CN118381734A - Method and device for adjusting bandwidth in FlexE network - Google Patents

Abstract

A method and apparatus for adjusting bandwidth in FlexE networks. The method comprises the following steps: obtaining a predicted value of the bandwidth required by a target client; under the condition that the bandwidth value of the time slot is a fixed value, determining the adjustment information of the number of the time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client; and sending the adjustment information. The embodiment of the application can realize the automatic adjustment of the bandwidth of the target client without manual adjustment; meanwhile, the problem of frequent adjustment caused by fluctuation near the threshold value is avoided, the system overhead is reduced, and the running stability is improved.

Description

Method and device for adjusting bandwidth in FlexE network

Technical Field

The present invention relates to network communication technology, and in particular, to a method and apparatus for adjusting bandwidth in FlexE networks.

Background

The flexible Ethernet (FlexEible Ethernet, flexE) is based on the principle of time division multiplexing, the FlexE network can bind PHYs of a plurality of physical layers to form a large bandwidth resource pool, then all bandwidth resources are divided based on time slot granularity, service bandwidths are more flexibly distributed conveniently, various specific users or leased clients and specific application services are met, the service is hard-sliced, the service bearing a plurality of scenes can be shared, and the system is safer and more reliable.

The adjustment and allocation of bandwidth are all operated based on minimum slot granularity, the granularity defined on the OIF-02.1 standard is 5G, with the development of technology and the need of fine management and control of resources, the granularity of the slots required to be supported becomes smaller and smaller, and the granularity of the slots reaches M level, so that the management of bandwidth becomes more and more troublesome under the condition of smaller and smaller slot granularity.

The bandwidth adjustment technology in the conventional FlexE network system generally has two modes, one is that management operators reserve a certain resource bandwidth according to service conditions and manually adjust the bandwidth; another is to adjust the threshold based on bandwidth usage.

The mode based on manual adjustment requires operation and maintenance personnel to be capable of being mastered by the related technology, in addition, the manual intervention degree is high, the workload is complex, the granularity of adjustment is not fine enough, and the utilization rate of resources is not efficient enough.

The adjustment method based on the threshold value is used for adjusting under the condition of triggering the threshold value threshold, so that the problem of 'passive' adjustment exists, and the problems of packet loss and jitter are likely to be caused by untimely adjustment; in addition, this adjustment method has a problem of "blind" adjustment, and the adjustment size is not fine enough, and especially when the adjustment is performed in a scene where the bandwidth is suddenly changed and fluctuates around the threshold value, frequent adjustment is often performed, and the system overhead is liable to be large and unstable.

Disclosure of Invention

The embodiment of the application provides a method and a device for adjusting bandwidth in FlexE networks.

A method of adjusting bandwidth in a FlexE network, comprising:

Obtaining a predicted value of the bandwidth required by a target client;

Under the condition that the bandwidth value of the time slot is a fixed value, determining the adjustment information of the number of the time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client;

And sending the adjustment information.

An apparatus for adjusting bandwidth in a FlexE network, comprising:

the acquisition module is used for acquiring the predicted value of the bandwidth required by the target client;

the determining module is used for determining the adjusting information of the number of the time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client under the condition that the bandwidth value of the time slots is a fixed value;

And the sending module is used for sending the adjustment information.

According to the embodiment of the application, the automatic adjustment of the bandwidth of the target client is realized by determining the adjustment information of the number of the time slots corresponding to the target client, and the manual adjustment is not needed; in addition, the adjustment information of the number of time slots is determined through the predicted value and the preset value of the current bandwidth, so that the problem of frequent adjustment caused by fluctuation near the threshold value is avoided, the system overhead is reduced, and the running stability is improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. Other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.

Drawings

The accompanying drawings are included to provide an understanding of the principles of the application, and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain, without limitation, the principles of the application.

