CN113438681A - Feasibility evaluation method and device of network slice and computing equipment - Google Patents
Feasibility evaluation method and device of network slice and computing equipment Download PDFInfo
- Publication number
- CN113438681A CN113438681A CN202010209696.4A CN202010209696A CN113438681A CN 113438681 A CN113438681 A CN 113438681A CN 202010209696 A CN202010209696 A CN 202010209696A CN 113438681 A CN113438681 A CN 113438681A
- Authority
- CN
- China
- Prior art keywords
- slice
- sub
- evaluation
- evaluation result
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5019—Ensuring fulfilment of SLA
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
- H04L43/55—Testing of service level quality, e.g. simulating service usage
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The embodiment of the invention relates to the technical field of computers, and discloses a feasibility evaluation method and device for network slicing and computing equipment. The method comprises the following steps: receiving a creation request of a slice, wherein the creation request comprises creation demand information; generating service level agreement index data according to the creation demand information; acquiring resource condition data of each sub-slice according to the creation request; inputting the service level protocol index data and the resource condition data of each sub-slice into a preset evaluation model, and acquiring an evaluation result output by the preset evaluation model; determining whether the slice passes feasibility evaluation according to the evaluation result; and if the section is determined to pass the feasibility evaluation, creating the section according to the creation request. Through the mode, the evaluation efficiency can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a feasibility evaluation method and device for network slices and computing equipment.
Background
Network Slice (Network Slice) refers to a physical Network is cut into a plurality of virtual end-to-end networks, and devices, access networks, transmission networks and core networks in the networks are logically independent among the virtual networks. Therefore, when an error or a fault occurs in one virtual network, other virtual networks are not affected. And 5G slicing is to cut the 5G network into a plurality of virtual networks so as to support more services.
At present, the feasibility evaluation method of the 5G network slice mainly depends on manual evaluation, and the efficiency is low.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a method, an apparatus, and a computing device for evaluating feasibility of a network slice, which can improve evaluation efficiency.
According to a first aspect of the embodiments of the present invention, a feasibility assessment method for network slicing is provided, including: receiving a creation request of a slice, wherein the creation request comprises creation demand information; generating service level agreement index data according to the creation demand information; acquiring resource condition data of each sub-slice according to the creation request; inputting the service level protocol index data and the resource condition data of each sub-slice into a preset evaluation model, and acquiring an evaluation result output by the preset evaluation model; determining whether the slice passes feasibility evaluation according to the evaluation result; and if the section is determined to pass the feasibility evaluation, creating the section according to the creation request.
In an optional manner, the creation requirement information includes performance index information and service characteristic information, and the service level protocol index data includes one or more of time delay, bandwidth, throughput rate, packet loss rate, call drop rate, connection number, user scale, isolation, service range, and access manner; generating service level agreement index data according to the creation demand information specifically comprises: generating one or more of the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate and the connection number according to the performance index demand information; and generating one or more of the user scale, the isolation, the service range and the access mode according to the service characteristic information.
In an optional manner, each sub-slice includes an access network sub-slice, a transmission network sub-slice, and a core network sub-slice, resource status data of the access network sub-slice includes radio resource status data, resource status data of the transmission network sub-slice includes transmission resource status data, resource status data of the core network sub-slice includes core network resource status data, and the evaluation result includes the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result;
the inputting the service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model, and obtaining an evaluation result output by the preset evaluation model specifically includes: inputting the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate, the connection number, the user scale, the isolation, the service range, the access mode, the wireless resource status data, the transmission resource status data, and the core network resource status data into the preset evaluation model, and obtaining the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result output by the preset evaluation model.
In an optional manner, the determining whether the slice passes the feasibility evaluation according to the evaluation result specifically includes: respectively judging whether the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result pass or not; and if the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result are determined to pass, determining that the slices pass the feasibility evaluation.
In an optional manner, the method further comprises: acquiring historical service level protocol index data and historical resource condition data of each sub-slice; and training a preset neural network according to the historical service level agreement index data and the historical resource condition data of each sub-slice, and determining the trained preset neural network as the preset evaluation model.
