Bandwidth planning method and device based on edge calculation, equipment and medium

Abstract

The invention relates to the technical field of Internet, and discloses a bandwidth planning method and device based on edge computing, equipment and a medium, and the method comprises the steps: determining cost earnings corresponding to a plurality of expected total settlement bandwidths in a search mode, and determining an optimal expected total settlement bandwidth corresponding to the optimal cost earnings; and allocating the optimal expected settlement bandwidth of each charging unit corresponding to the optimal expected total settlement bandwidth to the corresponding charging unit, and indicating the charging unit to provide corresponding bandwidth resources according to the optimal expected settlement bandwidth. According to the method, the optimal expected total settlement bandwidth is searched and positioned in a search mode, and then the corresponding expected settlement bandwidth is allocated to each charging unit based on the optimal expected total settlement bandwidth, so that bandwidth cost optimization is realized; according to the invention, an objective function does not need to be constructed and optimized, the solving mode is simple, and rapid and accurate bandwidth cost optimization can be realized.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a bandwidth planning method, apparatus, device, and medium based on edge computing. Background Art

[0002] Edge computing is a computing model that moves data processing, storage, and application services from centralized cloud or data centers to the "edge" of the network. Deploying multiple server nodes at different locations within the network can provide users with the edge computing services they need and redirect user requests to the node closest to them, enabling rapid responses and accelerating content delivery.

[0003] The use of related business services requires billing of the business bandwidth of each server node. In order to avoid excessive costs, bandwidth cost optimization is generally required. Summary of the Invention

[0004] In view of this, the present disclosure provides a bandwidth planning method, apparatus, device and medium based on edge computing to achieve bandwidth cost optimization.

[0005] In a first aspect, the present disclosure provides a bandwidth planning method based on edge computing, which is applied to an edge server, and the method includes:

[0006] Determine the cost-benefit corresponding to multiple expected total settlement bandwidths by searching, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit;

[0007] Allocating the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instructing the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth;

[0008] The process of determining the cost-benefit corresponding to the expected total settlement bandwidth includes:

[0009] For the expected total settlement bandwidth for settling bandwidth fees, the expected settlement bandwidth of each billing unit is determined based on the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth;

[0010] According to the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined according to the bandwidth simulated and allocated to each billing unit;

[0011] The cost benefit corresponding to the expected total settlement bandwidth is determined according to the sum of the simulated settlement bandwidths of the respective billing units.

[0012] In a second aspect, the present disclosure provides a bandwidth planning device based on edge computing, which is applied to an edge server, and the device includes:

[0013] A search module is used to determine the cost benefits corresponding to multiple expected total settlement bandwidths by searching, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost benefit;

[0014] A processing module, configured to allocate the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instruct the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth;

[0015] The process of the search module determining the cost-benefit corresponding to the expected total settlement bandwidth includes:

[0016] For the expected total settlement bandwidth for settling bandwidth fees, the expected settlement bandwidth of each billing unit is determined based on the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth;

[0017] According to the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined according to the bandwidth simulated and allocated to each billing unit;

[0018] The cost benefit corresponding to the expected total settlement bandwidth is determined according to the sum of the simulated settlement bandwidths of the respective billing units.

[0019] In a third aspect, the present disclosure provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions stored in the memory, and the processor executing the edge computing-based bandwidth planning method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0020] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the edge computing-based bandwidth planning method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the edge computing-based bandwidth planning method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0022] Based on given service bandwidth data, the present disclosure can calculate the cost-benefit of the corresponding expected total settlement bandwidth. This allows a search approach to locate the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit. Based on this optimal expected total settlement bandwidth, each billing unit is allocated a corresponding expected settlement bandwidth. The bandwidth resources of each billing unit are then scheduled according to this expected settlement bandwidth, thereby achieving bandwidth cost optimization. Determining the optimal expected total settlement bandwidth through a search approach eliminates the need to construct and optimize an objective function, resulting in a simple solution and facilitating rapid and accurate bandwidth cost optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a schematic diagram of an interaction between an intermediary supplier, a network operator, and a user according to an embodiment of the present disclosure;

[0025] Figure 2 1 is a flow chart of a bandwidth planning method based on edge computing according to an embodiment of the present disclosure;

[0026] Figure 3 1 is a flow chart of another bandwidth planning method based on edge computing according to an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of the relationship between bandwidth and multiplexing rate according to an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of a process for determining an optimal expected total settlement bandwidth according to an embodiment of the present disclosure;

[0029] Figure 6 is a structural block diagram of a bandwidth planning device based on edge computing according to an embodiment of the present disclosure;

[0030] Figure 7 Schematic diagram of the hardware structure of the computer device according to the embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present disclosure.

[0032] Edge computing technology can move data processing, storage, and application services from centralized cloud or data centers to the "edge" of the network. Server nodes deployed in a CDN (Content Delivery Network) can function as edge nodes with edge computing capabilities. These edge nodes can complete storage and computing tasks without transmitting data back to the cloud, reducing reliance on the cloud and facilitating local decision-making.

[0033] Taking CDN applications as an example, an intermediary provider, such as a CDN provider, typically purchases bandwidth resources from network operators and provides these bandwidth resources to relevant edge nodes, enabling the edge nodes to provide the services required by users. For example, if a service requires 10Tbps (1Tb per second) of bandwidth resources and is provided by five edge nodes, each edge node can be evenly allocated 2Tbps of bandwidth, or the bandwidth can be allocated based on the actual needs of each edge node.

[0034] Figure 1 This diagram illustrates the interaction between intermediary providers, network operators, and users. When users use bandwidth resources provided by intermediary providers, the intermediary providers, when providing edge computing capabilities, can collect and bill each user's bandwidth usage. For example, each of the intermediary provider's computer rooms can serve as an edge node. This way, the intermediary provider earns revenue after deducting the cost of purchasing bandwidth resources from the network operator from the fees collected from users.

[0035] In addition, for users who provide services, they can also access multiple intermediate suppliers, and multiple intermediate suppliers provide the services required by users. Users need to pay bandwidth fees to each intermediate supplier; for example, Figure 1 In the example, user B and user D use the same service. By optimizing usage strategies, users' bandwidth costs can be minimized.

[0036] Currently, CDN billing methods mainly include:

[0037] (1) 95 Billing: The calculated value of 95 is used as the billing value (also called billing bandwidth or settlement bandwidth), and is multiplied by the number of valid billing points in the billing period to charge fees. For example, if the billing period is one month (30 days), the bandwidth is counted every 5 minutes within the month, resulting in 8640 bandwidth points. After sorting the bandwidth of these time points in descending order, the first 5% of the bandwidth, approximately 432 bandwidth points, are ignored, and the 433rd bandwidth point is used as the billing value.

[0038] (2) Traffic billing: Fees are charged directly based on the total amount of traffic.

[0039] (3) Daily Peak Monthly Average Billing: The average of the daily peak values ​​is taken as the billing value and multiplied by the number of valid billing points in the billing period to charge the fee. For example, if the billing period is one month (30 days), the bandwidth peak value can be determined for each day and the average of the 30 bandwidth peak values ​​can be used as the billing value.

[0040] In the 95% billing method, the first 5% of bandwidth is not billed, meaning it has free time. Assuming a monthly billing cycle, as described above, the free time corresponding to 432 bandwidth units is 432 x 5 minutes, or approximately 36 hours. By properly utilizing this free time, bandwidth costs can be optimized, effectively reducing them and achieving optimal returns.

[0041] The optimal benefit of bandwidth cost optimization refers to the best actual benefit value that can be obtained based on a given service bandwidth waveform under specified configurations and constraints.