Fig. 1 is a flowchart of a method for adjusting bandwidth in FlexE networks according to an embodiment of the present application;

Fig. 2 is a schematic structural diagram of a device for adjusting bandwidth in FlexE networks according to an embodiment of the present application.

Detailed Description

The present application has been described in terms of several embodiments, but the description is illustrative and not restrictive, and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the described embodiments. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or in place of any other feature or element of any other embodiment unless specifically limited.

The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The disclosed embodiments, features and elements of the present application may also be combined with any conventional features or elements to form a unique inventive arrangement. Any feature or element of any embodiment may also be combined with features or elements from other inventive arrangements to form another unique inventive arrangement. It is therefore to be understood that any of the features shown and/or discussed in the present application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not to be restricted except in light of the attached claims and their equivalents. Further, various modifications and changes may be made within the scope of the appended claims.

Furthermore, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other sequences of steps are possible as will be appreciated by those of ordinary skill in the art. Accordingly, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Furthermore, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.

Fig. 1 is a flowchart of a method for adjusting bandwidth in FlexE networks according to an embodiment of the present application. As shown in fig. 1, the method includes:

step 101, obtaining a predicted value of a bandwidth required by a target client;

Wherein, the predicted value of the bandwidth required by the target customer is obtained by using the artificial intelligent model.

With the gradual maturation and development of artificial intelligence technology, the artificial intelligence technology has begun to be widely applied in various fields. In the operation and maintenance management system of the communication equipment network, the related technology of artificial intelligence is introduced, so that the operation and maintenance and management network system can be more intelligent and efficient, the management efficiency can be greatly improved, and the cost is saved.

Specifically, a model can be built according to sample data, and the model is used for predicting the bandwidth used by a client in the future, so that support is provided for actively and finely adjusting the bandwidth, and in addition, the system overhead and the occurrence probability of the problems of packet loss and jitter can be effectively reduced.

The sample data used by the artificial intelligent model are time sequences, and each time sequence records the configuration data of FlexE networks, the flow data characteristics of clients and the running environment information in respective time intervals, wherein the running environment information comprises at least one of the position information of equipment in a network topological graph, weather and holidays.

102, Under the condition that the bandwidth value of a time slot is a fixed value, determining the adjustment information of the number of time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client;

in the definition of OIF-02.1, the bandwidth value of the time slot is 5G, where in practical application, the bandwidth value of the time slot may also be other values.

Specifically, according to the difference between the predicted value and the preset value, the adjustment information of the number of time slots corresponding to the target client is determined according to the difference, and the adjustment information is used as the adjustment strategy of the bandwidth of the target client.

Step 103, sending the adjustment information;

Because FlexE overhead frames carry time slot mapping information, the adjustment information can be sent through FlexE overhead frames, so that a target client can conveniently acquire the corresponding time slot adjustment information, the time slot information can be conveniently acquired, and the data transmission efficiency is improved.

According to the method provided by the embodiment of the application, the automatic adjustment of the bandwidth of the target client is realized by determining the adjustment information of the number of the time slots corresponding to the target client, and the manual adjustment is not needed; in addition, the adjustment information of the number of time slots is determined through the predicted value and the preset value of the current bandwidth, so that the problem of frequent adjustment caused by fluctuation near the threshold value is avoided, the system overhead is reduced, and the running stability is improved.

The following describes the method provided by the embodiment of the application:

in one exemplary embodiment, the artificial intelligence model is obtained by:

Constructing a network link state topological graph based on configuration information on equipment, and collecting FlexeE configuration data, characteristic information of a data flow packet and some external influence factor information irrelevant to the equipment;

preprocessing the acquired data information, including quantization and normalization, forming time series data, and making a label, wherein the label is the flow of the next moment and is used as sample data;

and (5) inputting the preprocessed data into the deep learning model for iterative training to obtain an artificial intelligent model.

