Cross-region bandwidth allocation method and device, computer device, storage medium and computer program product

Abstract

The application relates to a cross-region bandwidth allocation method and device, computer equipment, a storage medium and a computer program product. It relates to the technical field of computers. The method comprises the following steps: acquiring cross-region bandwidth proportions of a plurality of to-be-processed regions; in the case that a first target region with a cross-region bandwidth proportion greater than a corresponding bandwidth proportion threshold exists in each to-be-processed region, re-distributing associated sub-region units of the first target region in each to-be-processed region to obtain a plurality of new regions; acquiring bandwidth entropy of each new region, and determining a second target region with bandwidth entropy less than a bandwidth entropy threshold from each new region; performing gradient adjustment on the second target region and associated regions of the second target region to obtain an updated gradient; and determining a bandwidth allocation scheme for the second target region and the associated regions of the second target region according to the updated gradient. The method can improve the cross-region bandwidth allocation efficiency.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for allocating cross-regional bandwidth. Background Art

[0002] With the development of the internet, users are increasingly demanding interprovincial data usage. However, interprovincial data settlement requires the user's province to pay a fee to the province where the data is used. This results in data usage costs being distributed across different provinces, impacting the operator's revenue structure. Therefore, operators have implemented an interprovincial data settlement mechanism to balance costs and benefits across provinces.

[0003] However, the current traffic settlement mechanism requires content distribution network vendors to control costs while ensuring service quality, meet users' cross-provincial bandwidth needs, and avoid speed limits caused by excessive cross-provincial bandwidth usage. However, the current method suffers from unreasonable node layout and resource allocation strategies, which affects the efficiency of cross-provincial bandwidth allocation. As a result, cross-regional bandwidth allocation is currently inefficient. Summary of the Invention

[0004] Based on this, it is necessary to provide a cross-regional bandwidth allocation method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the above-mentioned technical problem of low efficiency in cross-regional bandwidth allocation.

[0005] In a first aspect, the present application provides a cross-region bandwidth allocation method, comprising:

[0006] Obtain the cross-region bandwidth ratio of multiple areas to be processed;

[0007] In a case where there is a first target area in each of the to-be-processed areas where the cross-area bandwidth ratio is greater than a corresponding bandwidth ratio threshold, sub-area units associated with the first target area are reallocated in each of the to-be-processed areas to obtain a plurality of new areas;

[0008] Obtaining bandwidth entropy of each new area, and determining a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each of the new areas;

[0009] performing gradient adjustment on the second target region and an associated region of the second target region to obtain an updated gradient;

[0010] A bandwidth allocation scheme for the second target area and areas associated with the second target area is determined according to the updated gradient.

[0011] In one embodiment, the associated sub-regional units of the first target area include sub-regional units within the first target area and sub-regional units within other areas to be processed; and the associated sub-regional units of the first target area are reallocated in each of the areas to be processed to obtain multiple new areas, including: obtaining bandwidth data and a cross-regional bandwidth amount of the first target area, and determining a cross-regional bandwidth line of the first target area based on the bandwidth data of the first target area and a current cross-regional bandwidth ratio; selecting an initial sub-regional unit to be scheduled from the associated sub-regional units of the first target area based on the cross-regional bandwidth amount and the cross-regional bandwidth line; if the initial sub-regional unit does not meet an allocation condition, reselecting a sub-regional unit to be scheduled until the selected sub-regional unit meets the allocation condition or reaches a preset termination condition, thereby terminating the reallocation of the associated sub-regional units of the first target area and obtaining multiple new areas.

[0012] In one embodiment, the selecting of the initial sub-regional unit to be scheduled from the associated sub-regional units of the first target region based on the cross-regional bandwidth amount and the cross-regional bandwidth line includes: if the cross-regional bandwidth amount of the first target region is less than the cross-regional bandwidth line, selecting the sub-regional unit to be scheduled from within the first target region; if the cross-regional bandwidth amount of the first target region is greater than or equal to the cross-regional bandwidth line, generating a random temperature within a preset temperature range, and if the random temperature is less than the initial temperature, selecting the sub-regional unit to be scheduled from within the first target region; if the random temperature is greater than or equal to the initial temperature, selecting the sub-regional unit to be scheduled from other to-be-processed regions outside the first target region.

[0013] In one embodiment, the method further includes: determining an initial temperature; the initial temperature represents an iteration benchmark; the preset end condition includes: if it is determined that the number of iterations of the sub-region unit to be scheduled reaches a first number threshold, then lowering the initial temperature, returning to the step of selecting the initial sub-region unit to be scheduled from the associated sub-region units of the first target region based on the cross-region bandwidth amount and the cross-region bandwidth line, until the temperature drops to the temperature threshold or the number of iterations reaches a second number threshold, and the iteration ends.

[0014] In one embodiment, the method further includes: calculating a new cross-regional bandwidth ratio of the first target area after the selected initial sub-regional unit is moved out of the associated sub-regional unit of the first target area; if the new cross-regional bandwidth ratio is lower than the current cross-regional bandwidth ratio, determining that the selected initial sub-regional unit meets the allocation condition; if the cross-regional bandwidth ratio is higher than the current cross-regional bandwidth ratio and is greater than a bandwidth ratio threshold, determining with a predetermined probability that the selected initial sub-regional unit meets the allocation condition; if the cross-regional bandwidth ratio is higher than the current cross-regional bandwidth ratio and is less than or equal to the bandwidth ratio threshold, determining that the selected initial sub-regional unit meets the allocation condition.

[0015] In one embodiment, the associated area of ​​the second target area represents an area that belongs to the same large area as the second target area; the gradient adjustment of the second target area and the associated area of ​​the second target area to obtain an updated gradient includes: for each area in the associated area of ​​the second target area and the second target area, obtaining a bandwidth entropy threshold and a current gradient of the area; determining a current gradient adjustment coefficient for each area based on the bandwidth entropy threshold and bandwidth entropy of each area; and adjusting the current gradient of each area based on the gradient adjustment coefficient of each area to obtain an updated gradient for each area.

