the content delivery network in the current period belongs; the processing unit is configured to determine the estimated resource usage of each content delivery network in the current period based on the amount of resources used by each content delivery network; the processing unit is further configured to select resources from content delivery networks other than a first content delivery network based on the estimated resource usage and target range of each content delivery network. The first content distribution network includes one or more content distribution networks whose estimated resource usage is below a target range. The processing unit is further configured to increase the proportion of tasks processed by the first content distribution network and decrease the proportion of tasks processed by the second content distribution network, so that at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the first content distribution network is within the target range of the first content distribution network; and at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the second content distribution network is higher than the minimum value in the target range, or higher than the minimum value in the preset numerical range to which the estimated resource usage actually belongs.

[0019] According to a third aspect of the present disclosure, an electronic device is provided, which may include: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement any of the optional network resource scheduling methods in the first aspect described above.

[0020] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which instructions are stored, such that when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform any of the optional network resource scheduling methods of the first aspect described above.

[0021] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising instructions that, when executed on a processor of an electronic device, cause the electronic device to perform any of the optional network resource scheduling methods of the first aspect described above.

[0022] The technical solution provided in this disclosure brings at least the following beneficial effects:

[0023] Based on any of the above, in this disclosure, after obtaining the amount of resources used and the target range of various content delivery networks in the current period, a first content delivery network whose estimated resource usage is lower than the target range can be identified. When the estimated resource usage of a content delivery network is lower than the target range, it indicates that the target resources corresponding to the network resources consumed by that content delivery network have increased. By identifying a second content delivery network from other content delivery networks, the proportion of tasks processed by the first content delivery network is increased, and the proportion of tasks processed by the second content delivery network is decreased. This ensures that the cumulative amount of network resources consumed by the first content delivery network at the end of the current period is within the target range of the first content delivery network, while the estimated resource usage of the second content delivery network remains within the preset value range it belonged to before the adjustment. In this way, the amount of network resources used by the first content delivery network will not exceed the target range, that is, it will not additionally increase the target resources corresponding to the amount of network resources used by the first content delivery network, and the amount of network resources used by the second content delivery network will not be less than the target resources corresponding to the amount of network resources used before the adjustment, thereby achieving the purpose of optimizing the total target resources corresponding to the amount of network resources used by all content delivery networks. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0025] Figure 1 This is a schematic diagram of a network resource scheduling system provided in an embodiment of the present disclosure;

[0026] Figure 2 This illustration shows a schematic diagram illustrating the working principle of a content delivery network provided in an embodiment of this disclosure;

[0027] Figure 3 This illustration shows a flowchart of a network resource scheduling method provided in an embodiment of the present disclosure. Figure 1 ;

[0028] Figure 4 This illustration shows a flowchart of a network resource scheduling method provided in an embodiment of the present disclosure. Figure 2 ;

[0029] Figure 5 This illustration shows a flowchart of a network resource scheduling method provided in an embodiment of the present disclosure. Figure 3 ;

[0030] Figure 6 This diagram illustrates the control logic of a network resource scheduling method provided in an embodiment of the present disclosure.

[0031] Figure 7This illustration shows a schematic diagram of the structure of a network resource scheduling device provided in an embodiment of the present disclosure. Figure 1 ;

[0032] Figure 8 This illustration shows a schematic diagram of the structure of a network resource scheduling device provided in an embodiment of the present disclosure. Figure 2 . Detailed Implementation

[0033] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0034] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0035] It should also be understood that the term "comprising" indicates the presence of the described feature, whole, step, operation, element and / or component, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements and / or components.

[0036] The data disclosed herein may be data authorized by the user or fully authorized by all parties.

[0037] As described in the background section, before the start of each period, audio and video companies, based on historical data of CDN network resource usage by various vendors during the period, predict the target range corresponding to the amount of network resources each CDN might use during that period. For example, Table 1 exemplifies how an audio and video company, before the start of a period, plans the target range corresponding to the amount of network resources used by each vendor's CDN during that period, based on historical data, so that the total target resources corresponding to the amount of network resources used by each CDN during that period are minimized.

[0038] Table 1. Example of target range for various CDNs (8 types) with a total network resource quantity of 30,000 before the start of the cycle.

[0039]

[0040] Due to the impact of activities and fault scheduling during the period, the prediction of the amount of network resources used by each CDN before the start of the period may have errors. Table 2 shows, for example, the relationship between the amount of network resources currently used by various CDNs and the target range at the end of the period.

[0041] Table 2. Examples of network resource usage for each CDN before the start of the cycle and at the end of the cycle.

[0042]

[0043]

[0044] Among them, target resources represent the costs and expenses associated with the network resources consumed by the content delivery network.

[0045] Generally, as the preset value range increases, the target resources corresponding to the preset value range also increase. Therefore, if the number of network resources used by CDN is lower than its corresponding target range at the end of the period, it will cause the total target resources to increase, which may bring unnecessary expenses to audio and video companies.

[0046] Therefore, how to schedule the workload of each CDN within a period so that the amount of network resources used by each CDN at the end of the period is within the target range corresponding to each CDN before the start of the period, and optimize the total target resources corresponding to the amount of network resources used by all content delivery networks, is a problem that needs to be solved.

[0047] Based on this, this disclosure provides a network resource scheduling method. After obtaining the amount of resources used and the target range of various content delivery networks in the current period, a first content delivery network whose amount of resources used in the current period is less than the target range can be determined. When the estimated resource usage of a content delivery network is lower than the target range, it indicates that the target resources corresponding to that content delivery network have increased. By determining a second content delivery network from other content delivery networks, the task load ratio of the first and second content delivery networks is adjusted, thereby ensuring that the cumulative amount of network resources used by the first content delivery network at the end of the current period is within the target range of the first content delivery network. In this way, the amount of network resources used by the first content delivery network will not exceed the target range, that is, the target resource quantity corresponding to the amount of network resources used by the first content delivery network will not increase additionally.

[0048] The network resource scheduling method provided in this disclosure is illustrated below with reference to the accompanying drawings:

[0049] Figure 1 This is a schematic diagram of a network resource scheduling system provided in an embodiment of the present disclosure, such as... Figure 1 As shown, the network resource scheduling system 10 may include: a network resource scheduling device 110 and various CDNs 120.

[0050] Among them, the network resource scheduling device 110 can be connected to various CDNs 120 through wired or wireless networks, and different types of CDNs are provided by different providers.

[0051] The network resource scheduling device 110 can be used to adjust the proportion of tasks processed by various CDNs 120, so as to change the amount of network resources used by various CDNs 120.

[0052] Various CDN120s are used to process tasks dispatched by the network resource scheduling device 110. In the process of processing these tasks, network resources are used. These network resources can include bandwidth, traffic, etc.

[0053] In some embodiments, the network resource scheduling device 110 may be a single server, or it may be a server cluster consisting of multiple servers. In some embodiments, the server cluster may also be a distributed cluster. This disclosure does not limit the specific implementation of the network resource scheduling device 110.

