FlexE-based bearer network network slicing management optimization method, device and medium

Abstract

The present invention relates to a method, device and storage medium for optimizing the management of bearer network slices based on FlexE. The method comprises: obtaining a service request queue, predicting according to the mapped bandwidth of each service request in the service request queue, and obtaining a predicted service bandwidth; in response to the predicted service bandwidth not matching the FlexE port bandwidth of the corresponding network slice, obtaining a target time slot according to the combination of the fixed time slot and the temporary time slot, and updating the FlexE port bandwidth of the network slice according to the bandwidth of the target time slot; and processing service requests according to the FlexE port bandwidth. According to an embodiment of the present invention, in general, it is executed in a fixed time slot allocation mode to avoid reducing the efficiency of time slot allocation, and at the same time, the time slot combination of the fixed time slot and the temporary time slot is dynamically determined according to the service request to adjust the FlexE port bandwidth, thereby improving bandwidth utilization.

Description

Technical Field

[0001] The present invention generally relates to the field of communications. More specifically, the present invention relates to a method, device and medium for optimizing network slicing management of a bearer network based on FlexE. Background Art

[0002] Flexible Ethernet (FlexE) is an interface technology for bearer networks to achieve service isolation and network slicing. FlexE can divide the physical layer (PHY) of a port into multiple time slots, and perform operations such as bundling and channelization on the time slots to achieve flexible service bandwidth support. Network slicing is to divide service nodes into different service networks under the hardware conditions of the existing network, so as to be applied to different service scenarios. At present, the physical layer of a port is usually divided into several time slots with fixed bandwidth. The time slot set that supports the network slicing is determined based on the actual bandwidth requirements of the services in the network slicing.

[0003] However, due to the complexity of business scenarios, the actual bandwidth demand of services in network slicing fluctuates. The use of fixed time slot sets to support network slicing may result in low bandwidth utilization or excessive latency. At the same time, in order to meet the bandwidth requirements of complex business scenarios and improve bandwidth utilization, the bandwidth of the divided time slots can be as small as possible, but time slots with too small granularity will reduce the efficiency of time slot allocation, thereby affecting the efficiency of business processing. Therefore, how to optimize network slicing management to improve bandwidth utilization and business processing efficiency has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a FlexE-based bearer network network slicing management optimization method for taking into account both bandwidth utilization and service processing efficiency. The present invention also provides a FlexE-based bearer network network slicing management optimization device and a storage medium.

[0005] To solve the above problems, according to a first aspect of the present invention, the following technical solution is provided: a FlexE-based bearer network network slice management optimization method, wherein the FlexE-based bearer network has a fixed time slot bandwidth and a temporary time slot bandwidth, each network slice has a corresponding FlexE port bandwidth, and each service request has a corresponding mapping bandwidth; the method comprises: obtaining a service request queue, predicting according to the mapping bandwidth of each service request in the service request queue, and obtaining a predicted service bandwidth; in response to the predicted service bandwidth not matching the FlexE port bandwidth of the corresponding network slice, obtaining a target time slot according to the combination of the fixed time slot and the temporary time slot; and processing the service request according to the FlexE port bandwidth.

[0006] In one embodiment, the method further includes: updating the FlexE port bandwidth of the network slice according to the bandwidth of the target time slot.

[0007] In one embodiment, at a preset time point, the FlexE port bandwidth of the network slice is updated using a target time slot; wherein the preset time point is a time point when the previous service request corresponding to the service bandwidth is predicted to be processed.

[0008] In one embodiment, the mismatch between the predicted service bandwidth and the FlexE port bandwidth of the corresponding network slice includes: a difference between one or more consecutive predicted service bandwidths and the FlexE port bandwidth is outside a set range.

[0009] In one embodiment, the predicted service bandwidth includes accuracy, and in response to the accuracy of the current predicted service bandwidth being not higher than an accuracy threshold, the FlexE port bandwidth is not updated.

[0010] In one embodiment, the predicted service bandwidth includes a priority, and in response to the priority of the current predicted service bandwidth being not higher than a priority threshold, the FlexE port bandwidth is not updated.