[0016] In a second aspect, the present application further provides a cross-region bandwidth allocation device, comprising:

[0017] A data acquisition module, used to obtain the cross-region bandwidth ratio of multiple areas to be processed;

[0018] An allocating module, configured to, if a first target area having a cross-area bandwidth ratio greater than a corresponding bandwidth ratio threshold exists in each of the areas to be processed, reallocate sub-area units associated with the first target area in each of the areas to be processed to obtain a plurality of new areas;

[0019] The data acquisition module is further configured to acquire bandwidth entropy of each new area, and determine a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each new area;

[0020] a data adjustment module, configured to perform gradient adjustment on the second target area and an area associated with the second target area to obtain an updated gradient;

[0021] A scheme determining module is configured to determine a bandwidth allocation scheme for the second target area and an area associated with the second target area according to the updated gradient.

[0022] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0023] obtaining cross-region bandwidth ratios of a plurality of to-be-processed regions;

[0024] in a case where a first target region with a cross-region bandwidth ratio greater than a corresponding bandwidth ratio threshold exists in each of the to-be-processed regions, re-allocating associated sub-region units of the first target region in each of the to-be-processed regions to obtain a plurality of new regions;

[0025] obtaining bandwidth entropies of each of the new regions, and determining a second target region with a bandwidth entropy less than a bandwidth entropy threshold from each of the new regions;

[0026] performing gradient adjustment on the second target region and an associated region of the second target region to obtain an updated gradient;

[0027] determining a bandwidth allocation scheme for the second target region and the associated region of the second target region according to the updated gradient.

[0028] In a fourth aspect, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0029] obtaining cross-region bandwidth ratios of a plurality of to-be-processed regions;

[0030] in a case where a first target region with a cross-region bandwidth ratio greater than a corresponding bandwidth ratio threshold exists in each of the to-be-processed regions, re-allocating associated sub-region units of the first target region in each of the to-be-processed regions to obtain a plurality of new regions;

[0031] obtaining bandwidth entropies of each of the new regions, and determining a second target region with a bandwidth entropy less than a bandwidth entropy threshold from each of the new regions;

[0032] performing gradient adjustment on the second target region and an associated region of the second target region to obtain an updated gradient;

[0033] determining a bandwidth allocation scheme for the second target region and the associated region of the second target region according to the updated gradient.

[0034] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the following steps:

[0035] Obtain the cross-region bandwidth ratio of multiple areas to be processed;

[0036] In a case where there is a first target area in each of the to-be-processed areas where the cross-area bandwidth ratio is greater than a corresponding bandwidth ratio threshold, sub-area units associated with the first target area are reallocated in each of the to-be-processed areas to obtain a plurality of new areas;

[0037] Obtaining bandwidth entropy of each new area, and determining a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each of the new areas;

[0038] performing gradient adjustment on the second target region and an associated region of the second target region to obtain an updated gradient;

[0039] A bandwidth allocation scheme for the second target area and areas associated with the second target area is determined according to the updated gradient.

[0040] The above-mentioned cross-region bandwidth allocation method, apparatus, computer equipment, storage medium and computer program product, in the process of cross-region bandwidth allocation, first obtain the cross-region bandwidth ratio of multiple to-be-processed areas; then, if there is a first target area in each to-be-processed area whose cross-region bandwidth ratio is greater than the corresponding bandwidth ratio threshold, the associated sub-region units of the first target area are reallocated in each to-be-processed area to obtain multiple new areas; then, the bandwidth entropy of each new area is obtained, and a second target area whose bandwidth entropy is less than the bandwidth entropy threshold is determined from each new area; then, the gradient of the second target area and the associated area of ​​the second target area is adjusted to obtain an updated gradient; finally, based on the updated gradient, a bandwidth allocation plan for the second target area and the associated area of ​​the second target area is determined. In the above process, by calculating the cross-region bandwidth ratio of different to-be-processed areas, a first target area requiring priority processing is obtained, and then the associated sub-areas in the first target area are re-divided to form new areas, which can more reasonably allocate bandwidth resources. Then, by calculating the bandwidth entropy of the new area, a second target area with a bandwidth entropy less than a threshold is screened out, which can ensure efficient bandwidth utilization and reduce resource waste. Gradient adjustment is then performed on the screened second target area and the associated areas to optimize the bandwidth allocation plan and dynamically balance bandwidth demand. Based on the updated gradient, the bandwidth allocation plan is adjusted to achieve intelligent bandwidth scheduling, thereby improving the efficiency of cross-region bandwidth allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 Schematic diagram of a flow chart of a method for allocating cross-region bandwidth in one embodiment;

[0043] Figure 2 A schematic diagram of a process for acquiring multiple new zones in a method for allocating bandwidth across zones in one embodiment;

[0044] Figure 3 1 is a schematic diagram of a process for obtaining an updated gradient in a method for allocating bandwidth across regions in one embodiment;

[0045] Figure 4 is a schematic diagram of a cross-region bandwidth allocation system in one embodiment;

[0046] Figure 5 is a detailed schematic diagram of a cross-region bandwidth allocation method in one embodiment;

[0047] Figure 6 is a detailed schematic diagram of a cross-region bandwidth allocation method in another embodiment;

[0048] Figure 7 is a structural block diagram of a cross-region bandwidth allocation device in one embodiment;

[0049] Figure 8 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] With the rapid development of the mobile internet, users' demand for data traffic is growing, especially for interprovincial traffic usage. To address this change, operators have implemented an interprovincial traffic settlement mechanism to balance costs and benefits across provinces. However, this mechanism presents new challenges for content delivery network (CDN) vendors, who must effectively control costs and optimize node layout and resource allocation strategies while ensuring service quality. Interprovincial traffic settlement refers to a mechanism whereby when a user uses data traffic in a province other than their home province, the user's home province pays the province where the traffic is used. This mechanism distributes data traffic costs across provinces, impacting the operator's revenue structure. For CDN vendors, this means they need to more meticulously manage traffic distribution to adapt to the traffic demands and cost structures of different provinces.