[0054] CDN120, or Content Delivery Network, is an intelligent virtual network built on top of existing networks. Relying on edge servers deployed in various locations, it allows users to access content from the nearest server, reducing network congestion and improving user access response speed and hit rate. The working principle of CDN can be described as follows: Figure 2 As shown, when a user enters the domain name they want to access on their terminal device, the DNS (Domain Name System) first looks up the IP address of the nearest CDN to the user. When accessing a resource through that IP address, if the CDN does not cache the resource, it requests the resource from the origin server and caches it there. The next time the user accesses the resource, they can access it directly from that CDN. By adding a caching layer between the user and the origin server, CDNs direct user requests to the optimal CDN node, rather than the origin server site, thus accelerating access speed. Therefore, CDNs are commonly used in scenarios such as website / application acceleration, audio / video on-demand / large file download and distribution acceleration, live video streaming acceleration, and mobile application acceleration.

[0055] It should be understood that Figure 1 The network resource scheduling system shown is only an example. In practical applications, the network resource scheduling method of this disclosure embodiment can be executed independently by the terminal or the server, or the network resource scheduling method of this disclosure embodiment can be executed in cooperation between the terminal and the server. This disclosure embodiment does not limit the specific network resource scheduling system.

[0056] It should be noted that the aforementioned network resource scheduling device 110 can also be referred to as an electronic device.

[0057] The network resource scheduling method provided in this disclosure can be applied to the aforementioned... Figure 1 The network resource scheduling device 110 is shown in the application scenario.

[0058] like Figure 3 As shown, the network resource scheduling method may include:

[0059] S201. Obtain the amount of resources used and the target scope for each content delivery network in the current period.

[0060] The target range is a preset numerical range to which the content delivery network is to be used in the current cycle.

[0061] For example, a cycle could be a week, a month, 45 days, etc. The network resources used by various content delivery networks can be bandwidth, traffic, etc.

[0062] In one possible implementation, the network resource scheduling device obtains the amount of network resources consumed by each content delivery network in processing these tasks in the current period by acquiring the amount of tasks processed by each content delivery network in the current period.

[0063] S202. Based on the amount of resources used by each content delivery network, determine the estimated resource usage for each content delivery network in the current period.

[0064] In practical applications, if a period is one month, the amount of resources used can also be represented by the average daily resource usage up to the current date. For example, on the 20th of the month, the network resource scheduling device obtains that the target content delivery network's average daily resource usage for the first 19 days of the month is 1000, the target content delivery network used 1400 network resources on the 19th, and the average daily resource usage within the target range planned for the target content delivery network at the beginning of the month is 1200-2500. Taking the amount of network resources used by the target content delivery network on the 19th as the amount of resources used each day from the 20th to the 30th, the estimated resource usage of the target content delivery network in the current period can be represented by the average daily resource usage for the month, which is (1000×19+1400×11)÷30=1146.67 (rounded to two decimal places).

[0065] In some embodiments, before step S203, the network resource scheduling device further determines the resource usage status of each content delivery network based on its estimated resource usage and target range, and designates one or more content delivery networks with a resource usage status of "first state" as the first content delivery network. The first state indicates that the estimated resource usage of the content delivery network is lower than the target range.

[0066] For example, based on the previous example, the estimated resource usage of the target content delivery network is 1146.67, and the average daily resource usage within the target range is 1200-2500. Therefore, it can be seen that the estimated resource usage of the target content delivery network is lower than the target range, and the target content delivery network is in the first state.

[0067] For example, if there are three content delivery networks in the first state, the operator can choose one of them as the first content delivery network, or two of them as the first content delivery network, or all three of them as the first content delivery network, depending on the actual needs.

[0068] In this way, by estimating the resource usage and target scope of various content delivery networks, the resource usage status of each content delivery network can be accurately determined, and then one or more content delivery networks in the first state can be selected as the first content delivery network according to actual needs.

[0069] S203. Based on the estimated resource usage and target scope of each content delivery network, determine the second content delivery network from the content delivery networks other than the first content delivery network.

[0070] The first content delivery network includes one or more content delivery networks whose estimated resource usage is lower than the target range.

[0071] In some embodiments, the network resource scheduling device performs step S203, which can be specifically implemented as follows: generating multiple content distribution network combinations based on content distribution networks other than the first content distribution network; determining one of the multiple content distribution network combinations as the target optimized combination, and using the content distribution network in the target optimized combination as the second content distribution network. Each content distribution network combination includes one or more content distribution networks other than the first content distribution network.

[0072] For example, suppose the first content distribution network has three content distribution networks: A, B, and C. Besides the first content distribution network, there are four other content distribution networks: D, E, F, and G. Then the possible combinations of content distribution networks are as follows: Combination 1 (D), Combination 2 (E), Combination 3 (F), Combination 4 (G), Combination 5 (D and E), Combination 6 (D and F), Combination 7 (D and G), Combination 8 (E and F), Combination 9 (E and G), Combination 10 (F and G), Combination 11 (D, E, and F), Combination 12 (D, E, and G), Combination 13 (D, F, and G), Combination 14 (E, F, and G), and Combination 15 (D, E, F, and G). Assuming that Combination 11 is selected as the target optimization combination from these 15 combinations, then the second content distribution network is the content distribution network D, content distribution network E, and content distribution network F contained in Combination 11.

[0073] In this way, by generating multiple content distribution network combinations, the target optimal combination can be accurately determined from the multiple content distribution network combinations, and the content distribution network in the target optimal combination can be determined as the second content distribution network.

[0074] In some embodiments, the network resource scheduling device performs the step of determining one of a plurality of content delivery network combinations as the target optimized combination, which can be specifically implemented as follows: determining a first resource quantity based on estimated resource usage and a target range; determining a second resource quantity for each content delivery network combination; determining candidate combinations from the plurality of content delivery network combinations based on the second resource quantity for each content delivery network combination; and then determining one of the candidate combinations as the target optimized combination, and using the content delivery network in the target optimized combination as the second content delivery network corresponding to the first content delivery network. Wherein, the first resource quantity indicates the sum of the differences between the estimated resource usage of all first content delivery networks and the minimum value in the target range; each content delivery network combination includes one or more content delivery networks other than the first content delivery network; the second resource quantity indicates the cumulative amount of network resources that can be reduced by all content delivery networks within the content delivery network combination; and the second resource quantity of the candidate combination is greater than or equal to the first resource quantity.

[0075] For example, assuming the current period is the month, for a first content delivery network X, the amount of additional network resources required is... Among them, X l Let X represent the minimum value within the target range of the content delivery network X, and T represent the number of days in the current month. This represents the average daily resource usage of Content Delivery Network X (CDN) in the current month, calculated using the amount of network resources used by CDN X on the day before the current date as the estimated daily resource usage for the following days. Therefore, for all first-level CDNs, the estimated daily resource usage for the following days of the month is... Among them, T n This indicates the number of days preceding the current date of the current month.

[0076] In this way, by using the first resource quantity of the first content distribution network and the second resource quantity of the combination of multiple content distribution networks, the candidate combination corresponding to the first content distribution network can be accurately determined. Thus, the target optimized combination can be selected from the candidate combinations, and the second content distribution network corresponding to the first content distribution network can be determined.

