A method and device for dynamically adjusting OSU bandwidth

Abstract

The present invention relates to an OSU bandwidth dynamic adjustment method and device, the method comprising: determining the current adjusted metric bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments and the adjusted historical bandwidth peak value; determining the current effective metric bandwidth according to the relationship between the current real-time bandwidth and the current adjusted metric bandwidth; and performing real-time bandwidth allocation according to the current effective metric bandwidth after a fault occurs. The method can solve the problem that the bandwidth can be adaptively adjusted when the OSU service fault is dynamically restored.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an OSU bandwidth dynamic adjustment method and device. Background Art

[0002] At present, with the development of OSU technology, small-granular optical switching technology is becoming increasingly mature. Due to the characteristics of small bandwidth and flexible scheduling, each user no longer needs to reuse pipes with other users and can have exclusive optical connections. OSU technology can provide finer time slot granularity, simpler bandwidth lossless adjustment mechanism, and support efficient carrying of customer services at rates from 2M to 100Gbps, while retaining the advantages of traditional OTN hard pipes and rich OAM, so that OTN has the ability to sink from the backbone core to the access terminal. At the same time, customers' demand for service quality is constantly upgrading, and core performance parameters such as latency, bandwidth, and availability, especially in the core MESH networking scenario, large bandwidth, low latency, and resistance to multiple fiber breaks have become basic requirements. With the expansion of dedicated line users and the rapid growth of demand for high-quality home broadband services, differentiated services have become one of the core competitiveness of operators. Some high-value dedicated lines require 50ms protection capabilities, but the price is expensive; for some low-value dedicated lines, customers hope that operators can provide a low-priced service option, without mandatory 50ms protection performance, and hundreds of milliseconds or even seconds of recovery performance can meet the requirements. In this context, slicing technology that can hierarchically classify dedicated lines according to SLA requirements has become a solution that operators urgently need.

[0003] In the related technology, for ODUK services, since their rate is relatively fixed, when a service fails and needs to be rerouted and restored, the service rerouting recovery can be completed according to the fixed service rate and the corresponding routing strategy. However, since the OSU service bandwidth is more flexible and can dynamically adjust the bandwidth according to traffic changes, service failures occur randomly. If the existing ODUK-related routing switching rules and load balancing strategies are inherited, it is very likely that after the service failure switching is successfully restored, because only the real-time bandwidth of the service is considered, the routing calculation load distribution is unreasonable, and the remaining bandwidth space of some links is insufficient, which affects the subsequent dynamic adjustment capability of the service bandwidth, resulting in unreasonable and insufficient utilization of link resources and bandwidth. Due to the introduction of the service dynamic recovery function, the service bandwidth adjustment bottleneck problem is triggered. Summary of the invention

[0004] The embodiment of the present invention provides an OSU bandwidth dynamic adjustment method and device, which solves the problem of adaptively adjusting the bandwidth when an OSU service failure is dynamically restored.

[0005] An embodiment of the present invention provides a method for dynamically adjusting OSU bandwidth, characterized in that it includes the steps of:

[0006] Determine the current adjusted measured bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value;

[0007] Determine the current effective measurement bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted measurement bandwidth;

[0008] After a fault occurs, real-time bandwidth allocation is performed according to the current effective measured bandwidth.

[0009] In some embodiments, the initial bandwidth is set according to a minimum service bandwidth.

[0010] In some embodiments, the number of bandwidth adjustments includes the total number of adjustments up to now and the number of times the real-time bandwidth is greater than the average bandwidth.

[0011] In some embodiments, the steps are further included:

[0012] Compare the current real-time bandwidth with the initial bandwidth, and if the current real-time bandwidth is equal to the initial bandwidth, then do not update the total number of adjustments up to now;

[0013] If the current real-time bandwidth is greater than the initial bandwidth, the first counter is incremented by 1 and the total number of adjustments up to the current time is updated according to the accumulated value of the first counter.

[0014] In some embodiments, the steps are further included:

[0015] The current real-time bandwidth is compared with the adjusted average bandwidth. If the current real-time bandwidth is greater than the adjusted average bandwidth, the second counter is incremented by 1 and the number of times the real-time bandwidth is greater than the average bandwidth is updated according to the accumulated value of the second counter.