[0052] Currently, CDN vendors face two major challenges in this context: first, how to meet the growing demand for interprovincial bandwidth without increasing costs; second, how to avoid speed throttling caused by an excessively high proportion of interprovincial bandwidth and ensure user experience. To address these challenges, CDN vendors need to optimize their bandwidth allocation strategies, improve resource utilization efficiency, and ensure service quality.

[0053] In addition, in this application, lake, also known as node / region, is the logical representation of the computer room, which is related to the operator and is a collection of host groups, representing the physical or logical structure of the data center; pv is the abbreviation of resolution group (P) and region (V), corresponding to the sub-region unit in this application, usually refers to the basic unit that requires resource allocation and scheduling in the scheduling system; inter-provincial (inter-regional) traffic settlement refers to the mechanism in which when a user uses data traffic in a province other than his / her home province, the province to which the user belongs pays fees to the province where the traffic is used; heuristic link scheduling refers to the heuristic algorithm used by the current scheduling system to optimize link selection to balance cost and service quality; regional bandwidth entropy is a measure used to evaluate the uniformity of bandwidth distribution, reflecting the uniformity of bandwidth distribution; gradient is the value of the lake granularity obtained by recalculating the redundancy of the lake, which represents the degree of attraction to the lake's super-cost line bandwidth. The larger the gradient value, the stronger the directionality from the source lake to the lake.

[0054] In one embodiment, Figure 1 As shown, a method for allocating cross-regional bandwidth is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0055] Step S102: Obtain cross-region bandwidth ratios of multiple regions to be processed.

[0056] The to-be-processed region refers to a geographical or logical region that needs to be subjected to bandwidth resource optimization adjustment, and can be a region that has not completed dynamic scheduling. The cross-region bandwidth proportion is used to measure the distribution proportion of bandwidth resources in a to-be-processed region among multiple regions, and can be used to reflect the utilization of bandwidth among to-be-processed regions.

[0057] In step S104, in the case that there is a first target region in which the cross-region bandwidth proportion is greater than the corresponding bandwidth proportion threshold in each to-be-processed region, the associated sub-region units of the first target region are re-allocated in each to-be-processed region, to obtain multiple new regions.

[0058] The first target region is a region that is subjected to preferential processing according to the comparison result of the cross-region bandwidth proportion and the bandwidth proportion threshold, and is a region in which bandwidth resources are in short supply. The associated sub-region unit is the pv mentioned above, and can be a sub-region or a sub-unit in the first target region, is associated with the first target region, and needs to be dynamically adjusted in bandwidth allocation. The re-allocation is a process of adjusting the sub-region unit according to the change in bandwidth demand of the to-be-processed region. The multiple new regions are more balanced bandwidth allocation units formed.

[0059] In step S106, the bandwidth entropy of each new region is obtained, and a second target region in which the bandwidth entropy is less than a bandwidth entropy threshold is determined from each new region.

[0060] The bandwidth entropy can be used to measure the uniformity of the distribution of bandwidth resources in a region. The lower the entropy, the more concentrated the distribution of bandwidth resources in the new region, and the higher the utilization efficiency. The bandwidth entropy threshold is a preset limit, and is used to screen the second target region with a more reasonable distribution. The second target region is a region with a more reasonable bandwidth distribution after screening.

[0061] In step S108, gradient adjustment is performed on the second target region and the associated region of the second target region, to obtain an updated gradient.

[0062] The gradient adjustment is to adjust the gradient of the second target region and the associated region of the second target region, so that the resource configuration between the second target region and the associated region of the second target region is in an optimal state. The updated gradient is data used to reflect the current optimal bandwidth scheduling direction after adjustment.

[0063] In step S110, a bandwidth allocation scheme for the second target region and the associated region of the second target region is determined according to the updated gradient.

[0064] The bandwidth allocation scheme is a specific resource scheduling strategy, which can include the bandwidth allocation value or proportion of each region and the associated region, and is used for actual bandwidth regulation.

[0065] In the above-mentioned cross-region bandwidth allocation method, the cross-region bandwidth ratios of multiple to-be-processed regions are first obtained; then, if there is a first target region in each to-be-processed region whose cross-region bandwidth ratio is greater than the corresponding bandwidth ratio threshold, the associated sub-region units of the first target region are reallocated in each to-be-processed region to obtain multiple new regions; then, the bandwidth entropy of each new region is obtained, and a second target region whose bandwidth entropy is less than the bandwidth entropy threshold is determined from each new region; then, a gradient adjustment is performed on the second target region and the associated region of the second target region to obtain an updated gradient; finally, based on the updated gradient, a bandwidth allocation scheme for the second target region and the associated region of the second target region is determined. In the above process, by calculating the cross-region bandwidth ratio of different to-be-processed areas, a first target area requiring priority processing is obtained, and then the associated sub-areas in the first target area are re-divided to form new areas, which can more reasonably allocate bandwidth resources. Then, by calculating the bandwidth entropy of the new area, a second target area with a bandwidth entropy less than a threshold is screened out, which can ensure efficient bandwidth utilization and reduce resource waste. Gradient adjustment is then performed on the screened second target area and the associated areas to optimize the bandwidth allocation plan and dynamically balance bandwidth demand. Based on the updated gradient, the bandwidth allocation plan is adjusted to achieve intelligent bandwidth scheduling, thereby improving the efficiency of cross-region bandwidth allocation.