[0077] In some embodiments, the network resource scheduling device determines candidate combinations from multiple content distribution network combinations based on the second resource quantity of each content distribution network combination. Specifically, this can be achieved by: rounding up the first resource quantity according to a preset minimum adjustment granularity, and rounding down the second resource quantity of each content distribution network combination, wherein the first resource quantity after rounding up is a positive integer multiple of the minimum adjustment granularity, and the second resource quantity after rounding down is a positive integer multiple of the minimum adjustment granularity; and determining the content distribution network combinations whose second resource quantity after rounding down is greater than or equal to the first resource quantity after rounding up as candidate combinations.

[0078] In actual adjustment, the network resource scheduling device often changes the amount of network resources used by the content distribution network by altering the proportion of tasks processed by the content distribution network. Therefore, the preset minimum adjustment granularity is 1% of the total number of network resources. For example, when the total number of network resources is 30,000, the preset minimum adjustment granularity is 300. If the first resource quantity of the first content distribution network is 4,980, then the first resource quantity after rounding up is 5,100. If the second resource quantity of a certain content distribution combination is 6,200, then the second resource quantity after rounding down is 6,000.

[0079] In this way, by rounding up the first resource quantity according to the preset minimum adjustment granularity, the actual adjustment requirements are met, and it is ensured that the amount of network resources added to the first content delivery network remains within the target range. At the same time, by rounding down the second resource quantity according to the preset minimum adjustment magnitude, the actual adjustment requirements are met, and the second resource quantity is prevented from exceeding the amount of resources that can be reduced by the content delivery network combination.

[0080] In some embodiments, the network resource scheduling device determines the amount of resources that can be reduced for each content distribution network in each content distribution network combination, and then obtains a second resource quantity for each content distribution network combination based on the amount of resources that can be reduced for each content distribution network in each content distribution network combination. Specifically, for a content distribution network whose estimated resource usage is lower than a target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs; for a content distribution network whose estimated resource usage is higher than the minimum value in the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the target range of the content distribution network.

[0081] In actual adjustments, when determining the amount of resources that can be reduced for various content delivery networks (CDNs), it is also necessary to consider the daily minimum resource limits for each CDN. The daily minimum resource limit represents the minimum amount of network resources a CDN must consume on a given day.

[0082] For example, when the period is one month, for a content delivery network X whose estimated resource usage is lower than the target range, the amount of resources can be reduced to meet the requirements. Where, X′ l express The minimum value of the actual range, X z This represents the amount of network resources used by content delivery network X on the day preceding the current date of the current month. min This represents the daily minimum resource limit for content delivery network X. For content delivery network Y, whose estimated resource usage is higher than the minimum of the target range, the amount of resources that can be reduced to meet the requirement is... Among them, Y l express The minimum value in the target range, Y z Y represents the amount of network resources used by content delivery network Y on the day preceding the current date of the current month. min This represents the minimum daily resource limit for content delivery network Y.

[0083] If the minimum adjustment granularity is Δ, then for a given content distribution combination, its second resource quantity is:

[0084] For all first content delivery networks, the first resource quantity is

[0085] like This indicates that by adjusting the content distribution combination and the workload processed by the first content distribution network, the amount of network resources used by the first content distribution network can be kept within the target range.

[0086] In this way, by determining the amount of resources that can be reduced for each content delivery network with different resource usage status, the second resource quantity of the content delivery network combination can be accurately determined.

[0087] In some embodiments, different preset numerical ranges correspond to different amounts of target resources. The network resource scheduling device determines one of the candidate combinations as the target optimized combination, which can be specifically implemented as follows: determining an adjustment strategy corresponding to each candidate combination; determining the total target resources corresponding to each candidate combination based on the adjustment strategy corresponding to each candidate combination and the target resources corresponding to each preset numerical range; and determining the candidate combination that produces the minimum total target resources as the target optimized combination. Here, the adjustment strategy indicates a reduction in the amount of resources used by one or more content delivery networks in the candidate combination, and the total target resources represent the total amount of target resources required for all content delivery networks to cumulatively use the network resources at the end of the current period after reducing the amount of network resources used by the content delivery networks in the candidate combination according to the corresponding adjustment strategy.

[0088] In the actual adjustment process, the total target resources corresponding to the network resources consumed by all content distribution networks are the first factor to be considered. Therefore, if the task volume ratio of a certain content distribution network combination and the first content distribution network is to be adjusted, the target resources corresponding to the actual range of each content distribution network in the combination are first sorted in descending order, and the amount of network resources used by the content distribution network with high target resources is reduced first.

[0089] In this way, by determining the adjustment strategy for each candidate combination, and then based on the adjustment strategy of the candidate combinations and the target resources corresponding to each preset numerical range, the candidate combination that minimizes the total target resources is determined. That is, the candidate combination that produces the minimum total target resources is the target optimized combination. Based on the adjustment strategy of the target optimized combination, the workload processed by the first content distribution network and various content distribution networks in the target optimized combination is adjusted so that the amount of network resources used by the first content distribution network in the current period is within the target range, thus optimizing the total target resources corresponding to the network resources used by all content distribution networks.

[0090] In some embodiments, after obtaining multiple preset value ranges, the network resource scheduling device adds a preset value to the minimum value in each preset value range, and uses the value after adding the preset value as the minimum value in the preset value range. For example, if a preset value range is 500-1000 and the minimum value is 500, and the preset value is 5, then the modified preset value range is 505-1000. This avoids the situation where, when subsequently calculating the amount of resources that can be reduced in various content delivery networks, the amount of network resources used by content delivery networks that were originally within the target range after adjustment is less than the minimum value in the target range.

[0091] In some embodiments, if there are multiple candidate combinations that generate the minimum total target resource, the network resource scheduling device determines the candidate combination with the highest network quality and the minimum total target resource as the target optimal combination.

[0092] In this way, when there are multiple candidate combinations that generate the minimum total target resources, it indicates that there are multiple adjustment strategies when the total target resources are the same. Therefore, the candidate combination with the highest network quality and the minimum total target resources is selected as the target optimization combination, so as to provide better service quality for users while controlling the minimum total target resources.

[0093] S204. Increase the proportion of tasks processed by the first content delivery network and decrease the proportion of tasks processed by the second content delivery network, so that the cumulative amount of network resources consumed by the tasks processed by the first content delivery network at the end of the current period is within the target range of the first content delivery network.

[0094] Among them, at the end of the current period, the amount of network resources consumed by the tasks processed by the second content delivery network is higher than the minimum value in the target range, or higher than the minimum value in the preset value range to which the estimated resource usage actually belongs.

[0095] For example, if the number of network resources that the first content delivery network needs to increase accounts for 20% of the total resources, and before the adjustment, the first content delivery network needs to handle 20% of the tasks, while the second content delivery network handles 50% of the tasks, then after the adjustment, the first content delivery network needs to handle 40% of the tasks, and the second content delivery network handles 30% of the tasks.