[0042] Currently, bandwidth cost optimization typically involves establishing an objective function. This involves expressing the 95% billing method numerically, then combining it with price calculations to construct a mathematical expression (i.e., the objective function) for theoretical bandwidth cost optimization. This approach is theoretically feasible, but due to the nonlinear nature of the 95% billing method, the resulting numerical optimization problem is NP-Hard (Nondeterministic Polynomially) and is typically very difficult to solve. Some solutions use linear relaxation combined with a well-defined random round-robin approach, which typically takes a long time to solve.

[0043] In addition, this way of establishing the objective function generally requires the actual total bandwidth sequence D = {d1, d2, .., d T However, in reality, it is impossible to obtain the service bandwidth of the entire month. That is, in a billing cycle, at a certain time t, there may only be a sequence D = {d1, d2, ..., d t,0,0,…}. This solution is an ideal solution in theory, but has many limitations in practical application.

[0044] In the embodiment of the present disclosure, multiple billing units are divided, and by pre-setting a suitable settlement bandwidth for each billing unit, each billing unit can make a decision based on the settlement bandwidth to determine whether to use the free time, thereby achieving bandwidth cost optimization.

[0045] The billing unit is a unit that can independently perform bandwidth billing physically or logically. Generally, a 95 account corresponds to a group of domain names or a contract, which can be considered as a category, managing one or a group of resources, and thus serving as a billing unit. Specifically, the billing unit can be:

[0046] (1) A 95-billage computer room node, which calculates the billing value according to the billing rules and the node bandwidth or traffic during the billing cycle.

[0047] (2) A 95-rate BGP (Border Gateway Protocol) link channel, which calculates the billing value of the channel according to the billing rules and the channel bandwidth or traffic during the billing cycle; for example, the channel for transmitting data from the dedicated line of computer room 1 to computer room 2, etc.

[0048] (3) For a commercial CDN contract item, the total bandwidth of the domain names belonging to the contract item is calculated according to the billing rules and bandwidth or traffic during the billing period to calculate the billing value.

[0049] Compared with no scheduling, staggered scheduling of multiple billing units can improve the utilization of bandwidth resources and thus optimize bandwidth costs.

[0050] According to an embodiment of the present disclosure, an embodiment of a bandwidth planning method based on edge computing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, a bandwidth planning method based on edge computing is provided, which can be applied to processing devices on the intermediate provider or user side, such as edge servers; Figure 2 is a flow chart of a bandwidth planning method based on edge computing according to an embodiment of the present disclosure, such as Figure 2 As shown, the process includes the following steps.

[0052] Step S201 : determining the cost-benefit corresponding to a plurality of expected total settlement bandwidths by searching, and determining the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit.

[0053] In this embodiment, the content distribution network includes multiple billing units, which can be edge nodes in the network, such as the 95 billing data center node mentioned above, and will not be described in detail. These billing units correspond to the total settlement bandwidth. In this embodiment, bandwidth cost optimization is achieved by adjusting the total settlement bandwidth.

[0054] Specifically, the edge server sets the total settlement bandwidth that these billing units expect to achieve, that is, the expected total settlement bandwidth; as the name suggests, the expected total settlement bandwidth is an expected value. For the expected total settlement bandwidth, its corresponding cost-benefit can be determined. The higher the cost-benefit, the better the expected total settlement bandwidth. For the multiple expected total settlement bandwidths set, the corresponding cost-benefit can be determined respectively, and then the optimal cost-benefit can be searched to determine the optimal expected total settlement bandwidth, that is, the expected total settlement bandwidth corresponding to the optimal cost-benefit. It can be understood that the cost-benefit in this embodiment is specifically the bandwidth cost-benefit.

[0055] The process of determining the cost-benefit corresponding to the expected total settlement bandwidth in the above step S201 may specifically include steps S2011 to S2013.

[0056] Step S2011 : For the expected total settlement bandwidth used for settling bandwidth charges, the expected settlement bandwidth of each billing unit is determined according to the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth.

[0057] In this embodiment, for a certain expected total settlement bandwidth, the settlement bandwidth of each billing unit needs to be determined based on the expected total settlement bandwidth. Since the settlement bandwidth of the billing unit determined at this time is also an expected value, it is called the expected settlement bandwidth.

[0058] The sum of the expected settlement bandwidths of the various billing units is consistent with the expected total settlement bandwidth. For example, the sum of the expected settlement bandwidths of the various billing units is equal to the expected total settlement bandwidth; or the sum of the expected settlement bandwidths of the various billing units is close to the expected total settlement bandwidth, for example, the difference between the sum and the expected total settlement bandwidth is within a preset range.

[0059] Step S2012: Based on the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined based on the bandwidth simulated and allocated to each billing unit.

[0060] In this embodiment, the edge server can obtain service bandwidth data locally. This service bandwidth data includes bandwidth data for each service at each point in time. The sum of the bandwidth data for all services at a given point in time is the total service data at that point in time. Based on this service bandwidth data, a simulation calculation can be performed to simulate the bandwidth waveform of each billing unit, thereby determining the actual settlement bandwidth of each billing unit. In this embodiment, this is referred to as simulated settlement bandwidth.

[0061] Specifically, as shown above, each billing unit currently has a corresponding expected settlement bandwidth, so that when using the bandwidth resources of the billing unit, the bandwidth value used can be determined based on the expected settlement bandwidth. For example, for a billing unit, if the bandwidth resources it uses currently reaches the expected settlement bandwidth, it can be determined whether a peak load (i.e., a peak load of bandwidth) is required at this time. If a peak load is required, the bandwidth resources used by the billing unit can be set to the corresponding bandwidth peak to maximize the use of the free time; if a peak load is not required, the bandwidth resources used by the billing unit can be kept within the expected settlement bandwidth to maximize the use of the bandwidth during the paid time period.

[0062] Whether a peak rush is required may be determined based on the currently used scheduling policy, which is not limited in this embodiment.

[0063] By simulating the bandwidth allocation of each billing unit, the simulated bandwidth waveform for each billing unit can be determined, and thus the simulated settlement bandwidth for that billing unit can be determined. For example, the simulated bandwidth waveform includes the simulated bandwidth values ​​at each time point within the billing cycle. The simulated bandwidth value corresponding to the 5%th time point, arranged from highest to lowest, is used as the corresponding simulated settlement bandwidth. When settling bandwidth charges for that billing unit, billing is performed based on this simulated settlement bandwidth.

[0064] In this embodiment, a real CDN optimization system can be simulated based on a CDN bandwidth allocation simulator or a corresponding simulation algorithm. By observing the corresponding business data, decisions can be made and corresponding strategies (such as whether to rush the peak) can be executed, thereby achieving fast and long-term offline bandwidth simulation. When the data is complete, feedback can be obtained quickly, and then the nonlinear 95 billing optimization problem can be analyzed (the 95 billing method is nonlinear).

[0065] For example, by using a CDN bandwidth allocation simulator for planning and simulation, the bandwidth cost simulation within a billing cycle (e.g., one month) can be completed, and the waveform bandwidth of each billing unit within the billing cycle can be ultimately produced, and the simulated settlement bandwidth of each billing unit can be calculated based on this.

[0066] Step S2013: Determine the cost-benefit corresponding to the expected total settlement bandwidth based on the sum of the simulated settlement bandwidths of the various billing units.

[0067] In this embodiment, the simulated settlement bandwidth is a real value determined through simulation, compared to the expected settlement bandwidth. Therefore, the lower the sum of the simulated settlement bandwidths for each billing unit, the lower the bandwidth cost determined based on the simulation, the higher the benefit, and the better the cost-benefit ratio. Therefore, the cost-benefit ratio corresponding to the expected total settlement bandwidth can be determined based on the sum of the simulated settlement bandwidths for each billing unit. Furthermore, the lower the sum of the simulated settlement bandwidths for each billing unit, the higher the cost-benefit ratio corresponding to the expected total settlement bandwidth.