Wherein for more accurate predictions, the sample data may include characteristic values of various influencing factors, wherein the sampling time interval of the data may be based on every second, every fifth second, every minute, etc. Wherein:

FlexE configuration data including group id, group num, group bandwidth size, client id, client num, group to which the client belongs, client bandwidth size, etc.;

The feature information of the traffic data packet based on the time sequence on the client comprises: the type of the carried service, the number of packets, the average packet length, the packet length variance, the transmission delay, the current flow size and the like;

Peripheral influencing factors of the device, including: location information in the device topology, weather, holiday conditions, specific times, etc. The data sequence characteristic information is combined to form a group of data sequence characteristic information as a piece of sample data, and the expression mode is as follows:

[ group-id, group num, group bandwidth, client-id, client num, client bandwidth, client traffic size, client traffic first-order variance, client traffic second-order variance, traffic type, number of packets, average packet length, packet length variance, current traffic size, location node information, weather, holidays, time ].

In deep learning model selection, the artificial intelligence model can be a Long Short-Term Memory (LSTM) or LSTM-based (CNN-LSTM, GNN-LSTM, bi-LSTM, etc.) variational model. For example, taking an LSTM model as an example, the model structure is divided into an input layer, a circulating layer and a full-connection layer, the layer number of the neural network and super parameters including batch-size, dropout and the like related to training operation are set, and iterative training is carried out by using sample data to obtain a training model. In the training model, the selection parameters are as follows: the dropout value is 0.1, the LSTM unit number is 300, the LSTM layer number is 2, the total connection unit number is 30 x 30, the batch size is set to 20, and the loss function adopts the mean square error.

And the bandwidth of the target client is predicted based on the artificial intelligence model, so that the operation efficiency is high, and the prediction accuracy is improved.

In an exemplary embodiment, the predicted value includes a predicted value for each of 2n+1 time intervals, where n is an integer greater than or equal to 1;

the unit of the time interval can be flexibly set according to the actual scene, such as every minute, every five minutes, etc.

In the embodiment of the application, the value of n is not excessively large, and if the value is excessively large, the accuracy of the predicted value can be affected, and the calculation complexity of the artificial intelligent model can be increased to a certain extent. Therefore, in the embodiment of the application, the value of n is preferably set to be 1 or 2, so that enough predicted values are ensured to be obtained to accurately determine the adjustment information of the time slot number, and meanwhile, the calculation complexity of the artificial intelligent model can be controlled.

Wherein the determining, according to the predicted value and the value of the current bandwidth of the target client in the target FlexE group, the adjustment information of the number of time slots corresponding to the target client in the target FlexE group includes:

Obtaining a maximum value and a minimum value from predicted values corresponding to 2n+1 time intervals;

And determining the adjustment information according to the maximum value, the minimum value and the preset value.

Since the number of the obtained predicted values includes at least 3, only the extremum of the predicted values can be selected for the operation of adjusting the number of slots, thereby reducing the computational complexity of the operation of adjusting the number of slots.

Further, the determining the adjustment information according to the maximum value, the minimum value and the preset value includes the following three application scenarios, wherein:

application scenario 1: the minimum value is greater than the preset value

Since the minimum value is larger than the preset value, the bandwidths required by the time periods corresponding to the 2n+1 time intervals are larger than the preset value, so that it can be determined that the current bandwidths of the target clients cannot meet the use requirements of the time periods corresponding to the 2n+1 time intervals, the bandwidths of the target clients need to be increased, and the adjustment direction of the number of time slots is determined to be increased.

Application scenario 2: the maximum value is smaller than the value after the preset attenuation

The current bandwidth of the target client decreases with time, so that the bandwidth actually available at a time of a certain time interval of 2n+1 time intervals is smaller than the preset value without adjusting the bandwidth of the target client.

Based on the above reasons, in the embodiment of the present application, the maximum value is not compared with the preset value, but is compared with the value attenuated by the preset value, so as to accurately determine whether the current bandwidth of the target client meets the use requirement of the time period corresponding to 2n+1 time intervals.