[0096] The technical solution provided by the above embodiments brings at least the following beneficial effects: As shown in S201-S203, after obtaining the amount of resources used and the target range of various content distribution networks in the current period, a first content distribution network whose estimated resource usage is lower than the target range can be determined. When the estimated resource usage of a content distribution network is lower than the target range, it indicates that the target resources corresponding to the network resources consumed by that content distribution network have increased. By determining a second content distribution network from other content distribution networks, the proportion of tasks processed by the first content distribution network is increased, and the proportion of tasks processed by the second content distribution network is decreased. This ensures that the cumulative amount of network resources consumed by the first content distribution network at the end of the current period is within the target range of the first content distribution network, while the estimated resource usage of the second content distribution network remains within the preset value range before adjustment. In this way, the amount of network resources used by the first content distribution network will not exceed the target range, that is, there will be no additional increase in the target resources corresponding to the amount of network resources used by the first content distribution network, and the amount of network resources used by the second content distribution network will not be less than the target resources corresponding to the amount of network resources used before adjustment, thereby achieving the purpose of optimizing the total target resources corresponding to the amount of network resources used by all content distribution networks.

[0097] In one alternative embodiment, in Figure 3 Based on the illustrated method embodiments, this embodiment provides a possible implementation. In conjunction with... Figure 3 ,like Figure 4 As shown, the network resource scheduling method further includes:

[0098] S301. If a second content distribution network cannot be determined from content distribution networks other than the first content distribution network based on the estimated resource usage and target scope of each content distribution network, a third resource quantity for each content distribution network shall be determined.

[0099] The third resource quantity indicates the difference between the estimated resource usage of the content delivery network and the maximum value in the actual range of the content delivery network, where the actual range is the preset numerical range to which the estimated resource usage belongs.

[0100] In some embodiments, each content delivery network (CDN) has a daily maximum resource limit, meaning that the maximum amount of network resources consumed by each CDN per day cannot exceed the daily maximum resource limit. When the amount of network resources that a CDN needs to use each day exceeds the difference between the daily maximum resource limit of that CDN and the amount of network resources used by that CDN on the previous day, it indicates that the amount of network resources used by that CDN in the current period cannot be kept within the target range by adjusting the task load ratio of each CDN. In other words, if a second CDN cannot be identified, it is necessary to optimize the total target resources by making the amount of network resources used by one or more CDNs fall within a higher-level preset value range.

[0101] S302. The third content distribution network with a larger amount of resources is selected as the third content distribution network.

[0102] It should be understood that the closer the difference between the estimated resource usage of a content delivery network and the maximum value in the actual range of the content delivery network, the greater the possibility that the cumulative network resource usage of the content delivery network at the end of the current period exceeds the actual range. Therefore, according to the adjustment needs of the operators, the third content delivery network with a larger preset number of resources can be determined as the third content delivery network.

[0103] For example, if the preset quantity is 3, the network resource scheduling device will select the third content distribution network as the content distribution network with the larger preset quantity of resources.

[0104] S303. Modify the target range of the third content delivery network to the preset numerical range of the previous level of the actual range corresponding to the third content delivery network.

[0105] For example, if the actual range of the third content distribution network is 3000-6000, and the preset range of its superior level is 6000-9000, then the modified target range of the third content distribution network is determined to be 6000-9000.

[0106] S304. Based on the estimated resource usage and target scope, determine the fourth content distribution network from the content distribution networks other than the third content distribution network.

[0107] S305. Increase the proportion of tasks processed by the third content delivery network and decrease the proportion of tasks processed by the fourth content delivery network, so that the cumulative amount of network resources consumed by the tasks processed by the third content delivery network at the end of the current period is within the target range of the third content delivery network.

[0108] Specifically, if, before reducing the proportion of tasks processed by the fourth content delivery network, the estimated resource usage of the fourth content delivery network was higher than the minimum value in the target range, and after reducing the proportion of tasks processed by the fourth content delivery network, the cumulative network resources consumed by the fourth content delivery network at the end of the current period were higher than the minimum value in the target range; and if, before reducing the proportion of tasks processed by the fourth content delivery network, the actual estimated resource usage of the fourth content delivery network was lower than the target range within the preset value range, and after reducing the proportion of tasks processed by the fourth content delivery network, the cumulative network resources consumed by the fourth content delivery network at the end of the current period were higher than the minimum value in the preset value range within the estimated resource usage.

[0109] The technical solution provided by the above embodiments brings at least the following beneficial effects: As can be seen from S301-S305, in the absence of a second content distribution network, by determining a preset number of content distribution networks with a larger amount of third resources as the third content distribution network, that is, selecting a preset number of content distribution networks whose network resource usage is most likely to reach the preset value range of the previous level, and by adjusting the task volume ratio processed by the third content distribution network and its corresponding fourth content distribution network, the cumulative amount of network resources used by the third content distribution network at the end of the current period is within the target range modified by the third content distribution network, thereby achieving the purpose of optimizing the total target resources.

[0110] In one alternative embodiment, in Figure 4 Based on the illustrated method embodiments, this embodiment provides a possible implementation. In conjunction with... Figure 4 ,like Figure 5 As shown in S304, the method by which the network resource scheduling device determines a fourth content delivery network from content delivery networks other than the third content delivery network based on estimated resource usage and target scope includes:

[0111] S401. Determine the fourth resource quantity based on the estimated resource usage and target scope.

[0112] The fourth resource quantity refers to the sum of the differences between the estimated resource usage of all third content delivery networks and the minimum value in the target range.

[0113] For example, when a cycle corresponds to one month, for a third content delivery network, the amount of network resources it needs to consume daily after the current date of the month is: Then the daily fourth resource quantity for all third-party content delivery networks after the current date of the month is:

[0114] S402, Generate multiple content delivery network combinations.

[0115] Each content distribution network combination includes one or more content distribution networks other than the third content distribution network.

[0116] For example, suppose there are three content distribution networks: A, B, and C. In addition to the third content distribution network, there are four other content distribution networks: D, E, F, and G. Then the combinations of content distribution networks are as follows: Combination 1 (D), Combination 2 (E), Combination 3 (F), Combination 4 (G), Combination 5 (D and E), Combination 6 (D and F), Combination 7 (D and G), Combination 8 (E and F), Combination 9 (E and G), Combination 10 (F and G), Combination 11 (D, E, and F), Combination 12 (D, E, and G), Combination 13 (D, F, and G), Combination 14 (E, F, and G), and Combination 15 (D, E, F, and G).

[0117] S403. Determine the fifth resource quantity for each content delivery network combination.

[0118] The fifth resource quantity indicates the total amount of resources that can be reduced in consumption across all content delivery networks within the content delivery network portfolio.

[0119] In some embodiments, the network resource scheduling device determines the fifth resource quantity for each content delivery network combination. Specifically, this can be achieved by: for each content delivery network combination, determining one or more adjustment schemes corresponding to that combination, and then, based on each adjustment scheme, determining one or more fifth resource quantities corresponding to each adjustment scheme. Wherein, an adjustment scheme indicates the amount of resources that can be reduced for one or more content delivery networks in the combination, and the amount of resources that can be reduced for each content delivery network is the difference between the estimated resource usage of the content delivery network and the minimum value within a preset numerical range corresponding to the content delivery network.