[0068] By searching for the cost-benefit ratios corresponding to multiple desired total settlement bandwidths, the optimal cost-benefit ratio (i.e., the highest cost-benefit ratio) can be determined, thereby determining the optimal desired total settlement bandwidth. When searching for the cost-benefit ratios corresponding to multiple desired total settlement bandwidths, the edge server can perform all of the search work itself, or it can distribute some of the search work to other edge nodes, improving edge computing effectiveness.

[0069] Optionally, the cost-benefit corresponding to the expected total settlement bandwidth satisfies:

[0070]

[0071] Among them, Pct95 sum =ΣPct95 i ; r represents the cost-benefit corresponding to the expected total settlement bandwidth, Pct95 total Indicates the total settlement bandwidth corresponding to the service bandwidth data, Pct95 i represents the simulated settlement bandwidth of the i-th billing unit, Pct95 sum Indicates the sum of the simulated settlement bandwidth of each billing unit.

[0072] In this embodiment, for a given service bandwidth data, the total settlement bandwidth Pct95 total (i.e. 95 settlement bandwidth value) is also the settlement bandwidth corresponding to the total traffic of each billing unit, which is the expenditure when bandwidth cost optimization is not performed. By performing bandwidth cost optimization, if the expected settlement bandwidth of each billing unit is Pct95 i , then the sum of these expected settlement bandwidths is Pct95 sum =ΣPct95 i It can be understood that the appropriate expected settlement bandwidth Pct95 i , can reduce the expected settlement bandwidth and Pct95 sum .

[0073] Compared with the case without bandwidth cost optimization, the bandwidth resource reuse rate r after bandwidth cost optimization can be expressed as the above formula (1), that is, The reuse rate r can represent the cost-benefit corresponding to the expected total settlement bandwidth. A larger r indicates a higher cost-benefit corresponding to the expected total settlement bandwidth, that is, a better expected total settlement bandwidth.

[0074] Step S202 : Allocate the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instruct the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth.

[0075] In this embodiment, after determining the optimal expected total settlement bandwidth, the optimal expected settlement bandwidth for each billing unit can be determined based on the optimal expected total settlement bandwidth, and then the corresponding optimal expected settlement bandwidth can be allocated to each billing unit. The optimal expected settlement bandwidth for each billing unit can be determined based on step S2011 above, i.e., the sum of the optimal expected settlement bandwidths of each billing unit is consistent with the optimal expected total settlement bandwidth.

[0076] After allocating the corresponding optimal expected settlement bandwidth to each billing unit, each billing unit can provide corresponding bandwidth resources according to the corresponding optimal expected settlement bandwidth, and can perform edge computing to achieve cost optimization of settlement bandwidth.

[0077] For example, the optimal expected settlement bandwidth for a billing unit is 1 Tbps (1 Tbps per second), which is the predicted 95% billing settlement bandwidth. When the actual bandwidth of the billing unit reaches 1 Tbps, a decision can be made as to whether the billing unit can meet peak usage. If so, the bandwidth of the billing unit can be set to the maximum value, such as 1.2 Tbps or 1.3 Tbps, allowing the billing unit to fully utilize the 5% free time and optimize bandwidth costs.

[0078] The edge computing-based bandwidth planning method provided in this embodiment can calculate the cost-benefit of the corresponding expected total settlement bandwidth based on given service bandwidth data. This allows a search method to locate the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit. Based on this optimal expected total settlement bandwidth, each billing unit is allocated a corresponding expected settlement bandwidth. The bandwidth resources of each billing unit are scheduled according to this expected settlement bandwidth, thereby achieving bandwidth cost optimization. Determining the optimal expected total settlement bandwidth through a search method eliminates the need to construct and optimize an objective function, resulting in a simple solution method that facilitates rapid and accurate bandwidth cost optimization.

[0079] In this embodiment, a bandwidth planning method based on edge computing is provided, which can be applied to processing devices on the intermediate provider or user side, such as edge servers; Figure 3 is a flow chart of a bandwidth planning method based on edge computing according to an embodiment of the present disclosure, such as Figure 3As shown, the process includes the following steps.

[0080] Step S301 : determining the cost-benefit corresponding to a plurality of expected total settlement bandwidths by searching, and determining the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit.

[0081] Specifically, step S301 of "determining the cost-benefit corresponding to multiple expected total settlement bandwidths by searching, and determining the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit" is performed iteratively to search for the optimal expected total settlement bandwidth. The process specifically includes:

[0082] Iterate multiple rounds of settlement bandwidth search processing until the end search condition is met, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit.

[0083] Among them, Figure 3 As shown, for the current round of settlement bandwidth search processing, the process specifically includes the following steps S3011 to S3015.

[0084] Step S3011: For the expected total settlement bandwidth of the current round, determine the current cost-benefit corresponding to the expected total settlement bandwidth of the current round.

[0085] The process of determining the current cost-benefit can be found in Figure 2 In the embodiment shown in step S2011 to step S2013, specifically, determining the current cost-benefit corresponding to the expected total settlement bandwidth of the current round may include:

[0086] For the expected total settlement bandwidth of the current round, the expected settlement bandwidth of each billing unit in the current round is determined according to the expected total settlement bandwidth of the current round; the sum of the expected settlement bandwidths of each billing unit in the current round is consistent with the expected total settlement bandwidth of the current round.

[0087] According to the given service bandwidth data and the expected settlement bandwidth of each billing unit in the current round, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit in the current round is determined according to the bandwidth simulated and allocated to each billing unit.

[0088] The cost-benefit corresponding to the expected total settlement bandwidth of the current round, ie, the current cost-benefit, is determined based on the sum of the simulated settlement bandwidths of the current round for each billing unit.

[0089] In this embodiment, for each round of settlement bandwidth search processing, the corresponding expected total settlement bandwidth is different, and each expected total settlement bandwidth can be determined according to the above process.

[0090] In some optional implementations, each billing unit is provided with a settlement configuration, which includes a maximum settlement bandwidth and a minimum settlement bandwidth; as the name implies, the maximum settlement bandwidth is the maximum value of the settlement bandwidth allowed by the billing unit, and the minimum settlement bandwidth is the minimum value of the settlement bandwidth allowed by the billing unit.

[0091] The above step of "determining the expected settlement bandwidth of each billing unit according to the expected total settlement bandwidth" specifically includes step A1.

[0092] Step A1: Under the constraints of the settlement configuration of each billing unit, minimize the difference between the sum of the expected settlement bandwidths of each billing unit and the expected total settlement bandwidth to determine the expected settlement bandwidth of each billing unit.

[0093] In this embodiment, the expected total settlement bandwidth of the current round is X, and the expected settlement bandwidth of each billing unit is x i , and the maximum settlement bandwidth and minimum settlement bandwidth of the i-th billing unit are x i,max , x i,min , then under the constraints of the settlement configuration of each billing unit, the expected settlement bandwidth of each billing unit needs to be between the corresponding maximum settlement bandwidth and the minimum settlement bandwidth, that is, x i,min ≤x i ≤x i,max Under this constraint, by minimizing the difference between the sum of the expected settlement bandwidth of each billing unit and the expected total settlement bandwidth, that is, minimizing |X-Σx i |, so that the expected total settlement bandwidth is the sum of X and the expected settlement bandwidth of each billing unit ∑x i As close as possible, for example, the two are equal, so that the expected settlement bandwidth of each billing unit can be determined.