Because the maximum value is smaller than the value after the attenuation of the preset value, the bandwidths required by the time periods corresponding to the 2n+1 time intervals are smaller than the value after the attenuation of the preset value, so that the current bandwidths of the target clients can be determined to not only meet the use requirements of the time periods corresponding to the 2n+1 time intervals, but also have partial surplus, the bandwidths of the target clients need to be reduced, and the adjustment direction of the number of time slots is determined to be reduced.

Application scenario 3: the minimum value is smaller than the preset value and the maximum value is larger than the preset value

And because the minimum value is smaller than the preset value and the maximum value is larger than the preset value, the bandwidths required by one part of time periods corresponding to 2n+1 time intervals are larger than the preset value, and the bandwidths required by the other part of time periods corresponding to 2n+1 time intervals are smaller than the preset value. Wherein:

For the part of time periods corresponding to the 2n+1 time intervals, the required bandwidth is larger than the preset value, and the fact that the current bandwidth of the target client cannot meet the use requirement of the part of time periods corresponding to the 2n+1 time intervals can be determined, so that the bandwidth needs to be increased for the target client in the part of time periods corresponding to the 2n+1 time intervals, and the adjustment direction of the number of time slots is determined to be increased;

For the other part of time period corresponding to the 2n+1 time intervals, the required bandwidth is smaller than the preset value, it can be determined that the current bandwidth of the target client cannot meet the use requirement of the part of time period corresponding to the 2n+1 time intervals, so that the current bandwidth of the target client is determined to not only meet the use requirement of the other part of time period corresponding to the 2n+1 time intervals, but also have partial surplus, therefore, the bandwidth needs to be reduced for the target client in the other part of time period corresponding to the 2n+1 time intervals, and the adjustment direction of the number of time slots is determined to be reduced.

Because the application scene has the use requirements of reducing the number of time slots and increasing the number of time slots, in order to simplify the complexity of bandwidth adjustment operation, the target client is ensured to have enough bandwidth in all time periods corresponding to 2n+1 time intervals, the bandwidth can be determined to be increased for the target client in all time periods corresponding to 2n+1 time intervals, and the adjustment direction of the number of time slots is determined to be increased.

In the above 3 application scenarios, the adjustment direction of the number of time slots in each application scenario is given, and the number of time slots to be adjusted in the 3 application scenarios is described below:

In the embodiment of the application, the number of the time slots is adjusted according to the ratio of the difference value of the bandwidths in each application scene to the bandwidth value of the time slot. Since the bandwidth value of the slot is a fixed value, the following describes the bandwidth difference in each application scenario:

application scenario 1: the minimum value is greater than the preset value

Because the minimum value and the maximum value have a numerical difference, the adjustment information of the number of time slots determined according to the difference between the minimum value and the preset value may not meet the use in the time period corresponding to the maximum value, and therefore the numerical value of the number of time slots can be determined according to the difference between the minimum value and the preset value, so as to obtain a first numerical value; and determining the number of the time slots according to the difference between the maximum value and the preset value to obtain a second number, and taking the first number or the second number as the number of the time slots to be adjusted in the time period corresponding to any time interval of 2n+1 time intervals according to the actual management requirement.

The management requirement may be 2n+1 bandwidth adjustment times in time intervals, where:

If the bandwidth adjustment number is one in 2n+1 time intervals, the second value is taken as the total number of time slots increased in 2n+1 time intervals, so as to ensure that the target client has enough bandwidth in all time slots corresponding to 2n+1 time intervals.

If the bandwidth adjustment number is at least twice in 2n+1 time intervals, the first value or the second value is taken as the total number of increased time slots in at least one time interval according to the predicted value of 2n+1 time intervals.

Specifically, the time periods corresponding to 2n+1 time intervals are divided into two types of time periods, wherein the first type of time period uses a first value, and the second type of time period uses a second value. The values used can be determined in terms of the distribution of the two types of time periods.