[0120] For example, in combination five of the above examples, assuming that the provider of content delivery network D provides three preset numerical ranges D1, D2, and D3, and the provider of content delivery network E provides four preset numerical ranges E1, E2, E3, and E4, then for combination five, there are several adjustment schemes: Adjustment Scheme 1 (D1 and E1), Adjustment Scheme 2 (D1 and E2), Adjustment Scheme 3 (D1 and E3), Adjustment Scheme 4 (D1 and E4), Adjustment Scheme 5 (D2 and E1), Adjustment Scheme 6 (D2 and E2), Adjustment Scheme 7 (D2 and E3), Adjustment Scheme 8 (D2 and E4), Adjustment Scheme 9 (D3 and E1), Adjustment Scheme 10 (D3 and E2), Adjustment Scheme 11 (D3 and E4), and Adjustment Scheme 12 (D3 and E4). When adjusting the network resource quantity based on Adjustment Scheme 1, it means that the preset numerical range D1 is taken as the target range of content delivery network D, and the preset numerical range E1 is taken as the target range of content delivery network E, and the fifth resource quantity of combination five is determined accordingly.

[0121] The above example can also be understood as constructing a content delivery network instance for each type of content delivery network (CDN). A CDN can have multiple instances. For example, a CDN provider might offer multiple preset value ranges. When a preset value range is less than the amount of network resources the CDN plans to use in the current period, but greater than the target range, then that preset value range can be considered an instance of the CDN. An instance of a content delivery network typically also includes information such as the CDN provider, the amount of network resources the CDN plans to use in the current period, a preset value range that is less than the amount of network resources the CDN plans to use in the current period but greater than the target range, and the target resources for that preset value range.

[0122] For all content delivery network instances, they are sorted in descending order according to their corresponding target resources. Instances of content delivery networks with the same supplier are combined with instances of content delivery networks with different suppliers. That is, each combination of content delivery network instances contains only one instance of a content delivery network provided by the same supplier.

[0123] For each content delivery network instance combination, the reducible resource quantity of each content delivery network instance is determined sequentially according to the order of their target resources. The reducible resource quantity of each content delivery network instance in the combination is greedily increased to obtain the fifth resource quantity for that combination. When the fifth resource quantity... The number of network resources required daily after the current date of all third-party content delivery networks that is greater than or equal to this amount is... If this happens, the determined fifth resource quantity will be allocated to all third content delivery networks, ending the adjustment process. This represents the average daily resource usage of a content delivery network (CDN) during the current month, using the amount of network resources used on the day before the current date as the average daily network resource usage for the following days of the month. This indicates that the content delivery network instance corresponds to the minimum value within a preset numerical range. (CDN) z This indicates the amount of network resources used by the Content Delivery Network (CDN) on the day preceding the current date of the current month. min This indicates the daily minimum resource limit for this content delivery network. Therefore, the amount of network resources reduced daily for this content delivery network is...

[0124] If the amount of network resources that can be reduced by distributing all content within this combination to network instances is summed up...

[0125]

[0126] If this still does not hold true, then the combination of content delivery networks is not a feasible solution for the third content delivery network, and the workload of the third content delivery network cannot be adjusted to bring the third content delivery network within the target range.

[0127] In this way, the network resource scheduling device can determine one or more fifth resource quantities corresponding to each content distribution network combination based on the adjustment scheme corresponding to each content distribution network combination, which facilitates the selection of candidate combinations from multiple content distribution network combinations based on the fifth resource quantities of each content distribution network combination in the subsequent process.

[0128] S404. Based on the fifth resource quantity of each content delivery network combination, determine candidate combinations from multiple content delivery network combinations.

[0129] Among them, the fifth resource quantity of the candidate combination is greater than or equal to the fourth resource quantity.

[0130] In practical applications, the network resource scheduling device performs an up-rounding operation on the fourth resource quantity and a down-rounding operation on the fifth resource quantity according to the preset minimum adjustment granularity, so that the up-rounded fourth resource quantity is a positive integer multiple of the preset minimum adjustment granularity, and the down-rounded fifth resource quantity is a positive integer multiple of the preset minimum adjustment granularity.

[0131] S405. Select one of the candidate combinations as the target optimization combination, and use the content distribution network in the target optimization combination as the fourth content distribution network corresponding to the third content distribution network.

[0132] The technical solution provided by the above embodiments brings at least the following beneficial effects: As can be seen from S401-S405, by using the fourth resource quantity of the third content distribution network and the fifth resource quantity of the combination of multiple content distribution networks, the candidate combination corresponding to the third content distribution network can be accurately determined, thereby selecting the target optimized combination from the candidate combination and determining the fourth content distribution network corresponding to the third content distribution network.

[0133] In some embodiments, based on the above embodiments, the network resource scheduling device increases the proportion of tasks processed by the third content distribution network and decreases the proportion of tasks processed by the fourth content distribution network. This can be specifically implemented as follows: according to the target adjustment scheme corresponding to the candidate combination that generates the minimum total target resources, the various content distribution networks in the target optimization combination are arranged in descending order according to the target resources corresponding to the preset numerical range of the various content distribution networks in the target optimization combination; according to the order of decreasing target resources corresponding to the preset numerical range of the various content distribution networks in the target optimization combination, the proportion of tasks corresponding to the amount of resources that can be reduced by each content distribution network is reduced sequentially, until the cumulative amount of network resources consumed by the third content distribution network at the end of the current period is within the target range modified by the third content distribution network.

[0134] For example, in a target optimization combination, there are three content distribution networks (CDNs): A, B, and C. The target resources corresponding to instances of CDN B are greater than those corresponding to instances of CDN A, which in turn are greater than those corresponding to instances of CDN C. During adjustment, the reducible resource amount of CDN B is reduced first, followed by the reducible resource amount of CDN A. If the amount of network resources used by the third CDN in the current period is within the target range, the reducible resource amount of CDN C is no longer reduced. If the amount of network resources used by the third CDN in the current period is not within the target range, the reducible resource amount of CDN C is further reduced.

[0135] In this way, the network resource scheduling device prioritizes reducing the amount of network resources used by content delivery networks with higher target resources in the target optimization combination, thereby optimizing the total target resources of all content delivery networks.

[0136] The following example uses a one-month cycle. Figure 6 As shown, the control logic of the network resource scheduling method is briefly introduced:

[0137] First, at the end of the month (e.g., the 20th), based on the resource usage plans of each content delivery network planned at the beginning of the month, it is determined whether there are any content delivery networks whose estimated resource usage is lower than the target range. If so, the method of ensuring the target range for the first content delivery network is implemented, and it is then determined whether a second content delivery network has been identified. If a second content delivery network has been identified, a target optimization combination is further determined, and the network resource usage of the first and second content delivery networks is adjusted according to the adjustment strategy corresponding to the target optimization combination. If a second content delivery network has not been identified, the network resource scheduling device identifies a preset number of third content delivery networks, and determines whether there is a corresponding target optimization combination for the third content delivery network. If so, the network resource usage of the third and fourth content delivery networks is adjusted according to the adjustment strategy corresponding to the target optimization combination. If not, the current plan is maintained.

[0138] For example, Table 3 shows the planned network resource usage at the beginning of the month and the actual network resource usage at the end of the month for each content delivery network.

[0139] Table 3: Planned network resource usage at the beginning of the month and actual network resource usage at the end of the month for each content delivery network.

[0140]

[0141] in, Equal to The calculation methods are the same. CDN-A: indicates CDN service provided by provider A; CDN-B, CDN-C, etc., have similar meanings.

[0142] CDN n : The average number of CDN resources from the 1st to yesterday. For example, A n This represents the daily average amount of network resources used by the content delivery network provided by vendor A from the 1st to yesterday.