[0094] For example, the settlement configuration of a billing unit is shown in Table 1 below, where the unit of each bandwidth is Gbps; the minimum settlement bandwidth is 800 Gbps, and the maximum settlement bandwidth is 1200 Gbps. Therefore, the expected settlement bandwidth set for this billing unit needs to be between 800 Gbps and 1200 Gbps.

[0095] Table 1

[0096]

[0097]

[0098] If the billing unit uses the 95% billing method, its expected settlement bandwidth can be determined using the above method. If the billing unit uses the flow-based billing method or the daily peak / monthly average billing method, these two billing methods do not require expected settlement and can be ignored. The various settlement bandwidths in this embodiment mainly represent the settlement bandwidth values ​​for the 95% billing method.

[0099] In this embodiment, each billing unit is provided with a resource constraint configuration, namely the above-mentioned settlement configuration. Under the constraints of the settlement configuration, the expected settlement bandwidth of each billing unit is reasonably allocated. While achieving bandwidth cost optimization, it is ensured that the settlement bandwidth set for the billing unit meets the configuration requirements of the billing unit.

[0100] Optionally, the above step A1 "minimizing the difference between the sum of the expected settlement bandwidths of each billing unit and the expected total settlement bandwidth under the constraints of the settlement configuration of each billing unit to determine the expected settlement bandwidth of each billing unit" may include steps A11 to A13.

[0101] Step A11: Determine the maximum total settlement bandwidth and the minimum total settlement bandwidth; the maximum total settlement bandwidth is the sum of the maximum settlement bandwidths of each billing unit, and the minimum total settlement bandwidth is the sum of the minimum settlement bandwidths of each billing unit.

[0102] Step A12: Determine whether the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth.

[0103] In step A13, when the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth, the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit is used as the expected settlement bandwidth of the billing unit; the sum of the expected settlement bandwidths of each billing unit is the same as the expected total settlement bandwidth.

[0104] In this embodiment, based on the maximum settlement bandwidth x of each billing unit i,max , the maximum total settlement bandwidth X can be determined max , that is, X max =∑x i，max Similarly, based on the minimum settlement bandwidth x of each billing unit i,min , the minimum total settlement bandwidth X can be determined min , that is, X min =∑x i，min .

[0105] When executing the current round of settlement bandwidth search processing, if the expected total settlement bandwidth X of the current round is within the maximum total settlement bandwidth X max With the minimum total settlement bandwidth X min Between, that is, X min ≤X≤X max, it means that by reasonably setting the expected settlement bandwidth x of each billing unit i , which can make the sum of the expected settlement bandwidth of each billing unit Σx i , which is the same as the expected total settlement bandwidth X, that is, X = ∑x i .

[0106] On the contrary, if the expected total settlement bandwidth X of the current round is not within the maximum total settlement bandwidth X max With the minimum total settlement bandwidth X min Between, that is, X <X min , or, X>X max At this time, due to the constraints of the billing unit settlement configuration, it is impossible to perfectly configure the expected settlement bandwidth x of each billing unit based on the expected total settlement bandwidth x of the current round. i At this time, you can redefine the expected total settlement bandwidth X, or change the expected settlement bandwidth x of each billing unit to i Set as the corresponding maximum settlement bandwidth x i,max or minimum settlement bandwidth x i,min . Specifically, if <X min , then the expected settlement bandwidth of each billing unit is x i is the corresponding minimum settlement bandwidth x i,min ; If X>X max , then the expected settlement bandwidth of each billing unit is x i is the corresponding maximum settlement bandwidth x i,max .

[0107] Optionally, the settlement configuration also includes an initial settlement bandwidth. This initial settlement bandwidth refers to the settlement bandwidth initially set for the billing unit. For example, if bandwidth cost optimization is not performed, the settlement bandwidth of the billing unit can be set to this initial settlement bandwidth. It is understood that this initial settlement bandwidth is also between the maximum settlement bandwidth and the minimum settlement bandwidth. As shown in Table 1 above, the initial settlement bandwidth is 1000 Gbps.

[0108] The above-mentioned step A13 of "using the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit as the expected settlement bandwidth of the billing unit" may specifically include steps A131 to A136.

[0109] Step A131: Determine the settlement bandwidth ratio of each billing unit according to the initial settlement bandwidth of each billing unit.

[0110] In this embodiment, if the initial settlement bandwidth of each billing unit is x i,0 , then the sum of the initial settlement bandwidth of the billing unit is ∑x i,0 , then the initial settlement bandwidth x of each billing unit i,0The ratio between the initial settlement bandwidth and the initial settlement bandwidth is used as the settlement bandwidth ratio c of each billing unit. i , that is, the settlement bandwidth ratio c i for:

[0111] Step A132 : dividing the expected total settlement bandwidth into the pending settlement bandwidths corresponding to the respective billing units according to the settlement bandwidth ratios of the respective billing units.

[0112] Step A133: For the first billing unit, the pending settlement bandwidth of the first billing unit is used as the expected settlement bandwidth of the first billing unit; the pending settlement bandwidth of the first billing unit is between the maximum settlement bandwidth and the minimum settlement bandwidth of the first billing unit.

[0113] Step A134: For the second billing unit, the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit, whichever is closer to the pending settlement bandwidth of the second billing unit, is used as the expected settlement bandwidth of the second billing unit, and the bandwidth difference between the pending settlement bandwidth of the second billing unit and the expected settlement bandwidth of the second billing unit is recorded; the pending settlement bandwidth of the second billing unit is not between the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit.

[0114] For each billing unit, multiply the expected total settlement bandwidth X by the corresponding settlement bandwidth ratio c i , you can get the pending settlement bandwidth of the billing unit, that is, c i ×X.

[0115] The pending settlement bandwidth determined by this method may not be between the corresponding maximum settlement bandwidth and the minimum settlement bandwidth. For the convenience of description, for a certain billing unit, if its pending settlement bandwidth c i ×X is located at the highest settlement bandwidth x i,max and minimum settlement bandwidth x i,min If the bandwidth c of the billing unit is between i ×X is not located at the highest settlement bandwidth x i,max and minimum settlement bandwidth x i,min If the billing unit is between , the billing unit is called the second billing unit.

[0116] For the first billing unit, directly set the corresponding pending settlement bandwidth c i ×X is used as the expected settlement bandwidth for the first billing unit. For the second billing unit, since the pending settlement bandwidth does not meet the constraints of the settlement configuration, the highest or lowest settlement bandwidth of the second billing unit, whichever is closer to the pending settlement bandwidth of the second billing unit, is used as the expected settlement bandwidth for the second billing unit.

[0117] Moreover, for the second billing unit, its pending settlement bandwidth is different from the expected settlement bandwidth, and there is a certain difference between the two, namely, the bandwidth difference. This embodiment records the bandwidth difference of each second billing unit to facilitate subsequent filling.

[0118] For example, if the pending settlement bandwidth c of the second billing unit i ×X is less than the minimum settlement bandwidth x i,min , then the minimum settlement bandwidth x i,min As the expected settlement bandwidth of the second billing unit, the bandwidth difference is c i ×Xx i,min , which is a positive value. If the pending settlement bandwidth c of the second billing unit i ×X is greater than the maximum settlement bandwidth x i,max , then the maximum settlement bandwidth x i,max As the expected settlement bandwidth of the second billing unit, the bandwidth difference is c i ×Xx i,max , which is a negative value.

[0119] Step A135: Determine the total bandwidth difference; the total bandwidth difference is the sum of the bandwidth differences of each second billing unit.

[0120] Step A136: Under the constraints of the settlement configuration of the first billing unit, the total bandwidth difference is allocated to at least part of the first billing unit, and the expected settlement bandwidth of at least part of the first billing unit is updated.