[0066] In an exemplary embodiment, Figure 2 As shown, the associated sub-region units of the first target region include sub-region units in the first target region and sub-region units in other regions to be processed;

[0067] The associated sub-regional units of the first target region are reallocated among the regions to be processed to obtain a plurality of new regions, including: step S202, obtaining bandwidth data and a cross-regional bandwidth amount of the first target region; step S204, determining a cross-regional bandwidth line of the first target region based on the bandwidth data of the first target region and a current cross-regional bandwidth ratio; step S206, selecting an initial sub-regional unit to be scheduled from the associated sub-regional units of the first target region based on the cross-regional bandwidth amount and the cross-regional bandwidth line; step S208, if the initial sub-regional unit does not meet the allocation condition, reselecting a sub-regional unit to be scheduled, until the selected sub-regional unit meets the allocation condition or reaches a preset end condition, thereby completing the reallocation of the associated sub-regional units of the first target region and obtaining a plurality of new regions.

[0068] Among them, the associated sub-region units of the first target area may include sub-region units within the first target area and sub-region units within other areas to be processed, which are all sub-region units associated with the first target area; reallocation is to adjust the bandwidth resource allocation of the sub-region units; bandwidth data is the current bandwidth utilization of the first target area; the cross-region bandwidth volume is the total bandwidth traffic between the first target area and other areas, which can be used to reflect the connection strength and bandwidth usage between regions; the cross-region bandwidth line can help determine which sub-regions can be scheduled; the sub-region unit to be scheduled is a sub-region that meets the scheduling conditions and is adjustable, and can be used to reallocate bandwidth; the allocation condition can be a conditional restriction on the scheduling sub-region, such as bandwidth demand, current utilization, priority, etc.; the preset end condition can be the termination point of the restricted scheduling cycle, such as reaching a certain number of times, meeting the overall goal, or there are no more sub-regions that meet the conditions.

[0069] In addition, the process of determining the sub-regional units to be scheduled may be: according to the relationship between the cross-regional bandwidth amount and the bandwidth line, sub-regional units with low capacity or requiring adjustment are selected as sub-regional units to be scheduled.

[0070] In this embodiment, by reselecting sub-area units if the allocation conditions are not met until the conditions are met or the preset end conditions are reached, circular scheduling can be achieved, sub-areas can be dynamically screened, and units that do not meet the conditions can be gradually screened out. After a series of screening and scheduling, a group of sub-areas are formed for subsequent resource allocation or management, thereby improving efficiency.

[0071] Furthermore, in an exemplary embodiment, selecting an initial sub-area unit to be scheduled from the associated sub-area units of the first target area based on the inter-area bandwidth amount and the inter-area bandwidth line includes:

[0072] If the cross-regional bandwidth of the first target area is less than the cross-regional bandwidth line, a sub-regional unit for scheduling is selected from the first target area; if the cross-regional bandwidth of the first target area is greater than or equal to the cross-regional bandwidth line, a random temperature is generated within the preset temperature range. If the random temperature is less than the initial temperature, a sub-regional unit for scheduling is selected from the first target area; if the random temperature is greater than or equal to the initial temperature, a sub-regional unit for scheduling is selected from other to-be-processed areas outside the first target area.

[0073] Among them, the cross-regional bandwidth volume is the sum of the bandwidth traffic between the current region and other regions, reflecting the actual usage of the bandwidth between regions and can be used to judge the bandwidth pressure of the first target region; the cross-regional bandwidth line is a boundary set based on bandwidth data and proportional relationships, which can be used to divide the critical value of the scheduling rules. By comparing the cross-regional bandwidth volume and the cross-regional bandwidth line of the first target region, the subsequent scheduling behavior can be determined.

[0074] Exemplarily, if the cross-region bandwidth amount of the first target region is less than the region bandwidth line, a scheduling object is selected within the region, and optimization is performed by using the intra-region resource; if the cross-region bandwidth amount of the first target region is greater than or equal to the region bandwidth line, a random temperature is generated within a preset temperature range, the temperature can be a random preference for scheduling or a disturbance parameter; and according to the size relationship between the random temperature and the initial temperature, a sub-region unit is determined.

[0075] In this embodiment, by combining the region bandwidth amount with the region bandwidth line, and by using the random temperature scheduling mechanism, while ensuring that the intra-region resource is given priority, the exploration of the external region resource is also allowed, which is helpful to achieve efficient bandwidth scheduling balance and improve the bandwidth scheduling efficiency.

[0076] Further, in an exemplary embodiment, the method further includes: determining an initial temperature; the initial temperature represents an iteration reference; and the preset end condition includes: if the iteration number of the sub-region unit to be scheduled reaches a first number threshold, the initial temperature is reduced, and the step of selecting the initial sub-region unit to be scheduled from the associated sub-region unit of the first target region based on the cross-region bandwidth amount and the cross-region bandwidth line is returned until the temperature is reduced to a temperature threshold or the iteration number reaches a second number threshold, and the iteration is ended.

[0077] In this embodiment, the initial temperature is determined as a basic temperature value at the beginning of scheduling, as a starting parameter of random scheduling, and can be used as a reference point of random scheduling in the iteration process. The initial temperature represents an iteration reference, which means that the initial temperature is a reference value that affects the acceptance degree of the solution obtained by the iteration result (the higher the temperature, the greater the possibility of accepting a relatively poor solution). The preset end condition is a termination criterion set in advance, which is used to control the running time and convergence. The iteration number of the sub-region unit to be scheduled reaching the first number threshold means that if the preset maximum number is reached in each sub-region scheduling iteration, it indicates that the current scheme has been fully attempted. The step of returning to the scheduling based on the cross-region bandwidth amount and the bandwidth line is to reselect the sub-region unit to be scheduled according to the scheduling strategy, and to perform scheduling by fusing the bandwidth amount and the bandwidth line information. The temperature being reduced to the temperature threshold is a set minimum temperature limit, which is used to ensure that the randomness is no longer infinitely reduced, and to avoid premature convergence. The iteration number reaching the second number threshold is the maximum iteration number allowed by the algorithm, and the scheduling is stopped when the number exceeds the threshold to prevent infinite loop. The iteration being ended means that when the temperature reaches the threshold or the iteration number reaches the upper limit, the algorithm is finally stopped, and the optimization result is output.