[0016] In some embodiments, the steps are further included:

[0017] If the total number of adjustments up to now is updated, the adjusted average bandwidth is calculated and updated according to the first formula, where the first formula is:

[0018]

[0019] in, is the average bandwidth after adjustment, N is the total number of adjustments after update, and B i is the real-time bandwidth after the i-th adjustment.

[0020] In some embodiments, the step of determining the current adjusted measured bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value comprises the following steps:

[0021] The currently adjusted metric bandwidth is calculated according to a second formula, wherein the second formula includes:

[0022]

[0023] Where B(x) is the measured bandwidth of the service after the xth adjustment, B t is the current real-time bandwidth, is the average bandwidth after adjustment, B max is the maximum bandwidth of the service determined according to the adjusted historical bandwidth peak value, B0 is the initial bandwidth, and B i is the real-time bandwidth after the i-th adjustment, x is the total number of adjustments up to now, and y is the number of times the real-time bandwidth is greater than the average bandwidth.

[0024] In some embodiments, the step of determining the current effective metric bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted metric bandwidth comprises the following steps:

[0025] The current effective metric bandwidth is determined according to a third formula, wherein the third formula includes:

[0026] B w =C*Max(B t ,B(x)),

[0027] Among them, B w is the current effective measurement bandwidth, B(x) is the current adjusted measurement bandwidth, and C is the adjustable coefficient.

[0028] In some embodiments, the adjustable coefficient C is determined according to the current network resource utilization, and when the current network resource utilization is greater than a preset threshold, the value of the adjustable coefficient C is set to 1;

[0029] If the current network resource utilization is less than or equal to a preset threshold, the adjustable coefficient C is in the range of [1.2, 1.5].

[0030] Second, an embodiment of the present invention further provides a device, characterized in that the device comprises: at least one processor; and a memory coupled to the at least one processor, the memory containing instructions stored therein, the instructions being loaded and executed by the processor to implement the method as described in any one of claims 1-9.

[0031] The embodiment of the present invention provides a method and device for dynamically adjusting the bandwidth of an OSU. Considering that the routing calculation method based on the current real-time rate of the service is difficult to match the dynamic change characteristics of the bandwidth of the OSU service, it is proposed to comprehensively consider the current real-time bandwidth and the current adjusted metric bandwidth to determine the effective metric bandwidth, and finally use the effective metric bandwidth to allocate the real-time bandwidth and serve as the basis for routing calculation. Since the determination process of the metric bandwidth needs to comprehensively consider parameters of four dimensions, including the initial bandwidth, the adjusted average bandwidth, the number of adjustments, and the historical bandwidth peak value, when the OSU service fails, the effective metric bandwidth is used to replace the real-time bandwidth to calculate the restoration route, which can reasonably match the service characteristics and evenly distribute the link bandwidth load, avoiding the influence of the subsequent adjustment due to the service switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A schematic diagram of a flow chart of a method for dynamically adjusting OSU bandwidth provided by an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of a flow chart of a method for dynamically adjusting OSU bandwidth provided by an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of a link failure switching rule flow provided by an embodiment of the present invention;

[0036] Figure 4 A schematic diagram of a business load distribution method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] like Figure 1 As shown, an embodiment of the present invention provides an OSU bandwidth dynamic adjustment method, comprising the steps of:

[0039] S100: determining the current adjusted metric bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value;

[0040] S200: Determine the current effective measurement bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted measurement bandwidth;

[0041] S300: After a fault occurs, real-time bandwidth allocation is performed according to the current effective measured bandwidth.

[0042] It can be understood that S100 determines the measurement bandwidth based on parameters of four dimensions, among which the initial bandwidth is used to reflect the minimum service bandwidth particle of the OSU service, the average bandwidth is used to reflect the average situation of service adjustment, the number of adjustments is used to reflect the frequency of service adjustment, and the historical bandwidth peak value includes the peak value set of each service in the past bandwidth change, which can be used to estimate the type of the main service carried. In S200, when determining the effective measurement bandwidth, both the real-time bandwidth and the measurement bandwidth and the relationship between the two factors need to be considered at the same time, so the effective measurement bandwidth can take into account the characteristics of both the real-time bandwidth and the measurement bandwidth.