If the time periods corresponding to the 2n+1 time intervals are all the time periods of the first type in a certain continuous time period, using a first numerical value in the continuous time period; similarly, the second value is used for the continuous time period, and the first value is used for the continuous time period.

If there are both the first type of time period and the second type of time period within the certain continuous time period, the second value is used within the continuous time period to ensure that the target client has sufficient bandwidth for the time period corresponding to the 2n+1 time intervals.

Application scenario 2: the maximum value is smaller than the value after the preset attenuation

Since the value after the attenuation of the preset value is smaller than the preset value, the difference between the value after the attenuation of the preset value and the maximum value is smaller than the difference between the preset value and the maximum value, the number of time slots determined by the former is possibly smaller than the number of time slots determined by the latter, and the use requirement of the time period corresponding to the maximum value may not be met. Therefore, unlike the value attenuated by the preset value in the adjustment direction of determining the number of time slots, when determining the number of time slots to be adjusted, the value used is the preset value instead of the value attenuated by the preset value, that is, the difference value of the bandwidths in the application scene is the difference value between the preset value and the maximum value, so as to ensure that the target client has enough bandwidth in the time period corresponding to 2n+1 time intervals.

Application scenario 3: the minimum value is smaller than the preset value and the maximum value is larger than the preset value

In the application scene, in order to ensure that the target client has enough bandwidth in the time period corresponding to the 2n+1 time intervals, the maximum value is taken as the bandwidth value required in the time period corresponding to the 2n+1 time intervals, so that the difference value of the bandwidths in the application scene is the difference value between the maximum value and the preset value.

In the above 3 application scenarios, the ratio of the difference value of the bandwidths in each application scenario to the bandwidth value of the slot may not be an integer value. Since FlexE networks are allocated in units of time slots, when the ratio is not an integer value, the ratio needs to be adjusted to obtain the integer value corresponding to the ratio.

Specifically, when the adjustment information is that the number of time slots is increased, the total number of the time slots is obtained by performing an upward rounding operation on the ratio between the difference value and the bandwidth value of the time slots, so that the target client can obtain a part of bandwidth more on the basis of the required bandwidth, on one hand, the allocation requirement of the time slots is met, and on the other hand, the bandwidth obtained more by the target client can meet the temporary use requirement of the target client.

When the adjustment information is that the number of time slots is reduced, the total number of the time slots is obtained by performing downward rounding operation on the ratio between the difference value and the bandwidth value of the time slots, so that the target client can also subtract a part of bandwidth less on the basis of the required bandwidth, on one hand, the allocation requirement of the time slots is met, and on the other hand, the bandwidth subtracted less by the target client can meet the temporary use requirement of the target client.

Based on the above description, taking the current bandwidth value of the target client as P, the bandwidth value of the time slot as Q, and the bandwidth reduction factor as a as an example, the description is given:

Selecting a maximum value MAX and a minimum value MIN from the predicted values of 2n+1 time intervals;

if MIN is greater than P, the bandwidth size to be adjusted is

If MAX is less than a.P, then for bandwidth reduced scenarios, the bandwidth size that needs to be adjusted is

If MIN < P < MAX, then this indicates that there is an increased bandwidth condition, which requires consideration of the increased bandwidth, the increased bandwidth size

The bandwidth is not adjusted in other scenes;

Wherein + represents a downward rounding and + represents an upward rounding.

Taking Q as 5G and a as 0.2 as an example;

Condition 1: the current bandwidth value of the target client is 10G, the predicted value of the 3 time intervals is sequentially 13.6G for the target client in the 1 st time interval, 15.7G for the target client in the 2 nd time interval, and 19.0G for the target client in the 3 rd time interval.

Under condition 1, the bandwidth of 10G is directly allocated to avoid multiple adjustment, so that the adjustment information is determined to be increased by 2 time slots

Condition 2: the current bandwidth value of the target client is 80G, the predicted values of the 3 time intervals are sequentially 15G for the target client in the 1 st time interval, 10G for the target client in the 2 nd time interval, and 12G for the target client in the 3 rd time interval.