[0011] In one embodiment, the service type, service content, the FlexE port bandwidth, the mapped bandwidth, the fixed time slot bandwidth and the temporary time slot bandwidth are stored in the bandwidth mapping table.

[0012] In one embodiment, the fixed time slot bandwidth is the greatest common divisor of the FlexE port bandwidths of most service requests as the fixed time slot bandwidth, and the greatest common divisor of all service requests is used as the temporary time slot bandwidth; wherein the majority of service requests refer to service requests corresponding to network slices whose service proportion is higher than the set value.

[0013] In one embodiment, the predicted service bandwidth is obtained through a linear model.

[0014] In a second aspect of an embodiment of the present invention, a FlexE-based bearer network network slicing management optimization device is provided, comprising: a processor configured to execute program instructions; and a memory configured to store the program instructions, and when the program instructions are loaded and executed by the processor, the processor executes the method described in any one of the first aspects of the embodiment of the present invention.

[0015] In a third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which program instructions are stored. When the program instructions are loaded and executed by a processor, the processor executes the method according to any one of the first aspects of the embodiments of the present invention.

[0016] According to an embodiment of the present invention, a fixed time slot allocation method is generally used to avoid reducing the efficiency of time slot allocation. At the same time, the time slot combination of fixed time slots and temporary time slots is dynamically determined according to service requests to adjust the FlexE port bandwidth, thereby improving bandwidth utilization and service processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0018] Figure 1 A schematic diagram of a process according to an embodiment of the present invention is shown;

[0019] Figure 2 It shows a way to partition a logical network;

[0020] Figure 3 A schematic diagram of the process of obtaining predicted service bandwidth based on service request queues is shown;

[0021] Figure 4 A schematic block diagram of a FlexE-based bearer network slicing management optimization device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Those skilled in the art should know that the embodiments described below are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The method according to the present invention includes steps S101 to S104, which are described in detail below.

[0024] First, in step S101, a bandwidth mapping table is configured and stored. The bandwidth mapping table involves many concepts, which are described one by one below.

[0025] Figure 2 A logical network division method, namely, network slicing, is shown, which includes logical network A and logical network B. Logical network A can be used to process service type A, and logical network B can be used to process service type B. Nodes are combined into logical networks according to service types. Therefore, different logical networks are used to meet the differentiated requirements of different service types for network capabilities. It should be noted that the nodes in different logical networks can be different or the same (for example, Figure 2 In the example, some nodes are both nodes of logical network A and nodes of logical network B).

[0026] That is to say, the logical network includes multiple network nodes. According to the different services processed, different nodes constitute a logical network of the corresponding service type, that is, a network slice. Among them, the above-mentioned nodes may refer to network nodes in the basic network facilities; in a logical network (network slice), the nodes can be used to process the corresponding service types. The above-mentioned service types can be divided into: video service, encryption service, data service, etc.; of course, other division methods can also be used. Specifically, the deployment process of the logical network (network slice) includes creating slice interfaces, configuring slice bandwidth, configuring VPNs and tunnels, etc., and its deployment process can be implemented through existing technologies, so it will not be repeated in this article.

[0027] Table 1

[0028] Business Type Business Content Latency requirements Mapping bandwidth FlexE port bandwidth A A1 T1 X1 X3 A A2 T2 X2 X3 A A3 T3 X3(Max) X3 B B1 T4 X4 X6 B B2 T5 X5 X6 B B3 T6 X6(Max) X6 C C1 T7 X7(Max) X7 C C2 T8 X8 X7

[0029] Table 2 shows a bandwidth mapping table. The bandwidth mapping table is preset in the network controller and can be implemented according to the prior art. According to the bandwidth mapping table, different services are allocated different FlexE ports.

[0030] For example, logical network A corresponds to service type A, logical network B corresponds to service type B, and logical network C corresponds to service type C. The bandwidth mapping table shows the correspondence between different service types, service contents, latency requirements and mapped bandwidths.