[0043] It should be noted that in S300, in order to ensure the results of load sharing, each OSU service performs routing calculations based on the effective measured bandwidth, which can also take into account link bandwidth load management. After the routing is performed on the service, resources are pre-reduced based on the effective measured bandwidth, replacing the traditional method of updating based on the actual bandwidth of the service.

[0044] The embodiment of the present invention takes into account the problem that the routing calculation method based on the current real-time rate of the service is difficult to match the dynamic change characteristics of the OSU service bandwidth, and proposes a method of comprehensively considering the current real-time bandwidth and the current adjusted metric bandwidth to determine the effective metric bandwidth, and finally allocates the real-time bandwidth based on the effective metric bandwidth and serves as the basis for routing calculation. Since the determination process of the metric bandwidth needs to comprehensively consider parameters of four dimensions, including the initial bandwidth, the adjusted average bandwidth, the number of adjustments, and the historical bandwidth peak value, when the OSU service fails, the effective metric bandwidth is used instead of the real-time bandwidth to calculate the restoration route, which can reasonably match the service characteristics and evenly distribute the link bandwidth load, avoiding the influence of the subsequent adjustment due to the service switching.

[0045] Preferably, in S300, when a failure occurs, priority is given to sorting according to the size of the effective metric bandwidth, load sharing is performed for routing calculation, and the service is reasonably allocated to different links for recovery; because the effective metric bandwidth of the service is usually larger than the current actual bandwidth of the service, in extreme scenarios (for example: multiple points of network failure, lack of remaining resources, etc.), if a large amount of service switching occurs, all services use the metric bandwidth to calculate the route, and there may be a situation where the total remaining bandwidth of the network is insufficient, and some services cannot complete service recovery according to the metric bandwidth. Therefore, in the event of failure to allocate effective metric bandwidth, relevant control strategies can be introduced, combined with resource pre-reduction rules, and fall back to using real-time bandwidth to recalculate the route and switch for recovery; try to avoid unreasonable service switching routing sharing, which affects subsequent bandwidth adjustment.

[0046] Specifically, the dynamic bandwidth adjustment of OSU services will report the relevant bandwidth parameter information to the control plane, and the control plane will record and update the effective measurement bandwidth value for all OSU services in units of links. The control plane updates the ranking of the corresponding link services according to the latest effective measurement bandwidth of the service. , where the link services are sorted by effective measurement bandwidth and real-time bandwidth respectively. Figure 3 As shown in the figure, after a link failure, the equipment link failure is reported to the control plane. The control plane prioritizes the sorting according to the effective measured bandwidth of the service, performs route calculation and pre-reduces resources. If the service switching is successful, it directly enters the signaling route construction. If the route calculation fails (the service switching is unsuccessful), the resource pre-reduction is maintained, and the real-time bandwidth sorting is directly switched to perform route calculation. If the route calculation is successful (the service switching is successful), the warning risk is reported (prompting that the service adjustment may fail) and the signaling route is constructed. If the route calculation still fails, the timer is started, and the pre-reduction time is waited for to end, and the real-time bandwidth sorting is recalculated. If the route calculation is successful, the signaling route is constructed. If it still fails, the route calculation is stopped and the service switching failure alarm is reported.

[0047] Preferably, the initial bandwidth is set according to the minimum service bandwidth. Since the OSU service provides finer time slot granularity and a simpler bandwidth lossless adjustment mechanism, it supports efficient carrying of customer services at rates from 2M to 100Gbps. On this basis, considering business development, simplifying OSU technology and reducing equipment costs, the initial bandwidth can be set to 10M.

[0048] In some embodiments, the number of bandwidth adjustments includes the total number of adjustments to date and the number of times the real-time bandwidth is greater than the average bandwidth.

[0049] It can be understood that in this embodiment, the number of bandwidth adjustments is divided into two levels. The first level is the total number of adjustments up to the present, that is, the total number of adjustments from the establishment of the service to the present; the second level is the number of times the real-time bandwidth is greater than the average bandwidth. The number at this level only records the number of times the adjusted bandwidth is greater than the mean (that is, the adjusted average bandwidth), which can be used to analyze the frequency of large bandwidth adjustments in the service.