[0121] In this embodiment, the bandwidth differences of each second billing unit are summed to calculate the total bandwidth difference, which is the bandwidth value that needs to be filled. Since the current expected settlement bandwidth of the first billing unit is between the lowest settlement bandwidth and the highest settlement bandwidth, the expected settlement bandwidth of these first billing units is updated by allocating the total bandwidth difference to some or all of the first billing units, thereby filling the total bandwidth difference. The sum of the expected settlement bandwidths of each billing unit (including the first billing unit and the second billing unit) is finally equal to the expected total settlement bandwidth X. At this time, the bandwidth values ​​corresponding to the total bandwidth difference are all allocated to the corresponding first billing units, and the total bandwidth difference is zero.

[0122] Optionally, the settlement configuration further includes: priority; as shown in Table 1 above, the priority of the billing unit is 1; for example, the smaller the priority value, the higher the priority.

[0123] In addition, the above-mentioned step A136 "under the constraints of the settlement configuration of the first billing unit, allocating the total bandwidth difference to at least part of the first billing units, and updating the expected settlement bandwidth of at least part of the first billing units" includes: updating the expected settlement bandwidth of the first billing units in sequence according to the priority of each first billing unit from high to low until the total bandwidth difference is allocated.

[0124] The above step of “updating the expected settlement bandwidth of the first billing unit” specifically includes:

[0125] Allocate part or all of the total bandwidth difference to the first billing unit to update the expected settlement bandwidth of the first billing unit until the expected settlement bandwidth of the first billing unit is the highest settlement bandwidth or the lowest settlement bandwidth of the first billing unit, or all of the total bandwidth difference is allocated to the first billing unit.

[0126] In this embodiment, when updating the expected settlement bandwidth of the first billing unit, the first billing unit with a high priority is updated first. In addition, the updated expected settlement bandwidth cannot exceed the corresponding maximum settlement bandwidth or minimum settlement bandwidth.

[0127] Specifically, for a first billing unit, if the expected settlement bandwidth of the first billing unit needs to be updated based on the total bandwidth difference, let the current expected settlement bandwidth of the first billing unit be x i (i.e. based on the expected settlement bandwidth determined in step A133 above), if the total bandwidth difference ΔX is a positive value, the maximum settlement bandwidth x of the first billing unit is determined. i,max With the current expected settlement bandwidth x i The difference between i,max -x i ) is less than the total bandwidth difference ΔX, if less than, then the expected settlement bandwidth of the first billing unit is updated to its maximum settlement bandwidth x i,max , and continue to update other first billing units; if it is not less than, then based on the current expected settlement bandwidth of the first billing unit, increase the total bandwidth difference ΔX, that is, the updated expected settlement bandwidth is x i +ΔX and stop updating.

[0128] Similarly, if the total bandwidth difference ΔX is a negative value, the current expected settlement bandwidth x of the first billing unit is determined. i With minimum settlement bandwidth x i,min The difference between i -x i,min ) is less than the absolute value of the total bandwidth difference |ΔX|, if less than, then the expected settlement bandwidth of the first billing unit is updated to its minimum settlement bandwidth x i,min, and continue to update other first billing units; if it is not less than, then based on the current expected settlement bandwidth of the first billing unit, increase the total bandwidth difference ΔX, that is, the updated expected settlement bandwidth is x i +ΔX(i.e. x i -|ΔX|) and stop updating.

[0129] When determining the expected settlement bandwidth x for each billing unit i Finally, bandwidth simulation is performed based on this to finally determine the current cost-benefit corresponding to the expected total settlement bandwidth of the current round.

[0130] Step S3012: If the current cost benefit is greater than the currently recorded best cost benefit, the currently recorded best cost benefit is updated as the current cost benefit, and the currently recorded best expected total settlement bandwidth is updated as the expected total settlement bandwidth of the current round.

[0131] Step S3013: When the current cost benefit is less than the currently recorded best cost benefit, the currently recorded best cost benefit and the best expected total settlement bandwidth are kept unchanged.

[0132] In this embodiment, the best cost-benefit and the corresponding best expected total settlement bandwidth are recorded in real time. For example, the best cost-benefit and the best expected total settlement bandwidth are recorded based on two fields. After determining the current cost-benefit, it can be determined whether the current cost-benefit is greater than the currently recorded best cost-benefit. If the current cost-benefit is greater than the currently recorded best cost-benefit, it indicates that a better expected total settlement bandwidth has been found, and an update is required. Specifically, the currently recorded best cost-benefit is updated to the current cost-benefit, and the currently recorded best expected total settlement bandwidth is updated to the expected total settlement bandwidth for the current round.

[0133] On the contrary, if the current cost-benefit is less than the currently recorded best cost-benefit, it means that the previously determined expected total settlement bandwidth is better, or that the expected total settlement bandwidth of the current round is not optimal. Therefore, no additional processing is required at this time, and the currently recorded best cost-benefit and best expected total settlement bandwidth can be kept unchanged.

[0134] Step S3014: determine whether the current cost-benefit meets the search end condition.

[0135] Step S3015: If the current cost-benefit does not satisfy the search termination condition, the expected total settlement bandwidth of the current round is reduced according to a preset step size to generate the expected total settlement bandwidth of the next round.

[0136] In this embodiment, a pre-set end search condition is set. If the end search condition is currently met, the search can be stopped. The optimal expected total settlement bandwidth recorded at this time is the final optimal expected total settlement bandwidth. Conversely, if the current cost-benefit does not meet the end search condition, the search needs to be continued. In this embodiment, the expected total settlement bandwidth is gradually updated by gradually decreasing it to determine the next round of expected total settlement bandwidth. This next round of expected total settlement bandwidth is used to perform the next round of settlement bandwidth search processing.

[0137] A certain step length, ie, a preset step length, is preset, and the expected total settlement bandwidth is gradually reduced according to the preset step length to achieve a search for each expected total settlement bandwidth.

[0138] In the process of realizing the invention disclosed herein, in order to understand the relationship between the set settlement bandwidth and the obtained benefits (cost-benefit), using real business bandwidth data, combined with the settlement configuration of the relevant manufacturer's billing unit, a simulation calculation can be performed to determine the reuse rate r corresponding to each expected settlement bandwidth, that is, the cost-benefit. The reuse rate r is calculated by the above formula (1). Among them, the relationship between bandwidth and reuse rate in a certain month (the billing cycle is one month) can be seen in Figure 4 shown.

[0139] Figure 4 The horizontal axis is the total bandwidth, and the vertical axis is the multiplexing rate r calculated based on the above formula (1). Figure 4 It can be seen that:

[0140] 1. Even if the total settlement bandwidth exceeds 95% of the total service bandwidth, no revenue will be generated because peak shaving cost optimization is essentially not implemented.

[0141] 2. When the total settlement bandwidth is below 95% of the total service bandwidth, the lower the total settlement bandwidth, the higher the profit. This is because the reuse space of bandwidth resources can support bandwidth cost optimization.

[0142] 3. When the total settlement bandwidth continues to be lower than the optimal settlement value point ( Figure 4 When the optimal settlement value point is 75.69T), the reuse space of bandwidth resources cannot support the bandwidth demand of services, and bandwidth resources will be overused, resulting in a rapid decline in reuse rate.

[0143] 4. When the total settlement bandwidth is at a relatively low level, the revenue also stabilizes at a negative number. This is mainly due to excessive resource usage leading to serious waste (settlement is not stable when 95 billing items are overused, and bandwidth costs fluctuate significantly in a negative direction).