[0143] CDN z The amount of resources used by the CDN yesterday. This disclosure assumes that the amount of network resources used each day of the following month will be similar to the amount of resources used yesterday.

[0144] The CDN estimates the average daily resource quantity for the month before the adjustment.

[0145] T: Total number of days in the month.

[0146] Tn: Yesterday's date.

[0147] CDN l The minimum value within the target range of CDN. For example, A lThis represents the minimum value within the target range corresponding to the content delivery network provided by vendor A.

[0148] CDN u The maximum value within the target range of the CDN. For example, A u This represents the maximum value within the target range corresponding to the content delivery network provided by vendor A.

[0149] CDN' l The minimum value within the actual range of CDN. For example, A′ l This represents the minimum value within the actual range corresponding to the content delivery network provided by supplier A.

[0150] CDN' u The maximum value within the actual range of the CDN. For example, A′ u This represents the maximum value within the actual range corresponding to the content delivery network provided by vendor A.

[0151] Based on the above network resource scheduling method, a feasible adjustment scheme for the proportion of task processing by each content distribution network can be shown in Table 4.

[0152] Table 4 shows examples of feasible adjustment schemes for the proportion of task processing by each content delivery network.

[0153]

[0154] CDN add The amount of network resources that CDN needs to use daily needs to be increased.

[0155] CDN reduce CDN can reduce the amount of network resources used daily.

[0156] All feasible adjustment schemes are ranked according to total target resources and network quality, and the one with the lowest total resource cost is selected as the adjustment scheme for the first content delivery network.

[0157] It is understood that, in practical implementation, the network resource scheduling apparatus described in the embodiments of this disclosure may include one or more hardware structures and / or software modules for implementing the aforementioned corresponding network resource scheduling method. These hardware structures and / or software modules can constitute an electronic device. Those skilled in the art should readily recognize that, based on the algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or software-driven manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0158] Based on this understanding, the present disclosure also provides a network resource scheduling device. Figure 7 A schematic diagram of the structure of the network resource scheduling device provided in the embodiments of this disclosure is shown. Figure 1 .like Figure 7 As shown, the network resource scheduling device includes an acquisition unit 1101 and a processing unit 1102.

[0159] The acquisition unit 1101 is configured to acquire the amount of resources used and the target range of each content distribution network in the current period, wherein the target range is a preset numerical range to which the amount of network resources planned to be used by the content distribution network in the current period belongs; the processing unit 1102 is configured to determine the estimated resource usage of each content distribution network in the current period based on the amount of resources used by each content distribution network; the processing unit 1102 is further configured to determine a second content distribution network from the content distribution networks other than the first content distribution network based on the estimated resource usage and target range of each content distribution network. The content distribution network includes one or more content distribution networks whose estimated resource usage is lower than a target range; the processing unit 1102 is further configured to increase the proportion of tasks processed by the first content distribution network and decrease the proportion of tasks processed by the second content distribution network, so that at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the first content distribution network is within the target range of the first content distribution network; and at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the second content distribution network is higher than the minimum value in the target range, or higher than the minimum value in the preset value range to which the estimated resource usage actually belongs.

[0160] Optionally, the processing unit 1102 is specifically configured to perform: generating multiple content distribution network combinations based on content distribution networks other than the first content distribution network, each content distribution network combination containing one or more content distribution networks other than the first content distribution network; determining one of the multiple content distribution network combinations as the target optimization combination, and using the content distribution network in the target optimization combination as the second content distribution network.

[0161] Optionally, the processing unit 1102 is specifically configured to perform: determining a first resource quantity based on the estimated resource usage and the target range, the first resource quantity indicating the difference between the estimated resource usage of all first content delivery networks and the minimum value in the target range; determining a second resource quantity for each content delivery network combination, the second resource quantity indicating the cumulative amount of network resources that can be reduced in the content delivery networks within the content delivery network combination; determining candidate combinations from multiple content delivery network combinations based on the second resource quantity of each content delivery network combination, the second resource quantity of the candidate combinations being greater than or equal to the first resource quantity; determining one of the candidate combinations as the target optimized combination, and using the content delivery networks in the target optimized combination as the second content delivery networks corresponding to the first content delivery networks.

[0162] Optionally, the processing unit 1102 is specifically configured to perform: rounding up the first resource quantity according to a preset minimum adjustment granularity, and rounding down the second resource quantity of each content distribution network combination, wherein the first resource quantity after rounding up is a positive integer multiple of the minimum adjustment granularity, and the second resource quantity after rounding down is a positive integer multiple of the minimum adjustment granularity; and determining the content distribution network combination whose second resource quantity after rounding down is greater than or equal to the first resource quantity after rounding up as a candidate combination.

[0163] Optionally, the processing unit 1102 is specifically configured to perform: determining the amount of resources that can be reduced for each content distribution network in each content distribution network combination; wherein, for a content distribution network whose estimated resource usage is lower than the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs; for a content distribution network whose estimated resource usage is higher than the minimum value in the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the target range of the content distribution network; and obtaining a second resource amount for each content distribution network combination based on the amount of resources that can be reduced for each content distribution network in each content distribution network combination.

[0164] Optionally, different preset numerical ranges correspond to different numbers of target resources; the processing unit 1102 is specifically configured to perform: determining the adjustment strategy corresponding to each candidate combination, the adjustment strategy indicating a reduction in the number of resources used by one or more content delivery networks in the candidate combination; based on the adjustment strategy corresponding to each candidate combination and the target resources corresponding to each preset numerical range, determining the total target resources corresponding to each candidate combination, the total target resources representing the total number of target resources required for the cumulative number of network resources used by all content delivery networks at the end of the current period after reducing the number of network resources used by the content delivery networks in the candidate combination according to the corresponding adjustment strategy; and determining the candidate combination that produces the minimum total target resources as the target optimized combination.

[0165] Optionally, the processing unit 1102 is also configured to perform the following: if there are multiple candidate combinations that generate the minimum total target resource, determine the candidate combination with the highest network quality and the minimum total target resource as the target optimization combination.

[0166] Optionally, the processing unit 1102 is further configured to perform the following: If, based on the estimated resource usage and target range of each content distribution network, no second content distribution network is identified from content distribution networks other than the first content distribution network, then: a third resource quantity is determined for each content distribution network, where the third resource quantity indicates the difference between the estimated resource usage of the content distribution network and the maximum value within the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs; a preset number of content distribution networks with larger third resource quantities are identified as the third content distribution network; the target range of the third content distribution network is modified to a preset numerical range one level above the actual range corresponding to the third content distribution network; a fourth content distribution network is identified from content distribution networks other than the third content distribution network based on the estimated resource usage and target range; the proportion of tasks processed by the third content distribution network is increased, and the proportion of tasks processed by the fourth content distribution network is decreased. The resource usage ratio is set so that the cumulative network resource consumption of the tasks processed by the third content distribution network at the end of the current period is within the target range of the third content distribution network. Specifically, if the estimated resource usage of the fourth content distribution network is higher than the minimum value in the target range before reducing the task usage ratio of the fourth content distribution network, the cumulative network resource consumption of the tasks processed by the fourth content distribution network at the end of the current period is still higher than the minimum value in the target range after reducing the task usage ratio of the fourth content distribution network; if the actual estimated resource usage of the fourth content distribution network is lower than the target range before reducing the task usage ratio of the fourth content distribution network, the cumulative network resource consumption of the tasks processed by the fourth content distribution network at the end of the current period is higher than the minimum value in the preset range to which the estimated resource usage actually belongs.