[0078] In this embodiment, in the iteration process, by combining the temperature control and the number threshold, it can be ensured that the scheduling process can fully search the scheduling region and converge within a reasonable time, thereby improving the efficiency of the cross-region bandwidth scheduling.

[0079] In one embodiment, the method further includes: calculating a new cross-region bandwidth ratio of the first target area after the selected initial sub-region unit is moved out of the associated sub-region units of the first target area; if the new cross-region bandwidth ratio is lower than the current cross-region bandwidth ratio, determining that the selected initial sub-region unit meets the allocation condition; if the cross-region bandwidth ratio is higher than the current cross-region bandwidth ratio and is greater than a bandwidth ratio threshold, determining with a predetermined probability that the selected initial sub-region unit meets the allocation condition; if the cross-region bandwidth ratio is higher than the current cross-region bandwidth ratio and is less than or equal to the bandwidth ratio threshold, determining that the selected initial sub-region unit meets the allocation condition.

[0080] The new cross-region bandwidth ratio of the first target region refers to the recalculated bandwidth ratio of the region across other regions after the sub-region is removed, which can reflect the resource changes between regions after the adjustment. The relationship between the new cross-region bandwidth ratio and the current cross-region bandwidth ratio includes increases and decreases. A decrease means that after the adjustment, the cross-region bandwidth ratio of the region becomes smaller, which means that the bandwidth usage between regions tends to be balanced or reduced. Meeting the allocation conditions means that the scheduling of the sub-region meets the preset resource allocation or policy requirements. An increase that is greater than the bandwidth ratio threshold means that after the sub-region is removed, the cross-region bandwidth ratio increases and exceeds the established threshold, which may indicate excessive resource concentration and the need for adjustment. An increase that is less than or equal to the bandwidth ratio threshold means that although the ratio has increased, it is still within the threshold range, indicating that the adjustment may be reasonable or the risk is low.

[0081] In this embodiment, by dynamically evaluating the impact of sub-area removal on the overall bandwidth ratio, comparing the change trend and threshold, and combining probabilistic judgment, a scientific determination is made as to whether the sub-area meets the scheduling conditions, thereby optimizing the reasonable allocation and balance of bandwidth resources.

[0082] In addition, in an exemplary embodiment, Figure 3 As shown, the associated area of ​​the second target area represents an area that belongs to the same large area as the second target area; performing gradient adjustment on the second target area and the associated area of ​​the second target area to obtain an updated gradient includes: step S302, for each area in the associated area of ​​the second target area and the second target area, obtaining the bandwidth entropy threshold and current gradient of the area; step S304, determining the current gradient adjustment coefficient for each area based on the bandwidth entropy threshold and bandwidth entropy of each area; step S306, adjusting the current gradient of each area based on the gradient adjustment coefficient of each area to obtain an updated gradient for each area.

[0083] Among them, gradient adjustment is to fine-tune the gradient values ​​of the second target area and the associated areas of the second target area based on the optimization goal, such as bandwidth entropy. The updated gradient is a new gradient generated through adjustment based on the original gradient, which can be used for subsequent resource scheduling. The bandwidth entropy threshold is a preset indicator threshold used to screen or judge bandwidth utilization efficiency. The current gradient is the gradient value of the area in the current state, representing the trend or rate of change of resource scheduling. The adjustment coefficient can be a numerical value used to adjust the gradient to ensure that the adjustment is neither excessive nor insufficient.

[0084] As an example, adjusting the current gradient of each region may be multiplying the original gradient of each region by a corresponding adjustment coefficient to obtain an updated gradient.

[0085] In this embodiment, the gradient value is dynamically adjusted by combining the bandwidth entropy index with the status of each region, gradually guiding the bandwidth resources to evolve toward a more reasonable and efficient distribution state, thereby improving the efficiency of cross-regional bandwidth allocation.

[0086] More importantly, in the implementation process of the present application method, the cooperation between the cross-provincial (cross-regional) bandwidth ratio configuration module, the cross-provincial bandwidth ratio value acquisition module and the heuristic link scheduling module based on simulated annealing is indispensable. Among them, the cross-provincial bandwidth ratio configuration module, that is, the configuration module of the SDCP platform configures the cross-provincial speed-limited lake, mainly configuring the cross-provincial ratio or specific value of the speed-limited lake, and finally providing the lake bandwidth data and cross-provincial ratio data to the subsequent modules in the form of an interface; the cross-provincial bandwidth ratio value acquisition module is responsible for regularly obtaining the real-time bandwidth data, cross-provincial bandwidth ratio configuration and cross-provincial bandwidth volume data of the lake from the SDCP platform, and providing the above data to the subsequent scheduling module; the heuristic link scheduling module based on simulated annealing uses a heuristic link scheduling strategy based on the simulated annealing algorithm to dynamically adjust the bandwidth of the super-cost line lake, shaving peaks and filling valleys to optimize cost control and service quality.

[0087] Therefore, in order to better understand the process of the above cross-region bandwidth allocation method, combined with Figure 4 As shown in the schematic diagram of the cross-regional bandwidth allocation system, in one embodiment, the cross-provincial bandwidth data acquisition module obtains the data of each node to be processed from the SDCP platform and transmits it to the simulated annealing module and the regional bandwidth entropy module respectively, wherein the data in the simulated annealing module is directly transmitted to the heuristic chain scheduling module, and the data in the regional bandwidth entropy module needs to pass through the large-region gradient adjustment module before being sent to the heuristic chain scheduling module, and finally a bandwidth shifting plan (the cross-regional bandwidth allocation plan for each of the nodes to be processed) is obtained.