[0144] based on Figure 4As shown in the relationship, searching sequentially in descending order of the expected total settlement bandwidth can gradually lead to the maximum reuse rate, that is, the optimal cost-benefit ratio, and thus determine the corresponding optimal expected total settlement bandwidth. Optionally, the initial value of the expected total settlement bandwidth is the total settlement bandwidth corresponding to the service bandwidth data, meaning that the initial value of the total settlement bandwidth can be conveniently set based on the service bandwidth data.

[0145] For example, the total settlement bandwidth corresponding to the service bandwidth data is Pct95 as shown in the above formula (1): total , then the initial value of the expected total settlement bandwidth is set to Pct95 total , and then gradually reduce the expected total settlement bandwidth until the optimal expected total settlement bandwidth is found.

[0146] Also, based on Figure 4 For example, if the current cost benefit shows multiple (e.g., four) consecutive downward trends, or the current cost benefit becomes zero, then it can be determined that the current cost benefit meets the end search condition, which can be determined based on actual conditions.

[0147] Figure 5 A schematic diagram of a process for determining the optimal expected total settlement bandwidth is shown in FIG. Figure 5 As shown, first, given the service bandwidth data, settlement configuration, and scheduling strategy, the scheduling strategy is used to allocate bandwidth resources to each billing unit. First, it can be determined whether it is necessary to configure settlement bandwidth for the billing unit. If not, the process ends; if it is necessary, the appropriate expected total settlement bandwidth X can be set, and based on this, the expected settlement bandwidth x of each billing unit can be determined. i , then enter the simulation process, that is, simulate the bandwidth allocated to each billing unit based on the bandwidth allocation simulator. After the simulation is completed, the corresponding simulation data can be determined. The simulation data includes the bandwidth waveform of each billing unit (including bandwidth values ​​at multiple time points).

[0148] By statistically analyzing the simulated data for each billing unit, the simulated 95% billing value for each billing unit, i.e., the simulated settlement bandwidth, can be determined. Based on the simulated settlement bandwidth for each billing unit, it can be determined whether the currently recorded optimal expected total settlement bandwidth needs to be updated, thereby determining the settlement bandwidth search result. If the current end search criteria are not met, a new expected total settlement bandwidth X' is determined for the next round. The above process is repeated until the end search criteria are met. At this point, the optimal result, i.e., the optimal expected total settlement bandwidth, is output, and the subsequent step S302 is executed.

[0149] In this embodiment, searching is performed in descending order of the expected total settlement bandwidth, which is conducive to searching for the optimal expected total settlement bandwidth more quickly and accurately, and facilitates reasonable setting of the initial value of the expected total settlement bandwidth.

[0150] Optionally, to more accurately determine the optimal expected total settlement bandwidth, multiple levels of search steps are pre-set, arranged from largest to smallest. The search step size for each level can be determined based on the magnitude of the bandwidth. Generally, the search step sizes of adjacent levels differ by at least a factor of 10, and adjacent levels are not of the same magnitude.

[0151] For example, based on the bandwidth level, the three-level search step is defined, with the 95th value of the total service bandwidth as the benchmark, that is, Pct95 total As a benchmark, the corresponding proportion is used as the search step size. For example, 1% is the first-level search step size, 0.01% is the second-level search step size, 0.0001% is the third-level search step size, etc. The specific ratio can be determined based on actual needs.

[0152] The above-mentioned step S3015 of "reducing the expected total settlement bandwidth of the current round according to the preset step size to generate the expected total settlement bandwidth of the next round" includes step B1.

[0153] Step B1: reducing the expected total settlement bandwidth of the current round according to the current search step length to generate the expected total settlement bandwidth of the next round; the current search step length is the i-th search step length in the multi-level search step length;

[0154] Furthermore, the current round of settlement bandwidth search processing includes steps C1 to C3 below in addition to the above steps S3011 to S3015 .

[0155] Step C1, after determining whether the current cost-benefit meets the end search condition, if the current cost-benefit meets the end search condition, determine whether the current level search step is the last level search step.

[0156] In step C2, if the current search step is not the last search step, the range of the current search step before and after the currently recorded best expected total settlement bandwidth is used as the search range; the expected total settlement bandwidth for the next round is determined based on the upper limit of the search range, and the current search step is updated to the i+1th search step.

[0157] Step C3: When the current level search step is the last level search step, determine the optimal expected total settlement bandwidth corresponding to the optimal cost benefit.

[0158] In this embodiment, when executing the current round of settlement bandwidth search processing, a current-level search step size is provided. This is a pre-set search step size, specifically the i-th level search step size, such as a first-level search step size of 1%. If the current cost-benefit does not meet the search termination criteria, the expected total settlement bandwidth for the next round needs to be determined. This is determined based on the current-level search step size (i.e., the i-th level search step size). Specifically, the current-level search step size is subtracted from the current round's expected total settlement bandwidth to obtain the expected total settlement bandwidth for the next round, and the settlement bandwidth search processing for the next round can then be executed.

[0159] In addition, in order to be able to traverse all search steps, in addition to determining whether the current cost-benefit meets the end search condition, it is also necessary to determine whether the current level search step is the last level search step; in this case, the above-mentioned step of "iteratively executing multiple rounds of settlement bandwidth search processing until the end search condition is met, and determining the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit" may include: iteratively executing multiple rounds of settlement bandwidth search processing until the end search condition is met and the current level search step is the last level search step, at which time the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit is determined.

[0160] Specifically, when the current cost-benefit meets the search termination condition, it is further determined whether the current search step is the last search step. If the current search step is the last search step, no further search is required. As shown in step C3, the best expected total settlement bandwidth recorded at this time is the best expected total settlement bandwidth corresponding to the best cost-benefit.

[0161] On the contrary, if the current cost-benefit meets the end search condition, but the current level search step is not the last level search step, it is necessary to switch to the next level search step and search again.

[0162] Specifically, if the current search step size is not the last search step size, that is, the i-th search step size is not the last search step size, then the search range for the next search step size can be determined based on the currently recorded best expected total settlement bandwidth. The search range is defined as the range of the current search step size before and after the currently recorded best expected total settlement bandwidth. Specifically, the lower limit of the search range is the difference between the currently recorded best expected total settlement bandwidth and the current search step size (i.e., the i-th search step size), while the upper limit of the search range is the sum of the currently recorded best expected total settlement bandwidth and the current search step size (i.e., the i-th search step size).

[0163] For the search range, the expected total settlement bandwidth for the next round is determined based on the upper limit value of the search range, and the current level search step is updated to the i+1 level search step, so that the subsequent settlement bandwidth search process uses a smaller search step, thereby being able to more accurately determine the optimal expected total settlement bandwidth within a smaller range (i.e., the search range).

[0164] The upper limit of the search range can be directly used as the expected total settlement bandwidth for the next round; or the result of subtracting the i+1th level search step from the upper limit of the search range can be used as the expected total settlement bandwidth for the next round.

[0165] For example, if the best expected total settlement bandwidth of the current record is L, the current level search step (i.e., the i-th level search step) is s i , then the search range is [Ls i ,L+s i ), the upper limit is L+s i If the i+1th level search step is s i+1 , then L+s i -s i+1 Set it as the expected total settlement bandwidth for the next round. Repeat this process until the current cost-benefit meets the end search condition and the current level search step size is the last level search step size, and the iteration ends.

[0166] Step S302 : Allocate the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instruct the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth.

[0167] For details, please see Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0168] The edge computing-based bandwidth planning method provided in this embodiment uses a search method to locate the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit, and then allocates the corresponding expected settlement bandwidth to each billing unit based on the optimal expected total settlement bandwidth. This method does not require the construction and optimization of the objective function, and the solution is simple, which is conducive to achieving fast and accurate bandwidth cost optimization. Based on the relationship between the total settlement bandwidth and the reuse rate, the search is performed in descending order of the expected total settlement bandwidth, which is conducive to faster and more accurate search for the optimal expected total settlement bandwidth and facilitates the reasonable setting of the initial value of the expected total settlement bandwidth.