[0031] The second entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type A, service content A1 and delay requirement T1 is X1; the third entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type A, service content A2 and delay requirement T2 is X2; the fourth entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type A, service content A3 and delay requirement T3 is X3. Similarly, the fifth entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type B, service content B1 and delay requirement T4 is X4; the sixth entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type B, service content B2 and delay requirement T5 is X5; the seventh entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type B, service content B3 and delay requirement T6 is X6; the eighth entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type C, service content C1 and delay requirement T7 is X7; the ninth entry in Table 2 indicates that the mapping bandwidth corresponding to the service with service type C, service content C2 and delay requirement T8 is X8.

[0032] Wherein, T represents a delay value, and the delay values ​​represented by T1 to T8 may be the same or different. X represents a bandwidth, and the bandwidth values ​​represented by X1 to X8 may be the same or different.

[0033] Furthermore, in addition to allocating mapping bandwidths for different services, the bandwidth mapping table also allocates corresponding FlexE ports for the services. As shown in Table 1, the FlexE port bandwidth is also shown, where the FlexE port refers to a port at the physical layer, which mainly includes information about the FlexE port bandwidth. In this embodiment, the FlexE port bandwidth is equal to: the maximum value of the mapping bandwidths among multiple services of the same service type.

[0034] The significance of FlexE port bandwidth is that the controller can allocate time slots according to the FlexE port bandwidth. Since service requests of the same service type and different contents may correspond to different mapping bandwidths, the maximum mapping bandwidth of each service request in the service type is determined to be the FlexE port bandwidth, and time slots are allocated based on this FlexE port bandwidth, which can ensure that the network slice can guarantee the bandwidth for all service processing, while avoiding time slots with too small granularity, which will reduce the efficiency of time slot allocation, thereby affecting the efficiency of service processing.

[0035] For example, in Table 1, among services A1, A2, and A3, the mapping bandwidth X3 corresponding to A3 is the largest, so X3 is used as the FlexE port bandwidth of network slice A. Among services B1, B2, and B3, the mapping bandwidth X6 corresponding to B3 is the largest, so X6 is used as the FlexE port bandwidth of network slice B. Among services C1 and C2, the mapping bandwidth X7 corresponding to C1 is the largest, so X7 is used as the FlexE port bandwidth of network slice C.

[0036] Table 2

[0037]

[0038] Furthermore, Table 2 is a supplement to Table 1 and also belongs to the preset content, which is used to further determine the fixed time slot bandwidth and the temporary time slot bandwidth. It should be noted that Table 2 and Table 1 can be connected together, and Table 2 and Table 1 are described separately for the purpose of clarity. As shown in Table 2, service type A includes A1 to A100 service requests, service type B includes B1 to B50 service requests, and service type C includes C and C2 services. Moreover, Tables 1 and 2 list various types of common services. That is to say, for example, in Table 2, there are many service requests for service type A and service type B, while there are fewer service requests for service type C.

[0039] It is understandable that the fixed time slot bandwidth and temporary time slot bandwidth of all network slices are the same. The following first describes how to obtain the fixed time slot bandwidth and the temporary time slot bandwidth.

[0040] Considering the imbalance of service requests, the present invention expects that fixed time slots can cover most service requests, and temporary time slots can cover a small number of service requests. That is, the fixed time slot bandwidth may refer to the bandwidth of the basic time slot divided by FlexE, and the basic time slot can be used to provide bandwidth for the common majority of service requests, and the temporary time slot bandwidth may refer to the bandwidth of the temporary time slot divided by FlexE, and the temporary time slot can be used to provide bandwidth for the uncommon minority of service requests. The division may refer to the physical layer division of FlexE, and the fixed time slot corresponds to the fixed time slot bandwidth, and the temporary time slot corresponds to the temporary time slot bandwidth.

[0041] Based on the above considerations, the greatest common divisor of the FlexE port bandwidth of most service requests can be used as the fixed time slot bandwidth, and the greatest common divisor of all service requests can be used as the temporary time slot bandwidth. The majority of service requests refer to service requests corresponding to network slices whose service proportion is higher than the set value. As shown in Table 2, Class A service requests and Class B service requests belong to the majority of service requests, and Class C service requests belong to the minority of service requests. Assuming X3=40, X6=100, the fixed time slot bandwidth is equal to the greatest common divisor of the FlexE port bandwidth (X3 and X4) of most service requests; the temporary time slot bandwidth is equal to the greatest common divisor of the mapped bandwidth of all service requests (X1~X100, B1~B50, C1~C2), for example, equal to 5.