[0088] In addition, the cross-provincial bandwidth ratio value acquisition module is suitable for data collection modules. For example, it regularly (every 5 minutes) requests the bandwidth data, cross-provincial ratio configuration, and cross-provincial bandwidth volume data of all lakes in the entire network from the SDCP platform; then, based on the bandwidth data and cross-provincial ratio data of each lake currently collected, it calculates the cross-provincial bandwidth line of each lake; if the cross-provincial bandwidth volume of a lake exceeds the cross-provincial bandwidth line, the lake is marked as 1; if the cross-provincial bandwidth volume of a lake is less than the cross-provincial bandwidth line, the lake is marked as 0; if the lake does not have a cross-provincial speed limit ratio configuration, the lake is marked as 0.

[0089] In addition, the simulated annealing calculation module for inter-provincial bandwidth transfer selects the transfer strategy through the simulated annealing algorithm. When the inter-provincial bandwidth ratio of a lake exceeds the limit, the simulated annealing algorithm will be used to decide whether to transfer out the PV of the other province or the PV of the same province. The algorithm will simulate multiple possible scheduling schemes and converge to a feasible scheme through a certain iteration based on the mark of the lake. The simulated annealing algorithm is a probabilistic algorithm that finds the optimal solution to the problem by simulating the particle movement in the physical annealing process. The specific steps include: initialization, selecting the super-cost line lake and the PV list associated with the lake, the initial temperature, such as 90, and the initial temperature range is [0-100]; iteration, during the transfer process, if the inter-provincial bandwidth of the lake is less than the inter-provincial bandwidth line, then randomly select a PV from the current lake for scheduling. During the transfer process, if the inter-provincial bandwidth of the lake is greater than or equal to the inter-provincial bandwidth line, then at the current temperature, generate a PV in the range of [0-100]. Random value: If the random value is less than the current temperature, a PV is randomly selected from the current lake for scheduling. If the random value is greater than the current temperature, one is selected from the PVs in other provinces of the lake for scheduling, and the inter-provincial bandwidth line is recalculated according to the inter-provincial ratio of the lake. Acceptance criterion: If the called PV can find a lake that meets the relevant restrictions to take over, otherwise reselect the PV. If the PV currently called out by the lake can reduce the inter-provincial bandwidth ratio, the new solution is accepted. If the PV currently called out by the lake increases the inter-provincial bandwidth ratio, if the increase exceeds the inter-provincial bandwidth ratio threshold configured for the lake, the new solution is accepted with a certain probability, and the probability decreases as the temperature decreases. If the increase is less than the inter-provincial bandwidth ratio threshold configured for the lake, the new solution is accepted. Cooling: When a certain number of iterations is reached, the temperature is lowered and the two steps after initialization are repeated. Termination: When the temperature drops to a certain threshold or the maximum number of iterations is reached, the algorithm terminates.

[0090] In addition, the regional bandwidth entropy calculation module is used to calculate the entropy of the lake's regional bandwidth to evaluate the uniformity of bandwidth distribution and to subsequently adjust the regional gradient. The entropy H(X) is calculated as follows:

[0091]

[0092] Among them, p(x i ) is the ratio of the bandwidth of the ith region on the lake to the total bandwidth of the lake.

[0093] In the above process, the calculation of entropy requires real-time monitoring and statistics of the regional bandwidth of each lake; the regional affiliation calculation is to calculate the region corresponding to the current region based on the regional and geographical level information in the PV. For example, the region to which Jiangxi belongs is East China. The regional bandwidth entropy of the lake is calculated according to the entropy calculation formula, and then according to the configured regional bandwidth entropy threshold, it is decided whether the gradient gravity of the target region needs to be adjusted; if the regional bandwidth entropy is greater than the threshold, it means that the lake covers the amount of multiple regions of the analysis group, there is no obvious regional directionality, and there is no need to adjust the regional gradient; if the regional bandwidth entropy is less than the threshold, it means that the amount of the analysis group covered on the lake in multiple regions is obviously uneven, and the regional gradient needs to be adjusted.

[0094] In addition, the regional gradient gravity adjustment module dynamically adjusts the regional gradient gravity based on the lake's regional bandwidth entropy to optimize cross-provincial bandwidth scheduling. The gradient gravity adjustment formula is:

[0095]

[0096] Where α is the adjustment coefficient (hyperparameter, configurable), Hthreshold is the threshold of regional bandwidth entropy, and Hcurrent is the entropy value of the current regional bandwidth.

[0097] The gradient gravity adjustment strategy can include: based on the results of the regional bandwidth entropy calculation module, if the regional gradient does not need to be strengthened, then do not continue the subsequent process; if the regional gradient needs to be strengthened, then continue; regional gradient adjustment includes: calculating the list of lakes under the regional gradient that needs to be strengthened based on the regional-lake relationship; and updating the gradient of each lake in the list according to the formula.

[0098] More importantly, the heuristic chain scheduling module is a module that inputs the lake data after gradient adjustment and other data required for scheduling into the heuristic chain scheduling module to calculate and generate the scheduling plan.