[0169] By setting multiple search steps and setting the steps in descending order, you can use smaller search steps to achieve precise searches based on the search range determined by the previous search step, thereby improving search efficiency while ensuring the accuracy of search results. Determining the expected settlement bandwidth for each billing unit within the constraints of the billing unit's settlement configuration can ensure the rationality of the expected settlement bandwidth; dividing the expected total settlement bandwidth according to the settlement bandwidth ratio of each billing unit, and then processing the two types of billing units separately, can make up for the total bandwidth difference and ensure that the sum of the expected settlement bandwidth of each billing unit is the same as the expected total settlement bandwidth.

[0170] In this embodiment, a bandwidth planning device based on edge computing is also provided. The device is used to implement the above-mentioned embodiments and preferred implementation methods. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0171] This embodiment provides a bandwidth planning device based on edge computing, such as Figure 6 Shown, including:

[0172] A search module 601 is configured to determine the cost-benefit corresponding to a plurality of expected total settlement bandwidths by searching, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit;

[0173] Processing module 602 is configured to allocate the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instruct the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth;

[0174] The process of the search module 601 determining the cost-benefit corresponding to the expected total settlement bandwidth includes:

[0175] For the expected total settlement bandwidth for settling bandwidth fees, the expected settlement bandwidth of each billing unit is determined based on the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth;

[0176] According to the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined according to the bandwidth simulated and allocated to each billing unit;

[0177] The cost benefit corresponding to the expected total settlement bandwidth is determined according to the sum of the simulated settlement bandwidths of the respective billing units.

[0178] In some optional implementations, the search module 601 determines the cost-benefit corresponding to a plurality of expected total settlement bandwidths by searching, and determines the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit, including:

[0179] Iterate multiple rounds of settlement bandwidth search processing until the end search condition is met, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit;

[0180] The current round of settlement bandwidth search processing includes:

[0181] For the expected total settlement bandwidth of the current round, determining a current cost-benefit corresponding to the expected total settlement bandwidth of the current round;

[0182] If the current cost benefit is greater than the currently recorded best cost benefit, the currently recorded best cost benefit is updated to the current cost benefit, and the currently recorded best expected total settlement bandwidth is updated to the expected total settlement bandwidth of the current round; if the current cost benefit is less than the currently recorded best cost benefit, the currently recorded best cost benefit and the currently recorded best expected total settlement bandwidth are kept unchanged;

[0183] Determining whether the current cost-benefit satisfies the search end condition;

[0184] When the current cost-benefit does not satisfy the search termination condition, the expected total settlement bandwidth of the current round is reduced according to a preset step size to generate the expected total settlement bandwidth of the next round.

[0185] In some optional implementations, multiple levels of search step sizes arranged from largest to smallest are preset;

[0186] The search module 601 reduces the expected total settlement bandwidth of the current round according to a preset step size to generate the expected total settlement bandwidth of the next round, including:

[0187] Reducing the expected total settlement bandwidth of the current round according to the current level search step length to generate the expected total settlement bandwidth of the next round; the current level search step length is the i-th level search step length in the multi-level search step length;

[0188] Furthermore, the current round of settlement bandwidth search processing further includes:

[0189] After determining whether the current cost-benefit satisfies the end search condition, if the current cost-benefit satisfies the end search condition, determining whether the current level search step is the last level search step;

[0190] If the current search step is not the last search step, the range of the current search step before and after the currently recorded best expected total settlement bandwidth is used as the search range; the expected total settlement bandwidth for the next round is determined based on the upper limit of the search range, and the current search step is updated to the i+1th search step;

[0191] In a case where the current level search step is the last level search step, an optimal expected total settlement bandwidth corresponding to the optimal cost benefit is determined.

[0192] In some optional implementations, the initial value of the expected total settlement bandwidth is the total settlement bandwidth corresponding to the service bandwidth data.

[0193] In some optional implementations, the billing unit is provided with a settlement configuration, the settlement configuration including a maximum settlement bandwidth and a minimum settlement bandwidth;

[0194] The search module 601 determines the expected settlement bandwidth of each billing unit according to the expected total settlement bandwidth, including:

[0195] Under the constraints of the settlement configurations of the respective billing units, the difference between the sum of the expected settlement bandwidths of the respective billing units and the expected total settlement bandwidth is minimized to determine the expected settlement bandwidth of the respective billing units.

[0196] In some optional implementations, the search module 601 minimizes the difference between the sum of the expected settlement bandwidths of the respective billing units and the expected total settlement bandwidth under the constraints of the settlement configurations of the respective billing units to determine the expected settlement bandwidth of the respective billing units, including:

[0197] Determine a maximum total settlement bandwidth and a minimum total settlement bandwidth; the maximum total settlement bandwidth is the sum of the maximum settlement bandwidths of each billing unit, and the minimum total settlement bandwidth is the sum of the minimum settlement bandwidths of each billing unit;

[0198] determining whether the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth;

[0199] When the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth, the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit is used as the expected settlement bandwidth of the billing unit; the sum of the expected settlement bandwidths of all the billing units is the same as the expected total settlement bandwidth.

[0200] In some optional implementations, the settlement configuration further includes: an initial settlement bandwidth;

[0201] The searching module 601 uses the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit as the expected settlement bandwidth of the billing unit, including:

[0202] determining a settlement bandwidth ratio of each billing unit according to the initial settlement bandwidth of each billing unit;

[0203] According to the settlement bandwidth ratio of each billing unit, the expected total settlement bandwidth is divided into the pending settlement bandwidth corresponding to each billing unit;

[0204] For a first billing unit, the pending settlement bandwidth of the first billing unit is used as the expected settlement bandwidth of the first billing unit; the pending settlement bandwidth of the first billing unit is between the maximum settlement bandwidth and the minimum settlement bandwidth of the first billing unit;

[0205] For the second billing unit, the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit, whichever is closer to the pending settlement bandwidth of the second billing unit, are used as the expected settlement bandwidth of the second billing unit, and the bandwidth difference between the pending settlement bandwidth of the second billing unit and the expected settlement bandwidth of the second billing unit are recorded; the pending settlement bandwidth of the second billing unit is not between the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit;

[0206] Determine a total bandwidth difference; the total bandwidth difference is the sum of the bandwidth differences of each second billing unit;

[0207] Under the constraints of the settlement configuration of the first billing unit, the total bandwidth difference is distributed to at least part of the first billing units, and the expected settlement bandwidth of the at least part of the first billing units is updated.

[0208] In some optional implementations, the settlement configuration further includes: a priority;

[0209] The search module 601 distributes the total bandwidth difference to at least part of the first billing units under the constraint of the settlement configuration of the first billing unit, and updates the expected settlement bandwidth of the at least part of the first billing units, including:

[0210] updating the expected settlement bandwidth of each first billing unit in descending order of priority until the total bandwidth difference is completely allocated;

[0211] The updating of the expected settlement bandwidth of the first billing unit includes:

[0212] Allocate part or all of the total bandwidth difference to the first billing unit to update the expected settlement bandwidth of the first billing unit until the expected settlement bandwidth of the first billing unit is the highest settlement bandwidth or the lowest settlement bandwidth of the first billing unit, or all of the total bandwidth difference is allocated to the first billing unit.

[0213] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0214] The edge computing-based bandwidth planning device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, including a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0215] The present disclosure also provides a computer device having the above Figure 6 The bandwidth planning device based on edge computing is shown.

[0216] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0217] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0218] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0219] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0220] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0221] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0222] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0223] A portion of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes but is not limited to a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0224] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations should all be included in the scope of protection of the present disclosure.