[0042] The above introduces the relevant concepts of the bandwidth mapping table. The following will further describe the method steps of the present invention.

[0043] In step S102, a service request queue is obtained, and a prediction is performed according to the mapped bandwidth of each service request in the service request queue to obtain a predicted service bandwidth.

[0044] Figure 3 The schematic diagram of the process of obtaining the predicted service bandwidth based on the service request queue is shown. Among them, in a network slice, the service request queue can be in the form of a queue, in which service requests are stored, and the length of the queue is fixed. As time goes by, old service requests are removed from the queue and new service requests enter the queue. Based on this, the service request queue reflects the situation of multiple service requests within a period of time before the current moment. It can be understood that since each service request has its own mapped bandwidth (as shown in Table 1), the bandwidth of the next service request can be predicted based on all mapped bandwidths in the service request queue, that is, the predicted service bandwidth. For example, in the network slice corresponding to service type A, the bandwidth of the service request at the next moment can be predicted.

[0045] In the present invention, various methods in the prior art can be used to obtain the predicted service bandwidth. For example, a linear regression method can be used for prediction. The linear regression can establish a linear model and predict the next value based on the linear model.

[0046] As an example, the linear model representation can be y=w1x1+w2x2+…+w S x S +b, where x can refer to an element in the input, w can refer to the coefficient corresponding to the element, b can refer to the bias, and y represents the predicted service bandwidth. The input of the linear function is determined in the form of a sliding window. Suppose the length of the sliding window is S, the step size is 1, and the service bandwidth queue length is L. The initial input intercepted by the sliding window is [E L-S+1 , E L-S+2 , ..., E L ], where E L-S+1 Indicates the mapping bandwidth corresponding to the L-S+1th service request in the service bandwidth queue. The initial output is E L+1 , move the sliding window to the right by the step size to obtain the second input [E L-S+2 , E L-S+3 , ..., E L+1 ], and the second output E is obtained by the same linear function calculation. L+2 , repeatedly move the sliding window until a preset number of outputs is obtained. Let the preset number be Q. Then, when E is obtained L+Q Stop when.

[0047] The above is only an example of a linear model. In other embodiments, various other types of methods may be used to predict service bandwidth, such as a decision tree algorithm and a random forest algorithm, and the present invention is not limited thereto.

[0048] According to step S102, the predicted service bandwidth is acquired before the next actually received service request, thereby gaining time for adjusting the FlexE port bandwidth in subsequent steps.

[0049] In step S103, when it is detected that the predicted service bandwidth does not match the FlexE port bandwidth of the corresponding network slice, the target time slot is obtained by combining the temporary time slot bandwidth and the fixed time slot bandwidth, and the FlexE port bandwidth of the corresponding network slice is updated.

[0050] The principle of step S103 is: for a network slice, under normal circumstances (when the predicted service bandwidth matches the FlexE port bandwidth of the corresponding network slice), the received service request is processed according to the time slot allocation method corresponding to the FlexE port bandwidth. Since the FlexE port bandwidth is the largest mapping bandwidth in the network slice, the efficiency of time slot allocation is high; at the same time, in special circumstances (when the predicted service bandwidth does not match the FlexE port bandwidth of the corresponding network slice), the target time slot is recombined and the FlexE port bandwidth of the corresponding network slice is updated. Based on this, the FlexE port bandwidth is changed, and when a new service request is received, the time slot can be allocated according to the new FlexE port bandwidth. For example, the granularity of the new time slot allocation can be smaller, thereby improving bandwidth utilization.

[0051] That is to say, under normal circumstances, the FlexE port bandwidth does not need to be changed to ensure the efficiency of time slot allocation. In special circumstances (for example, when the mapping bandwidth of the next service request is predicted to be significantly different from the FlexE port bandwidth), the FlexE port bandwidth is changed to ensure bandwidth utilization.