[0099] In a specific embodiment, combining Figure 5 As shown in the figure, there is a chain scheduling with cross-province ratio restriction. Assume that Lake1 has cross-province restriction and the restriction ratio is 20% (that is, the out-of-province traffic on Lake1 can only retain 35% of the lake bandwidth). The PV situation on Lake1 is as follows Figure 5 and Figure 6As shown, v1 is in the same province (same region) as lake1, v2 is in the same province as lake2, and v3 is in the same province as lake3. Lake1 now exceeds the cost line 3g, but due to the special resource limitations of lake2, p4v2 cannot be covered by lake2. Therefore, it is impossible to simultaneously meet the peak shaving and cross-province ratio requirements by scheduling only out-of-province traffic. After convergence calculations using simulated annealing, it is possible to achieve peak shaving for lake1 and meet the cross-province ratio requirement by moving p1v1 and p3v3 to lake3 and moving p4v1 and p5v1.

[0100] In addition, combined Figure 5 and Figure 6 As shown in the figure, chain scheduling requires gradient reinforcement. Assume that Lake1 exceeds the cost line by 4G at this time, and Lake8 has sufficient redundancy to take on 4G of traffic. The gradient value of Lake2 is 0.5, and the gradient value of Lake3 is 0.3. It is obvious that the pulling effect of the Central China region on Lake1 will be greater than that of the North China region. However, because the redundancy of Lake2 and Lake5 in the Central China region is insufficient to take on 4G of traffic, without gradient reinforcement, chain scheduling will most likely move traffic to the Central China region, which may result in the failure of the solution to be successfully generated. By calculating the entropy value of the regional bandwidth and strengthening the regional gradient, the gradient of Lake3 under the North China region is updated to 0.7. After moving P2V3 and P3V3 of Lake1 to Lake3, Lake3 reaches Lake8 through Lake4, successfully reducing the peak of Lake1.

[0101] Through the above embodiments, the global search capability of the simulated annealing algorithm is combined with the local optimization characteristics of the heuristic link scheduling to achieve global optimization of the bandwidth allocation strategy; the simulated annealing algorithm allows a wider range of search in the initial stage, which helps to escape the local optimal solution, while the heuristic link scheduling makes fine adjustments to the solution in the later stage of the algorithm, thereby improving the convergence speed of the algorithm and the quality of the solution; and, by introducing regional bandwidth entropy, the regional gradient gravity is amplified to strengthen the directional traction of the gradient; the introduction of the concept of regional bandwidth entropy can quantify the uniformity of bandwidth distribution between different regions, providing a scientific basis for cost scheduling; further, by calculating the regional bandwidth entropy, the bandwidth allocation strategy can be adjusted according to the regional distribution of lake bandwidth, the regional gradient gravity can be adjusted, and the success rate of the cross-regional chain scheduling solution can be improved.

[0102] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0103] Based on the same inventive concept, embodiments of the present application also provide a cross-regional bandwidth allocation device for implementing the cross-regional bandwidth allocation method described above. The solution provided by this device is similar to the solution described in the method described above. Therefore, the specific limitations of one or more cross-regional bandwidth allocation device embodiments provided below can be found in the above-mentioned limitations of the cross-regional bandwidth allocation method and will not be further elaborated here.

[0104] In an exemplary embodiment, Figure 7 As shown, a cross-region bandwidth allocation device is provided, including: a data acquisition module 701, an allocation module 702, a data adjustment module 703 and a solution determination module 704, wherein:

[0105] The data acquisition module 701 is used to obtain the cross-region bandwidth ratio of multiple areas to be processed.

[0106] The allocation module 702 is configured to reallocate the associated sub-region units of the first target region among the regions to be processed to obtain multiple new regions when there is a first target region whose cross-region bandwidth ratio is greater than a corresponding bandwidth ratio threshold among the regions to be processed.

[0107] The data acquisition module 701 is further configured to acquire bandwidth entropy of each new area, and determine a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each new area.

[0108] A data adjustment module 703 is configured to perform gradient adjustment on the second target area and the associated area of ​​the second target area to obtain an updated gradient;

[0109] The solution determination module 704 is configured to determine a bandwidth allocation solution for the second target area and areas associated with the second target area according to the updated gradient.

[0110] Furthermore, in one embodiment, the allocation module 702 is further configured to obtain bandwidth data and cross-regional bandwidth amounts of the first target area, determine a cross-regional bandwidth line of the first target area based on the bandwidth data of the first target area and the current cross-regional bandwidth ratio; select an initial sub-regional unit to be scheduled from the associated sub-regional units of the first target area based on the cross-regional bandwidth amounts and the cross-regional bandwidth line; if the initial sub-regional unit does not meet the allocation conditions, reselect the sub-regional unit to be scheduled until the selected sub-regional unit meets the allocation conditions or reaches a preset termination condition, thereby terminating the reallocation of the associated sub-regional units of the first target area and obtaining multiple new areas.

[0111] Furthermore, in one embodiment, the allocation module 702 is also used to select a scheduled sub-regional unit from the first target area if the cross-regional bandwidth amount of the first target area is less than the cross-regional bandwidth line; if the cross-regional bandwidth amount of the first target area is greater than or equal to the cross-regional bandwidth line, generate a random temperature within a preset temperature range; if the random temperature is less than the initial temperature, select a scheduled sub-regional unit from the first target area; if the random temperature is greater than or equal to the initial temperature, select a scheduled sub-regional unit from other to-be-processed areas outside the first target area.

[0112] Furthermore, in one embodiment, the allocation module 702 is further configured to calculate a new cross-region bandwidth ratio of the first target area after the selected initial sub-region unit is moved out of the associated sub-region units of the first target area; if the new cross-region bandwidth ratio is lower than the current cross-region bandwidth ratio, then the selected initial sub-region unit is determined to meet the allocation condition; if the cross-region bandwidth ratio is higher than the current cross-region bandwidth ratio and is greater than a bandwidth ratio threshold, then the selected initial sub-region unit is determined to meet the allocation condition with a predetermined probability; if the cross-region bandwidth ratio is higher than the current cross-region bandwidth ratio and is less than or equal to the bandwidth ratio threshold, then the selected initial sub-region unit is determined to meet the allocation condition.