[0167] Optionally, the processing unit 1102 is specifically configured to perform the following: determining a fourth resource quantity based on the estimated resource usage and the target range, the fourth resource quantity indicating the sum of the differences between the estimated resource usage of all third content delivery networks and the minimum value in the target range; generating multiple content delivery network combinations, each content delivery network combination containing one or more content delivery networks other than the third content delivery network; determining a fifth resource quantity for each content delivery network combination, the fifth resource quantity indicating the cumulative amount of resources that can be reduced by all content delivery networks within the content delivery network combination; determining candidate combinations from the multiple content delivery network combinations based on the fifth resource quantity of each content delivery network combination, the fifth resource quantity of the candidate combinations being greater than or equal to the fourth resource quantity; and determining one of the candidate combinations as the target optimized combination, and using the content delivery network in the target optimized combination as the fourth content delivery network corresponding to the third content delivery network.

[0168] Optionally, the processing unit 1102 is specifically configured to perform: for each content distribution network combination, determining one or more adjustment schemes corresponding to the content distribution network combination, wherein an adjustment scheme indicates the amount of resources that can be reduced for one or more content distribution networks in the content distribution network combination, and the amount of resources that can be reduced for each content distribution network is the difference between the estimated resource usage of the content distribution network and the minimum value in a preset numerical range corresponding to the content distribution network; and determining one or more fifth resource quantities corresponding to each adjustment scheme based on the content distribution network combination.

[0169] Optionally, the processing unit 1102 is specifically configured to perform the following: based on the target adjustment scheme corresponding to the candidate combination that generates the minimum total target resources, sort the various content distribution networks in the target optimization combination in descending order according to the target resources corresponding to the preset numerical range of the various content distribution networks in the target optimization combination; and in the order of decreasing the target resources corresponding to the preset numerical range of the various content distribution networks in the target optimization combination, sequentially reduce the task volume ratio corresponding to the amount of resources that can be reduced by each content distribution network, until the cumulative amount of network resources consumed by the third content distribution network at the end of the current period is within the target range modified by the third content distribution network.

[0170] As described above, the embodiments of this disclosure can divide the storage device into functional modules according to the above method examples. The integrated modules can be implemented in hardware or as software functional modules. Furthermore, it should be noted that the module division in these embodiments is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into a single processing module.

[0171] The specific methods by which each module performs its operations and the beneficial effects of the network resource scheduling device in the above embodiments have been described in detail in the foregoing method embodiments, and will not be repeated here.

[0172] This disclosure also provides a network resource scheduling device. Figure 8 A schematic diagram of the structure of the network resource scheduling device provided in the embodiments of this disclosure is shown. Figure 2 The network resource scheduling device may include at least one processor 221, a communication bus 222, a memory 223, and at least one communication interface 224.

[0173] Processor 221 may be a central processing unit (CPU), a microprocessor unit, an ASIC, or one or more integrated circuits for controlling the execution of programs according to the present disclosure.

[0174] The communication bus 222 may include a path for transmitting information between the aforementioned components.

[0175] Communication interface 224 uses any transceiver-like device for communicating with other devices or communication networks, such as electronic devices, Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0176] The memory 223 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may exist independently and be connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0177] The memory 223 stores the application code that executes the scheme of this disclosure, and its execution is controlled by the processor 221. The processor 221 executes the application code stored in the memory 223 to implement the functions of the method of this disclosure.

[0178] In a specific implementation, as one embodiment, processor 221 may include one or more central processing units, such as... Figure 8 Central Processing Unit 0 and Central Processing Unit 1.

[0179] In a specific implementation, as one example, the network resource scheduling device may include multiple processors, for example... Figure 8Processors 221 and 225 are described herein. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0180] In a specific implementation, as one embodiment, the network resource scheduling device may further include an input device 226 and an output device 227. The input device 226 and output device 227 communicate and can accept user input in various ways. For example, the input device 226 may be a mouse, keyboard, touchscreen device, or sensor device. The output device 227 communicates with the processor 221 and can display information in various ways. For example, the output device 227 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, etc.

[0181] Those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on the network resource scheduling device, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0182] This disclosure also provides a computer-readable storage medium including instructions stored thereon, wherein when the instructions in the computer-readable storage medium are executed by a processor of a network resource scheduling device, the network resource scheduling device is able to perform the network resource scheduling method provided in the above-described embodiments. For example, the computer-readable storage medium may be a memory 223 including instructions, which may be executed by a processor 221 of the network resource scheduling device to complete the above method.

[0183] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0184] This disclosure also provides a computer program product containing instructions that, when run on an electronic device, cause the electronic device to execute the network resource scheduling method provided in the embodiments described above.

[0185] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0186] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A network resource scheduling method, characterized in that, The method includes: Obtain the amount of resources used and the target range for each content delivery network in the current period, wherein the target range is a preset numerical range to which the amount of network resources planned to be used by the content delivery network in the current period belongs; Based on the amount of resources used for each of the content delivery networks, determine the estimated resource usage for each content delivery network in the current period; Based on the estimated resource usage and the target range of each content distribution network, a second content distribution network is determined from the content distribution networks other than the first content distribution network, wherein the first content distribution network includes one or more content distribution networks whose estimated resource usage is lower than the target range; Increase the proportion of tasks processed by the first content distribution network and decrease the proportion of tasks processed by the second content distribution network, so that at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the first content distribution network is within the target range of the first content distribution network; and at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the second content distribution network is higher than the minimum value in the target range, or higher than the minimum value in the preset value range to which the estimated resource usage actually belongs.

2. The method according to claim 1, characterized in that, Determining the second content distribution network from content distribution networks other than the first content distribution network includes: Based on the content distribution networks other than the first content distribution network, multiple content distribution network combinations are generated, and each content distribution network combination includes one or more content distribution networks other than the first content distribution network; One of the multiple content distribution network combinations is determined as the target optimization combination, and the content distribution network in the target optimization combination is used as the second content distribution network.

3. The method according to claim 2, characterized in that, The step of determining one of the multiple content delivery network combinations as the target optimized combination includes: Based on the estimated resource usage and the target range, a first resource quantity is determined, wherein the first resource quantity indicates the sum of the differences between the estimated resource usage of all the first content delivery networks and the minimum value in the target range; Determine a second resource quantity for each of the content delivery network combinations, the second resource quantity indicating the amount of network resources that can be reduced in total consumption across all content delivery networks within the content delivery network combination; Candidate combinations are determined from the plurality of content distribution network combinations based on the second resource amount of each of the content distribution network combinations, wherein the second resource amount of the candidate combinations is greater than or equal to the first resource amount; One of the candidate combinations is selected as the target optimized combination, and the content distribution network in the target optimized combination is selected as the second content distribution network corresponding to the first content distribution network.