Under condition 2, the bandwidth of 65G can be directly reduced, and thus, the adjustment information is determined to be reduced by 13 slots.

The above description is made on how to acquire the adjustment information, which needs to be sent to the target client to complete the adjustment of the bandwidth, so the following description is made on how to send the adjustment information:

In one exemplary embodiment, the adjustment information is sent through a reserved field on FlexE overhead frames.

According to the definition of OIF-02.1, the shim layer defines the mapping relationship between overhead frames (overhead frames) to provide in-band management channels to carry configuration management information between two FlexE client, link negotiations, and determination client, group, slot. Because FlexE overhead frames have the function of determining the mapping relation between client, group, slot, the FlexE overhead frames are utilized to transmit the adjustment information, so that a client can acquire bandwidth adjustment information while determining the mapping relation, the analysis of bandwidth information by a target client is facilitated, and the efficiency of bandwidth adjustment is improved.

Further, the reserved field is located in the FlexE nd overhead block and the 3 rd overhead block in the overhead frame.

One overhead frame comprises 32 overhead frames, one overhead frame comprises 8 overhead blocks, the first 3 overhead blocks in the overhead frame carry the mapping relation between the corresponding client, group, slot on FlexE overhead blocks, and the last 5 overhead blocks are used for carrying management message information, such as DCN, 1588, and the like. Wherein, in the 2 nd overhead block and the 3 rd overhead block, there are reserved fields of 47 bits (bit 17-bit 63) and 13 bits (bit 35-bit 47) respectively, and bandwidth adjustment in FlexE networks can be realized by using the fields at the two positions.

Further, the reserved field is represented by 2 bits to increase, decrease or not adjust, and at least 2 bits to represent the value of the adjusted number of time slots.

Taking FlexE Group consisting of 100G PHY as an example, the reserved field in the 3 rd overhead block may be directly used for adjustment, and a total of 13 bits may be used as an adjustment value (00 represents no adjustment, 10 represents increasing bandwidth, and 01 represents decreasing bandwidth), and the next 11 bits may be used as an indication of the number of timeslots to be adjusted, for example, a value of 3 represents 3 timeslots to be adjusted, and 10 represents 10 timeslots to be adjusted. In a larger bundling bandwidth and fine-grained slot scenario, more reserved fields may be utilized for adjustment.

According to the method provided by the embodiment of the application, bandwidth adjustment is performed based on the deep learning model in FlexE networks, so that 'active' adjustment and fine adjustment are realized, the purposes of more flexible and intelligent operation and maintenance management and control are achieved, the overhead of the system is reduced, the dependence on manpower is reduced, and the cost is saved.

Fig. 2 is a schematic structural diagram of a device for adjusting bandwidth in FlexE networks according to an embodiment of the present application. As shown in fig. 2, the apparatus includes:

an obtaining module 201, configured to obtain a predicted value of a bandwidth required by a target client;

a determining module 202, configured to determine, under a condition that a bandwidth value of a time slot is a fixed value, adjustment information of a number of time slots corresponding to the target client according to the predicted value and a preset value of a current bandwidth of the target client;

And the sending module 203 is configured to send the adjustment information.

The device provided by the embodiment of the application realizes the automatic adjustment of the bandwidth of the target client by determining the adjustment information of the number of the time slots corresponding to the target client, and does not need manual adjustment; in addition, the adjustment information of the number of time slots is determined through the predicted value and the preset value of the current bandwidth, so that the problem of frequent adjustment caused by fluctuation near the threshold value is avoided, the system overhead is reduced, and the running stability is improved.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable 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, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term "computer storage media" includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

Claims (10)

1. A method for adjusting bandwidth in a FlexE network, comprising:

Obtaining a predicted value of the bandwidth required by a target client;

Under the condition that the bandwidth value of the time slot is a fixed value, determining the adjustment information of the number of the time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client;

And sending the adjustment information.