[0050] In some embodiments, determining the total number of adjustments to date includes the steps of:

[0051] S110: Compare the current real-time bandwidth with the initial bandwidth, and if the current real-time bandwidth is equal to the initial bandwidth, do not update the total number of adjustments up to now;

[0052] S111: If the current real-time bandwidth is greater than the initial bandwidth, the first counter is incremented by 1 and the total number of adjustments up to the current time is updated according to the accumulated value of the first counter.

[0053] It can be understood that, in this embodiment, when calculating the total number of adjustments, the situation of adjusting back to the initial bandwidth is excluded, which means that the situation of no actual bearer service is excluded, which is conducive to further accurately estimating the service bandwidth change.

[0054] In some embodiments, determining the number of times the real-time bandwidth is greater than the average bandwidth comprises the steps of:

[0055] S112: Compare the current real-time bandwidth with the adjusted average bandwidth. If the current real-time bandwidth is greater than the adjusted average bandwidth, add 1 to the second counter and update the number of times the real-time bandwidth is greater than the average bandwidth according to the accumulated value of the second counter.

[0056] In some embodiments, the calculation of the adjusted average bandwidth in S100 includes the steps of:

[0057] S120: If the total number of adjustments up to now is updated, the adjusted average bandwidth is calculated and updated according to formula (1),

[0058]

[0059] in, is the average bandwidth after adjustment, N is the total number of adjustments after update, and B i is the real-time bandwidth after the i-th adjustment.

[0060] It is understandable that the OSU service changes according to the traffic, ignoring the situation of adjusting back to the initial bandwidth. The average bandwidth after each dynamic adjustment will have deviations when the sampling sample is small. When the sample is large enough, it can basically estimate the average situation of the approximate adjustment of the service.

[0061] In some embodiments, when determining the current adjusted metric bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value in S100, the following steps are further included:

[0062] S130: Calculate the currently adjusted metric bandwidth according to formula (2), where the second formula includes:

[0063]

[0064] Where B(x) is the measured bandwidth of the service after the xth adjustment, B t is the current real-time bandwidth, is the average bandwidth after adjustment, B max is the maximum bandwidth of the service determined according to the adjusted historical bandwidth peak value, B0 is the initial bandwidth, x is the total number of adjustments up to now, and y is the number of times the real-time bandwidth is greater than the average bandwidth.

[0065] It is understandable that the measured bandwidth is mainly determined by the number / frequency of service adjustments, the historical average bandwidth (i.e. the average bandwidth after adjustment), the fluctuation range, etc. The measured bandwidth is related to the real-time bandwidth, the offset (adjustment range) between the real-time bandwidth and the historical average bandwidth, the adjustment frequency, etc., and the measured bandwidth is proportional to the frequency at which the adjusted bandwidth is greater than the average bandwidth, and the measured bandwidth is proportional to the service adjustment range.

[0066] In some embodiments, determining the current effective metric bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted metric bandwidth in S200 includes the steps of:

[0067] S210: Determine the current effective metric bandwidth according to formula (3), wherein the third formula includes:

[0068] B w = C*Max(B t , B(x)) , (3)

[0069] Among them, B w is the current effective measurement bandwidth, B(x) is the current adjusted measurement bandwidth, and C is the adjustable coefficient.

[0070] It can be understood that the effective measurement bandwidth is obtained by weighting the maximum value of the real-time bandwidth and the measurement bandwidth.

[0071] Preferably, the adjustable coefficient C is determined according to the current network resource utilization, and when the current network resource utilization is greater than a preset threshold, the value of the adjustable coefficient C is set to 1;

[0072] If the current network resource utilization is less than or equal to a preset threshold, the adjustable coefficient C is in the range of [1.2, 1.5].

[0073] It is understandable that, usually when the network resource utilization is greater than a preset threshold (such as 50%), the C value is 1. For networks with large bandwidth capacity, when the network link resource utilization ratio is lower than 50%, the C value can be appropriately increased by 20% to 50%, so that the service can be reasonably and evenly distributed to each link according to the frequency and bandwidth adjusted in history, and the impact of fault switching on the service adjustment space can be minimized.