4. The method according to claim 3, characterized in that, The step of determining candidate combinations from the plurality of content delivery network combinations based on the second resource amount of each of the content delivery network combinations includes: According to the preset minimum adjustment granularity, the first resource quantity is rounded up, and the second resource quantity of each content distribution network combination is rounded down. The first resource quantity after rounding up is a positive integer multiple of the minimum adjustment granularity, and the second resource quantity after rounding down is a positive integer multiple of the minimum adjustment granularity. Content delivery networks whose second resource quantity after rounding down is greater than or equal to the first resource quantity after rounding up are determined as the candidate combination.

5. The method according to claim 3, characterized in that, Determining the second resource amount for each of the content delivery network combinations includes: Determine the amount of resources that can be reduced for each content distribution network in each of the content distribution network combinations; wherein, for a content distribution network whose estimated resource usage is lower than the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs; for a content distribution network whose estimated resource usage is higher than the minimum value in the target range, the amount of resources that can be reduced represents the difference between the estimated resource usage of the content distribution network and the minimum value in the target range of the content distribution network. The second resource quantity for each content distribution network combination is obtained based on the amount of resources that can be reduced for each of the content distribution network combinations.

6. The method according to claim 3 or 4, characterized in that, Different preset numerical ranges correspond to different quantities of target resources; The step of determining one of the candidate combinations as the target optimized combination includes: Determine an adjustment strategy for each of the candidate combinations, the adjustment strategy indicating a reduction in the amount of resources used for one or more content delivery networks in the candidate combinations; Based on the adjustment strategy corresponding to each candidate combination and the target resources corresponding to each preset numerical range, the total target resources corresponding to each candidate combination are determined. The total target resources represent the total number of target resources required for the cumulative number of network resources used by the content delivery network at the end of the current period after the number of network resources used by the content delivery network in the candidate combination is reduced according to the corresponding adjustment strategy. The candidate combination that produces the minimum total target resources is determined as the target optimal combination.

7. The method according to claim 6, characterized in that, The method further includes: If there are multiple candidate combinations that generate the minimum total target resource, the candidate combination with the highest network quality and the minimum total target resource is determined as the target optimization combination.

8. The method according to claim 1, characterized in that, The method further includes: If, based on the estimated resource usage and the target range of each content distribution network, no second content distribution network is determined from the content distribution networks other than the first content distribution network, a third resource quantity is determined for each content distribution network. The third resource quantity indicates the difference between the estimated resource usage of the content distribution network and the maximum value in the actual range of the content distribution network, where the actual range is a preset numerical range to which the estimated resource usage belongs. The third content distribution network with a relatively large amount of resources is selected as the third content distribution network. Modify the target range of the third content distribution network to the preset numerical range one level above the actual range corresponding to the third content distribution network; Based on the estimated resource usage and the target range, a fourth content distribution network is determined from the content distribution networks other than the third content distribution network. Increase the proportion of tasks processed by the third content distribution network and decrease the proportion of tasks processed by the fourth content distribution network, so that the cumulative amount of network resources consumed by the third content distribution network at the end of the current period is within the target range of the third content distribution network. Specifically, if, before reducing the proportion of tasks processed by the fourth content distribution network, the estimated resource usage of the fourth content distribution network is higher than the minimum value in the target range, then after reducing the proportion of tasks processed by the fourth content distribution network, the cumulative network resource consumption of the tasks processed by the fourth content distribution network at the end of the current period is higher than the minimum value in the target range; if, before reducing the proportion of tasks processed by the fourth content distribution network, the actual estimated resource usage of the fourth content distribution network falls within a preset value range lower than the target range, then after reducing the proportion of tasks processed by the fourth content distribution network, the cumulative network resource consumption of the tasks processed by the fourth content distribution network at the end of the current period is higher than the minimum value in the preset value range to which the estimated resource usage actually belongs.

9. The method according to claim 8, characterized in that, The step of determining a fourth content distribution network from content distribution networks other than the third content distribution network based on the estimated resource usage and the target range includes: Based on the estimated resource usage and the target range, a fourth resource quantity is determined, which indicates the sum of the differences between the estimated resource usage of all the third content delivery networks and the minimum value in the target range; Generate multiple content distribution network combinations, each of the content distribution network combinations comprising one or more content distribution networks other than the third content distribution network; A fifth resource quantity is determined for each of the content delivery network combinations, the fifth resource quantity indicating the amount of resources that can be reduced in total consumption across all content delivery networks within the content delivery network combination; Based on the fifth resource quantity of each of the content delivery network combinations, candidate combinations are determined from the plurality of content delivery network combinations, wherein the fifth resource quantity of the candidate combinations is greater than or equal to the fourth resource quantity; One of the candidate combinations is selected as the target optimized combination, and the content distribution network in the target optimized combination is selected as the fourth content distribution network corresponding to the third content distribution network.

10. The method according to claim 9, characterized in that, The determination of the fifth resource quantity for each of the content delivery network combinations includes: For each of the content distribution network combinations, one or more adjustment schemes corresponding to the content distribution network combination are determined. One of the adjustment schemes indicates the amount of resources that can be reduced for one or more content distribution networks in the content distribution network combination. The amount of resources that can be reduced for each content distribution network is the difference between the estimated resource usage of the content distribution network and the minimum value in a preset numerical range corresponding to the content distribution network. Based on the content delivery network combination corresponding to each adjustment scheme, determine one or more fifth resource quantities corresponding to each adjustment scheme.

11. The method according to claim 10, characterized in that, Increasing the proportion of tasks processed by the third content delivery network and decreasing the proportion of tasks processed by the fourth content delivery network includes: Based on the target adjustment scheme corresponding to the candidate combination that generates the minimum total target resources, the various content distribution networks in the target optimization combination are arranged in descending order according to the target resources of the various content distribution networks in the target optimization combination corresponding to the preset numerical range of the target resources. According to the order of decreasing target resources corresponding to the preset numerical range of each content distribution network in the target optimization combination, the task volume ratio corresponding to the amount of resources that each content distribution network can reduce is reduced in turn, until the cumulative amount of network resources consumed by the third content distribution network in processing the tasks is within the target range modified by the third content distribution network at the end of the current period.

12. A network resource scheduling device, characterized in that, include: Acquisition unit and processing unit; The acquisition unit is configured to acquire the amount of resources used and the target range of each content delivery network in the current period, wherein the target range is a preset numerical range to which the amount of network resources that the content delivery network plans to use in the current period belongs. The processing unit is configured to perform an operation to determine the estimated resource usage of each content delivery network in the current period based on the amount of resources used for each content delivery network. The processing unit is further configured to perform the following: determine a second content distribution network from content distribution networks other than the first content distribution network based on the estimated resource usage and the target range of each content distribution network, wherein the first content distribution network includes one or more content distribution networks whose estimated resource usage is lower than the target range; The processing unit is further configured to increase the proportion of tasks processed by the first content distribution network and decrease the proportion of tasks processed by the second content distribution network, so that at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the first content distribution network is within the target range of the first content distribution network; and at the end of the current period, the cumulative amount of network resources consumed by the tasks processed by the second content distribution network is higher than the minimum value in the target range, or higher than the minimum value in the preset value range to which the estimated resource usage actually belongs.

13. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the network resource scheduling method as described in any one of claims 1-11.

14. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the network resource scheduling method as described in any one of claims 1-11.

Images