[0113] Furthermore, in one embodiment, the data adjustment module 703 is also used to obtain the bandwidth entropy threshold and current gradient of each area in the second target area and the associated area of ​​the second target area; determine the current gradient adjustment coefficient for each area based on the bandwidth entropy threshold and bandwidth entropy of each area; and adjust the current gradient of each area based on the gradient adjustment coefficient of each area to obtain an updated gradient for each area.

[0114] Each module in the above-mentioned cross-regional bandwidth allocation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0115] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store cross-regional bandwidth allocation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a cross-regional bandwidth allocation method is implemented.

[0116] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0117] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0118] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0119] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0121] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0122] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A cross-region bandwidth allocation method, characterized in that: The method comprises: Obtain the cross-region bandwidth ratio of multiple areas to be processed; In a case where a first target area having a cross-area bandwidth ratio greater than a corresponding bandwidth ratio threshold exists in each of the to-be-processed areas, sub-area units associated with the first target area are reallocated in each of the to-be-processed areas to obtain a plurality of new areas; the associated sub-area units of the first target area include sub-area units within the first target area and sub-area units within other to-be-processed areas; the reallocation is to adjust bandwidth resource allocation of the sub-area units; Obtaining bandwidth entropy of each new area, and determining a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each of the new areas; performing gradient adjustment on the second target area and an associated area of ​​the second target area to obtain an updated gradient; the associated area of ​​the second target area represents an area that belongs to the same large region as the second target area; A bandwidth allocation scheme for the second target area and areas associated with the second target area is determined according to the updated gradient.

2. The method according to claim 1, characterized in that The sub-region units associated with the first target region are reallocated in each of the regions to be processed to obtain a plurality of new regions, including: Obtaining bandwidth data and a cross-region bandwidth amount of the first target area, and determining a cross-region bandwidth line of the first target area based on the bandwidth data of the first target area and a current cross-region bandwidth ratio; Selecting an initial sub-area unit to be scheduled from the associated sub-area units of the first target area based on the inter-area bandwidth amount and the inter-area bandwidth line; If the initial sub-area unit does not meet the allocation condition, the sub-area unit to be scheduled is reselected until the selected sub-area unit meets the allocation condition or reaches the preset end condition, and the reallocation of the associated sub-area units of the first target area is ended to obtain multiple new areas.

3. The method according to claim 2, characterized in that The selecting, based on the inter-regional bandwidth amount and the inter-regional bandwidth line, an initial sub-regional unit to be scheduled from the associated sub-regional units of the first target region includes: If the inter-region bandwidth amount of the first target region is less than the inter-region bandwidth line, selecting a sub-region unit for scheduling from within the first target region; If the cross-region bandwidth of the first target area is greater than or equal to the cross-region bandwidth line, a random temperature is generated within the preset temperature range. If the random temperature is less than the initial temperature, a sub-region unit is selected for scheduling from within the first target area; if the random temperature is greater than or equal to the initial temperature, a sub-region unit is selected for scheduling from other to-be-processed areas outside the first target area.

4. The method according to claim 2, characterized in that Also includes: Determine the initial temperature; The initial temperature represents an iteration benchmark; The preset termination condition includes: if it is determined that the number of iterations of the sub-region unit to be scheduled reaches a first number threshold, lowering the initial temperature, returning to the step of selecting the initial sub-region unit to be scheduled from the associated sub-region units of the first target region based on the cross-region bandwidth amount and the cross-region bandwidth line, and terminating the iteration until the temperature drops to the temperature threshold or the number of iterations reaches a second number threshold.

5. The method according to claim 2, characterized in that Also includes: Calculating a new cross-region bandwidth ratio of the first target region after the selected initial sub-region unit is moved out of the associated sub-region units of the first target region; If the new cross-region bandwidth ratio is lower than the current cross-region bandwidth ratio, determining that the selected initial sub-region unit meets the allocation condition; If the cross-region bandwidth ratio increases relative to the current cross-region bandwidth ratio and is greater than a bandwidth ratio threshold, determining with a predetermined probability that the selected initial sub-region unit meets the allocation condition; If the cross-region bandwidth ratio increases relative to the current cross-region bandwidth ratio and is less than or equal to the bandwidth ratio threshold, it is determined that the selected initial sub-region unit meets the allocation condition.

6. The method according to claim 1, characterized in that The step of performing gradient adjustment on the second target area and an area associated with the second target area to obtain an updated gradient includes: For each area in the second target area and the associated area of ​​the second target area, obtaining a bandwidth entropy threshold and a current gradient of the area; Determining a current gradient adjustment coefficient for each region based on the bandwidth entropy threshold and the bandwidth entropy of each region; The current gradient of each region is adjusted according to the gradient adjustment coefficient of each region to obtain an updated gradient of each region.

7. A cross-region bandwidth allocation device, characterized in that: The device comprises: A data acquisition module, used to obtain the cross-region bandwidth ratio of multiple areas to be processed; an allocation module configured to, if a first target area having a cross-area bandwidth ratio greater than a corresponding bandwidth ratio threshold exists in each of the to-be-processed areas, reallocate associated sub-area units of the first target area within each of the to-be-processed areas to obtain a plurality of new areas; the associated sub-area units of the first target area include sub-area units within the first target area and sub-area units within other to-be-processed areas; and the reallocation is to adjust bandwidth resource allocation of the sub-area units; The data acquisition module is further configured to acquire bandwidth entropy of each new area, and determine a second target area having a bandwidth entropy less than a bandwidth entropy threshold from each new area; a data adjustment module, configured to perform gradient adjustment on the second target area and an associated area of ​​the second target area to obtain an updated gradient; the associated area of ​​the second target area represents an area belonging to the same macro region as the second target area; A scheme determining module is configured to determine a bandwidth allocation scheme for the second target area and an area associated with the second target area according to the updated gradient.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images