[0052] As an example, for network slice A, its FlexE port bandwidth is 40; the predicted service bandwidth is around 40, for example, 30 to 40 (that is, the difference between the predicted service bandwidth and the FlexE port bandwidth is within the set range), then the FlexE port bandwidth will not be changed. If the predicted service bandwidth is far from 40, for example, 25 (between 5 and 30, that is, the difference between the predicted service bandwidth and the FlexE port bandwidth is outside the set range), then according to the temporary time slot bandwidth (5) and the fixed time slot bandwidth (20), the target time slot is combined, and the target time slot is equal to 2 temporary time slots + 1 fixed time slot. At the same time, the FlexE port bandwidth of the corresponding network slice A is updated. According to an embodiment of the present invention, in general, it is executed in a fixed time slot allocation mode to avoid reducing the efficiency of time slot allocation. At the same time, the time slot combination of fixed time slots and temporary time slots is dynamically determined according to the service request to obtain the optimal time slot bandwidth division result to adjust the FlexE port bandwidth, thereby improving bandwidth utilization.

[0053] Among them, the predicted service bandwidth does not match the FlexE port bandwidth of the corresponding network slice. It may mean that the gap between multiple consecutive predicted service bandwidths and the FlexE port bandwidth is large. At this time, the FlexE port bandwidth is changed to avoid frequent adjustment of the FlexE port bandwidth.

[0054] Specifically, the target time slot combination method can be obtained in the following manner: perform a modulo calculation on the predicted service bandwidth and the fixed time slot bandwidth to obtain a quotient and a remainder, determine the number of required fixed time slots by the value of the quotient, determine the number of required temporary time slots by the quotient of the remainder and the temporary time slot bandwidth, select the corresponding time slots according to the number of required fixed time slots and the number of required temporary time slots for combination, and obtain the target time slot, which corresponds to the bandwidth of the target time slot. At a preset time point, the target time slot is used to update the FlexE port bandwidth of the network slice to which it belongs. In this embodiment, the preset time point may be the time point when the previous service request corresponding to the service request of the predicted service bandwidth is processed.

[0055] In one embodiment, the preset time point may also be determined according to the reception time of the service request corresponding to the predicted service bandwidth and the predetermined configuration duration. It should be noted that the FlexE port bandwidth should be updated after the current service request is processed to avoid the update process affecting service processing.

[0056] Furthermore, considering that the predicted service bandwidth may be different from the mapping bandwidth of the service request actually received, that is, the prediction may be inaccurate, it is also possible to consider improving the above method. As an example, an accuracy attribute can be added to the predicted service bandwidth. If the accuracy of the current predicted service bandwidth is higher than the accuracy threshold, step S103 is executed, otherwise, step S103 is not executed. At the same time, when the service request is actually received, the accuracy value of the predicted service bandwidth is adjusted. For example, if the actually received service request matches the predicted service bandwidth, the accuracy value of the predicted service bandwidth is increased, otherwise the accuracy value of the predicted service bandwidth is reduced.

[0057] Furthermore, a priority attribute may be added to the predicted service bandwidth, for example, a priority value may be assigned, and the higher the priority, the larger the corresponding value. If the priority value of the current predicted service bandwidth is higher than the priority threshold, step S103 is executed, otherwise, step S103 is not executed.

[0058] Finally, in step S104, the newly received service request is processed according to the FlexE port bandwidth. The FlexE port bandwidth is updated or not updated.

[0059] The above describes the method of the exemplary embodiment of the present invention. Next, refer to Figure 4 A FlexE-based bearer network slice management and optimization device according to an exemplary embodiment of the present invention is described.

[0060] Figure 4 The following is a schematic block diagram of a FlexE-based bearer network slice management optimization device according to an embodiment of the present invention. Figure 4As shown, the device may include a processor 401 and a memory 402. The memory 402 stores computer instructions for executing the method described in the embodiment of the present invention. When the computer instructions are executed by the processor 401, the device executes the method described above.