Claims

1. A bandwidth planning method based on edge computing, characterized in that: Applied to an edge server, the method includes: Determine the cost-benefit corresponding to multiple expected total settlement bandwidths by searching, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit; Allocating the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instructing the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth; The process of determining the cost-benefit corresponding to the expected total settlement bandwidth includes: For the expected total settlement bandwidth for settling bandwidth fees, the expected settlement bandwidth of each billing unit is determined based on the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth; According to the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined according to the bandwidth simulated and allocated to each billing unit; The cost benefit corresponding to the expected total settlement bandwidth is determined according to the sum of the simulated settlement bandwidths of the respective billing units.

2. The method according to claim 1, characterized in that The method of determining the cost-benefit corresponding to a plurality of expected total settlement bandwidths by searching, and determining the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit, includes: Iterate multiple rounds of settlement bandwidth search processing until the end search condition is met and determine the optimal expected total settlement bandwidth corresponding to the optimal cost-benefit; The current round of settlement bandwidth search processing includes: For the expected total settlement bandwidth of the current round, determining a current cost-benefit corresponding to the expected total settlement bandwidth of the current round; If the current cost benefit is greater than the currently recorded best cost benefit, the currently recorded best cost benefit is updated to the current cost benefit, and the currently recorded best expected total settlement bandwidth is updated to the expected total settlement bandwidth of the current round; if the current cost benefit is less than the currently recorded best cost benefit, the currently recorded best cost benefit and the currently recorded best expected total settlement bandwidth are kept unchanged; Determining whether the current cost-benefit satisfies the search end condition; When the current cost-benefit does not satisfy the search termination condition, the expected total settlement bandwidth of the current round is reduced according to a preset step size to generate the expected total settlement bandwidth of the next round.

3. The method according to claim 2, characterized in that A multi-level search step size is pre-set in descending order; The reducing the expected total settlement bandwidth of the current round according to a preset step size to generate the expected total settlement bandwidth of the next round includes: Reducing the expected total settlement bandwidth of the current round according to the current level search step length to generate the expected total settlement bandwidth of the next round; the current level search step length is the i-th level search step length in the multi-level search step length; Furthermore, the current round of settlement bandwidth search processing further includes: After determining whether the current cost-benefit satisfies the end search condition, if the current cost-benefit satisfies the end search condition, determining whether the current level search step is the last level search step; If the current search step is not the last search step, the range of the current search step before and after the currently recorded best expected total settlement bandwidth is used as the search range; the expected total settlement bandwidth for the next round is determined based on the upper limit of the search range, and the current search step is updated to the i+1th search step; In a case where the current level search step is the last level search step, an optimal expected total settlement bandwidth corresponding to the optimal cost benefit is determined.

4. The method according to claim 2, characterized in that The initial value of the expected total settlement bandwidth is the total settlement bandwidth corresponding to the service bandwidth data.

5. The method according to claim 1, characterized in that The billing unit is provided with a settlement configuration, wherein the settlement configuration includes a maximum settlement bandwidth and a minimum settlement bandwidth; The determining the expected settlement bandwidth of each billing unit according to the expected total settlement bandwidth includes: Under the constraints of the settlement configurations of the respective billing units, the difference between the sum of the expected settlement bandwidths of the respective billing units and the expected total settlement bandwidth is minimized to determine the expected settlement bandwidth of the respective billing units.

6. The method according to claim 5, characterized in that Minimizing the difference between the sum of the expected settlement bandwidths of the respective billing units and the expected total settlement bandwidth under the constraints of the settlement configurations of the respective billing units to determine the expected settlement bandwidth of the respective billing units includes: Determine a maximum total settlement bandwidth and a minimum total settlement bandwidth; the maximum total settlement bandwidth is the sum of the maximum settlement bandwidths of each billing unit, and the minimum total settlement bandwidth is the sum of the minimum settlement bandwidths of each billing unit; determining whether the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth; When the expected total settlement bandwidth is between the maximum total settlement bandwidth and the minimum total settlement bandwidth, the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit is used as the expected settlement bandwidth of the billing unit; the sum of the expected settlement bandwidths of all the billing units is the same as the expected total settlement bandwidth.

7. The method according to claim 6, characterized in that The settlement configuration also includes: initial settlement bandwidth; The step of using the component of the expected total settlement bandwidth that matches the settlement configuration of the billing unit as the expected settlement bandwidth of the billing unit includes: determining a settlement bandwidth ratio of each billing unit according to the initial settlement bandwidth of each billing unit; According to the settlement bandwidth ratio of each billing unit, the expected total settlement bandwidth is divided into the pending settlement bandwidth corresponding to each billing unit; For a first billing unit, the pending settlement bandwidth of the first billing unit is used as the expected settlement bandwidth of the first billing unit; the pending settlement bandwidth of the first billing unit is between the maximum settlement bandwidth and the minimum settlement bandwidth of the first billing unit; For the second billing unit, the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit, whichever is closer to the pending settlement bandwidth of the second billing unit, are used as the expected settlement bandwidth of the second billing unit, and the bandwidth difference between the pending settlement bandwidth of the second billing unit and the expected settlement bandwidth of the second billing unit are recorded; the pending settlement bandwidth of the second billing unit is not between the highest settlement bandwidth and the lowest settlement bandwidth of the second billing unit; Determine a total bandwidth difference; the total bandwidth difference is the sum of the bandwidth differences of each second billing unit; Under the constraints of the settlement configuration of the first billing unit, the total bandwidth difference is distributed to at least part of the first billing units, and the expected settlement bandwidth of the at least part of the first billing units is updated.

8. The method according to claim 7, characterized in that The settlement configuration also includes: priority; Allocating the total bandwidth difference to at least part of the first billing units under the constraints of the settlement configuration of the first billing units, and updating the expected settlement bandwidth of at least part of the first billing units, includes: updating the expected settlement bandwidth of each first billing unit in descending order of priority until the total bandwidth difference is completely allocated; The updating of the expected settlement bandwidth of the first billing unit includes: Allocate part or all of the total bandwidth difference to the first billing unit to update the expected settlement bandwidth of the first billing unit until the expected settlement bandwidth of the first billing unit is the highest settlement bandwidth or the lowest settlement bandwidth of the first billing unit, or all of the total bandwidth difference is allocated to the first billing unit.

9. A bandwidth planning device based on edge computing, characterized in that: Applied to an edge server, the device includes: A search module is used to determine the cost benefits corresponding to multiple expected total settlement bandwidths by searching, and determine the optimal expected total settlement bandwidth corresponding to the optimal cost benefit; A processing module, configured to allocate the best expected settlement bandwidth of each billing unit corresponding to the best expected total settlement bandwidth to the corresponding billing unit, and instruct the billing unit to provide corresponding bandwidth resources according to the best expected settlement bandwidth; The process of the search module determining the cost-benefit corresponding to the expected total settlement bandwidth includes: For the expected total settlement bandwidth for settling bandwidth fees, the expected settlement bandwidth of each billing unit is determined based on the expected total settlement bandwidth; the sum of the expected settlement bandwidths of each billing unit is consistent with the expected total settlement bandwidth; According to the given service bandwidth data and the expected settlement bandwidth of each billing unit, the bandwidth of each billing unit is simulated and allocated, and the simulated settlement bandwidth of each billing unit is determined according to the bandwidth simulated and allocated to each billing unit; The cost benefit corresponding to the expected total settlement bandwidth is determined according to the sum of the simulated settlement bandwidths of the respective billing units.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the edge computing-based bandwidth planning method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the bandwidth planning method based on edge computing according to any one of claims 1 to 8.

Images