[0074] like Figure 2 As shown, in one embodiment, the OSU bandwidth dynamic adjustment method specifically includes:

[0075] S01: After the service bandwidth is adjusted, the real-time service bandwidth is recorded and a valid measured bandwidth update request is triggered;

[0076] S02: Compare the real-time bandwidth of the service with the initial bandwidth. If the real-time bandwidth is greater than the initial bandwidth, jump to step S03; if the real-time bandwidth is equal to the initial bandwidth (generally not less than), jump to step S07.

[0077] S03: adding 1 to the first counter, updating the total number of bandwidth adjustment times with the accumulated value of the first counter, and updating the average bandwidth value based on formula (1);

[0078] S04: Compare the real-time bandwidth with the minimum value of the historical peak cluster, and update the peak cluster and the cluster mean;

[0079] S05: compare the current real-time bandwidth with the average bandwidth. If the real-time bandwidth is less than the average bandwidth, jump to S07. If the real-time bandwidth is greater than or equal to the average bandwidth, jump to S06.

[0080] S06: adding 1 to the second counter, and updating the accumulated value of the second counter to the value of the number of times the real-time bandwidth is greater than the average bandwidth;

[0081] S07: Update the C value based on the resource utilization of the current TE link in the entire network and calculate and update the current metric bandwidth based on formula (2);

[0082] S08: Calculate and update the current effective metric bandwidth based on formula (3).

[0083] It should be noted that the formulas (1), (2) and (3) are referred to the above embodiments. The updating of the peak cluster and the cluster mean in S04 means replacing the minimum value in the original peak cluster with the value of the real-time bandwidth, and before the replacement, the current bandwidth of the service can be compared with the historical peak value in the original peak cluster. If the current bandwidth of the service is less than the minimum value in the peak cluster, it will not be replaced. Otherwise, the minimum value of the peak cluster will be replaced. At the same time, the average value of the updated peak cluster is taken to obtain a new cluster mean, which is used to affect B in formula (2). max The value of .

[0084] The TE link mentioned in S07 refers to a basic link of a control plane network, where TE stands for traffic engineering.

[0085] like Figure 4 As shown, in a specific embodiment, if there are three services (service A, service B, service C) between the AC topology. First, take service A as an example. If A is a cloud education broadband service, its initial bandwidth is 10M, the current real-time bandwidth is 30M, the historical average bandwidth is 90.6M (i.e., the calculation result of formula (1)), the maximum bandwidth is 195M, the number of adjustments (statistical sample, time limit is one month) is 96 times, and the number of adjustments greater than the average is 41 times. Then, by using formulas (1), (2), and (3), the adjusted metric bandwidth can be calculated to be 130.35M (simplified to 130M in this embodiment), and the metric bandwidths of services B and C can be calculated in the same way. Thus, the bandwidth data of services A, B and C are obtained respectively: the real-time bandwidth of service A is 30M, the adjusted measured bandwidth is 130M, and the effective measured bandwidth is 130M; the real-time bandwidth of service B is 20M, the adjusted measured bandwidth is 100M, and the effective measured bandwidth is 100M; the real-time bandwidth of service C is 90M, the adjusted measured bandwidth is 80M, and the effective measured bandwidth is 90M.

[0086] When AC fails, if services are allocated based on real-time bandwidth according to the relevant technology, service C will be switched first because its real-time bandwidth is the largest, and ABC will be selected first because the remaining bandwidth of path ABC is greater than ADC; then when service A is switched, path ADC will be selected; when service B is switched, path ADC will be selected.

[0087] In the case where services A and B need to adjust their bandwidth at the same time, since the total bandwidth of DC is only 200M, and the adjusted measured bandwidth of services A and B (taking into account the initial bandwidth, the average bandwidth after adjustment, the number of adjustments, and the historical bandwidth peak) is 230M (130M+100M), it means that one of the services A and B may fail to adjust.

[0088] If the effective metric bandwidth is used as the basis for traffic diversion, the result of the load balancing route calculation when AC fails is: service A is switched first (since the effective metric bandwidth corresponding to service A is 130M, the bandwidth value is the largest), and ABC is selected first; service B is switched next, and path ADC is selected; service C is switched next, and path ABC is selected. Even if services A and B need to adjust bandwidth at the same time, the bandwidth of BC and DC segments can meet the requirements to avoid adjustment failure.