[0061] According to another aspect of the present invention, the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions implement the method described above when executed by a processor.

[0062] It should be noted that although several steps of the FlexE-based bearer network slicing management optimization method are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more steps described above can be concretized in one step. Conversely, the features and functions of one step described above can be further divided into multiple steps to be concretized.

[0063] In the above description of this specification, unless otherwise clearly specified and limited, the terms "fixed", "installed", "connected" or "connected" should be understood in a broad sense. For example, with regard to the term "connection", it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal connection of two elements or the interaction relationship between two elements. Therefore, unless otherwise clearly defined in this specification, those skilled in the art can understand the specific meanings of the above terms in the present invention according to the specific circumstances.

[0064] According to the above description of this specification, those skilled in the art can also understand that the terms "first" or "second" used in this specification to refer to numbers or ordinals are only used for descriptive purposes, and cannot be understood as explicitly or implicitly indicating relative importance or implicitly indicating the number of technical features indicated. Therefore, the feature defined as "first" or "second" can explicitly or implicitly include at least one of the features. In the description of this specification, the meaning of "plurality" is at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0065] Although this specification has shown and described a plurality of embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present invention. It should be understood that in the process of practicing the present invention, various alternatives to the embodiments of the present invention described herein may be adopted. The attached claims are intended to define the scope of protection of the present invention, and therefore cover the modular composition, equivalent or alternatives within the scope of protection of these claims.

Claims

1. A FlexE-based bearer network slicing management optimization method, characterized in that: in, The FlexE-based bearer network has a fixed time slot bandwidth and a temporary time slot bandwidth, each network slice has a corresponding FlexE port bandwidth, and each service request has a corresponding mapping bandwidth; the method includes: Obtain a service request queue, and make a prediction based on the mapped bandwidth of each service request in the service request queue to obtain a predicted service bandwidth; In response to the predicted service bandwidth not matching the FlexE port bandwidth of the corresponding network slice, obtaining a target time slot according to the combination of the fixed time slot and the temporary time slot, and updating the FlexE port bandwidth of the network slice according to the bandwidth of the target time slot; Processing a service request according to the FlexE port bandwidth; The service type, service content, the FlexE port bandwidth, the mapped bandwidth, the fixed timeslot bandwidth and the temporary timeslot bandwidth are stored in a bandwidth mapping table; The fixed time slot bandwidth is the greatest common divisor of the FlexE port bandwidths of most service requests, and the greatest common divisor of all service requests is used as the temporary time slot bandwidth; wherein the majority of service requests refer to service requests corresponding to network slices whose service proportion is higher than the set value.

2. The FlexE-based bearer network slicing management optimization method according to claim 1, characterized in that: At a preset time point, the bandwidth of the target time slot is used to update the FlexE port bandwidth of the network slice, wherein the preset time point is a time point when the previous service request corresponding to the service bandwidth is predicted to be processed.

3. The FlexE-based bearer network slicing management optimization method according to claim 2, characterized in that: The mismatch between the predicted service bandwidth and the FlexE port bandwidth of the corresponding network slice includes: a difference between one or more consecutive predicted service bandwidths and the FlexE port bandwidth is outside a set range.

4. The FlexE-based bearer network slicing management optimization method according to claim 3, characterized in that: The predicted service bandwidth includes accuracy, and in response to the accuracy of the current predicted service bandwidth being not higher than an accuracy threshold, the FlexE port bandwidth is not updated.

5. The FlexE-based bearer network slicing management optimization method according to claim 3, characterized in that: The predicted service bandwidth includes a priority, and in response to the priority of the current predicted service bandwidth being not higher than a priority threshold, the FlexE port bandwidth is not updated.

6. The method for optimizing bearer network slicing management based on FlexE according to any one of claims 1 to 5, characterized in that: The predicted service bandwidth is obtained through a linear model.

7. A FlexE-based bearer network slicing management and optimization device, characterized in that: include: a processor configured to execute program instructions; as well as A memory configured to store the program instructions, which, when loaded and executed by the processor, enables the processor to perform the method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: Program instructions are stored therein, and when the program instructions are loaded and executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

Images