2. The method according to claim 1, characterized in that:

And obtaining a predicted value of the bandwidth required by the target customer by utilizing an artificial intelligent model, wherein sample data used by the artificial intelligent model are time sequences, and each time sequence records configuration data of FlexE networks, traffic data characteristics of the customer and operation environment information in respective time intervals, wherein the operation environment information comprises at least one of position information of equipment in a network topological graph, weather and holidays.

3. The method according to claim 1 or 2, characterized in that:

The predicted value comprises a predicted value of each of 2n+1 time intervals, wherein n is an integer greater than or equal to 1;

wherein the determining, according to the predicted value and the value of the current bandwidth of the target client in the target FlexE group, the adjustment information of the number of time slots corresponding to the target client in the target FlexE group includes:

Obtaining a maximum value and a minimum value from predicted values corresponding to 2n+1 time intervals;

And determining the adjustment information according to the maximum value, the minimum value and the preset value.

4. A method according to claim 3, wherein said determining said adjustment information based on said maximum value, said minimum value and said preset value comprises:

When the minimum value is larger than the preset value, determining that the adjustment information is the number of the increased time slots, and determining the total number of the adjusted time slots according to the difference value between one of the minimum value and the maximum value and the preset value;

When the maximum value is smaller than the value of the preset value after attenuation, determining that the adjustment information is the number of the reduced time slots, and determining the total number of the adjusted time slots according to the difference between the preset value and the maximum value;

And when the minimum value is smaller than the preset value and the maximum value is larger than the preset value, determining that the adjustment information is the number of the increased time slots, and determining the total number of the adjusted time slots according to the difference value between the maximum value and the preset value.

5. The method of claim 4, wherein the determining of the total number of increased time slots when the minimum value is greater than the preset value comprises:

Determining the number of time slots according to the difference between the minimum value and the preset value to obtain a first value; and determining the numerical value of the number of time slots according to the difference between the maximum value and the preset value to obtain a second numerical value;

If the bandwidth adjustment times are one time in 2n+1 time intervals, the second value is taken as the total number of the time slots increased in 2n+1 time intervals;

if the bandwidth adjustment number is at least twice in 2n+1 time intervals, the first value or the second value is taken as the total number of increased time slots in at least one time interval according to the predicted value of 2n+1 time intervals.

6. The method according to claim 4, wherein:

the number of the time slots is determined according to the ratio of the respective difference value to the bandwidth value of the time slot; wherein:

When the adjustment information is that the number of time slots is increased, the total number of the time slots is obtained by carrying out upward rounding operation on the ratio between the difference value and the bandwidth value of the time slots;

when the adjustment information is to reduce the number of time slots, the adjusted total number of time slots is obtained by performing downward rounding operation on the ratio between the difference value and the bandwidth value of the time slots.

7. The method of any of claims 1 to 6, wherein the adjustment information is sent through a reserved field on a FlexE overhead frame.

8. The method of claim 7 wherein the reserved field is located in a2 nd overhead block and a 3 rd overhead block in a FlexE overhead frame, wherein at least one of the 2 nd overhead block and the 3 rd overhead block carries a mapping relationship between clients, flexE groups, slots.

9. The method of claim 7, wherein the reserved field comprises an adjustment direction field and a slot number field; the adjustment direction field is used for recording the adjustment direction of the bandwidth; the time slot number field is used for recording the numerical value of the adjusted time slot number.

10. An apparatus for adjusting bandwidth in a FlexE network, comprising:

the acquisition module is used for acquiring the predicted value of the bandwidth required by the target client;

the determining module is used for determining the adjusting information of the number of the time slots corresponding to the target client according to the predicted value and the preset value of the current bandwidth of the target client under the condition that the bandwidth value of the time slots is a fixed value;

And the sending module is used for sending the adjustment information.