[0089] On the other hand, based on the same inventive concept, an embodiment of the present invention also provides a device, characterized in that the device includes: at least one processor; and a memory coupled to the at least one processor, the memory containing instructions stored therein, and the instructions are loaded and executed by the processor to implement a method as any one of the method embodiments.

[0090] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer-readable storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0091] It should be noted that, in the present invention, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0092] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for dynamically adjusting OSU bandwidth, characterized in that: It includes the steps of: Determine the current adjusted measured bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value; Determine the current effective measurement bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted measurement bandwidth; After a fault occurs, real-time bandwidth allocation is performed according to the current effective measured bandwidth.

2. The OSU bandwidth dynamic adjustment method according to claim 1, characterized in that: The initial bandwidth is set according to the minimum service bandwidth.

3. The OSU bandwidth dynamic adjustment method according to claim 1, characterized in that: The bandwidth adjustment times include the total adjustment times up to now and the times when the real-time bandwidth is greater than the average bandwidth.

4. The OSU bandwidth dynamic adjustment method as claimed in claim 3, characterized in that: Also includes the steps: Compare the current real-time bandwidth with the initial bandwidth, and if the current real-time bandwidth is equal to the initial bandwidth, then do not update the total number of adjustments up to now; If the current real-time bandwidth is greater than the initial bandwidth, the first counter is incremented by 1 and the total number of adjustments up to the current time is updated according to the accumulated value of the first counter.

5. The OSU bandwidth dynamic adjustment method as claimed in claim 3, characterized in that: Also includes the steps: The current real-time bandwidth is compared with the adjusted average bandwidth. If the current real-time bandwidth is greater than the adjusted average bandwidth, the second counter is incremented by 1 and the number of times the real-time bandwidth is greater than the average bandwidth is updated according to the accumulated value of the second counter.

6. The OSU bandwidth dynamic adjustment method as claimed in claim 4, characterized in that: Also includes the steps: If the total number of adjustments up to now is updated, the adjusted average bandwidth is calculated and updated according to the first formula, where the first formula is: in, is the average bandwidth after adjustment, N is the total number of adjustments after update, and B i is the real-time bandwidth after the i-th adjustment.

7. The OSU bandwidth dynamic adjustment method according to claim 1, characterized in that: The method of determining the current adjusted metric bandwidth according to the initial bandwidth, the adjusted average bandwidth, the number of bandwidth adjustments, and the adjusted historical bandwidth peak value comprises the following steps: The currently adjusted metric bandwidth is calculated according to a second formula, wherein the second formula includes: Where B(x) is the measured bandwidth of the service after the xth adjustment, B t is the current real-time bandwidth, is the average bandwidth after adjustment, B max is the maximum bandwidth of the service determined according to the adjusted historical bandwidth peak value, B0 is the initial bandwidth, and B i is the real-time bandwidth after the i-th adjustment, x is the total number of adjustments up to now, and y is the number of times the real-time bandwidth is greater than the average bandwidth.

8. The OSU bandwidth dynamic adjustment method according to claim 1, characterized in that: The method of determining the current effective measurement bandwidth according to the relationship between the current real-time bandwidth and the currently adjusted measurement bandwidth comprises the following steps: The current effective measurement bandwidth is determined according to the third formula. include: B w =C*Max(B t ,B(x)), Among them, B w is the current effective measurement bandwidth, B(x) is the current adjusted measurement bandwidth, and C is the adjustable coefficient.

9. The OSU bandwidth dynamic adjustment method as claimed in claim 8, characterized in that: The adjustable coefficient C is determined according to the current network resource utilization. When the current network resource utilization is greater than a preset threshold, the value of the adjustable coefficient C is set to 1; If the current network resource utilization is less than or equal to a preset threshold, the adjustable coefficient C is in the range of [1.2, 1.5].

10. A device, characterized in that: The device comprises: at least one processor; and a memory coupled to the at least one processor, wherein the memory contains instructions stored therein, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 9.

Images