In an optional manner, the method further comprises: rejecting the creation request if it is determined that the slice does not pass the feasibility assessment.
In an optional manner, the method further comprises: determining the sub-slices which do not pass the evaluation result according to the evaluation result; performing resource expansion on the sub-slices which do not pass the evaluation result; and after the resource expansion is completed, notifying a sender of the creation request.
According to a second aspect of the embodiments of the present invention, there is provided a feasibility assessment apparatus for network slicing, including: a creation request receiving module, configured to receive a creation request for a slice, where the creation request includes creation requirement information; the index data generation module is used for generating service level protocol index data according to the creation demand information; a resource status data acquisition module, configured to acquire resource status data of each sub-slice according to the creation request; the evaluation module is used for inputting the service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model and acquiring an evaluation result output by the preset evaluation model; a determination module for determining whether the slice passes feasibility evaluation according to the evaluation result; and the creating module is used for creating the slice according to the creating request if the slice is determined to pass the feasibility evaluation.
According to a third aspect of embodiments of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus; the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the feasibility assessment method of network slicing described above.
According to a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium having at least one executable instruction stored therein, which when executed on a computing device, causes the computing device to execute the feasibility assessment method for network slicing described above.
According to the method and the device, the creation request of the slice is received, the creation request comprises creation requirement information, service level agreement index data is generated according to the creation requirement information, the resource condition data of each sub-slice is obtained according to the creation request, the service level agreement index data and the resource condition data of each sub-slice are input into the preset evaluation model, the evaluation result output by the preset evaluation model is obtained, whether the slice passes feasibility evaluation or not is determined according to the evaluation result, if the slice passes the feasibility evaluation, the slice is created according to the creation request, SLA index data can be automatically generated according to the creation requirement information, the convenience of operation is improved, and the feasibility evaluation can be automatically carried out on the creation of the network slice, so that the evaluation efficiency is improved.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic application environment diagram of a feasibility assessment method for network slicing according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a feasibility assessment method for network slicing according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a feasibility assessment method for network slicing according to another embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a neural network according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram illustrating a feasibility assessment apparatus for network slicing according to an embodiment of the present invention;
fig. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein.
Currently, the feasibility evaluation method of 5G network slices mainly relies on manual evaluation. At the initial stage of network slice development, the number of applications is small, the number of resources is large, most of the creation requirements provided by a user side can be met, but with the rapid increase of the application requirements of the vertical industry, the problems of large number of applications and small number of resources are gradually faced, the efficiency of a manual evaluation mode is low, and the requirements of automatic operation and maintenance are not met.
Based on this, the embodiment of the invention provides a feasibility assessment method and device for a network slice and computing equipment, which can improve assessment efficiency.
Specifically, the embodiments of the present invention will be further explained below with reference to the drawings.
It should be understood that the following examples are provided by way of illustration and are not intended to limit the invention in any way to the particular embodiment disclosed.
Fig. 1 is a schematic application environment diagram illustrating a feasibility assessment method for network slicing according to an embodiment of the present invention. As shown in fig. 1, the application environment includes: a Communication Service Management Function (CSMF) module 101, a Slice Management Function (NSMF) module 102, and a sub-Slice Management Function (NSSMF) module 103.
The CSMF module 101 is configured to complete a requirement subscription and processing of a user service communication service, convert a communication service requirement of an operator or a third party customer into a requirement for a network slice, send a requirement (such as a request for creating, terminating, modifying, and the like) for the network slice to the NSMF module 102 through an interface with the NSMF module 102, further obtain management data (such as performance data, fault data, and the like) of the network slice from the NSMF module 102, generate management data of a communication service running on an instance of the network slice, and receive a subscription requirement, and the like, of the operator or the third party customer, for the network slice management data or the communication service.
The NSMF module 102 is configured to receive a network slice requirement sent by the CSMF module 101, manage a life cycle, performance, and failure of a network slice instance, arrange components of the network slice instance, decompose the requirement of the network slice instance into requirements of each network slice subnet instance or network function, and send a network slice subnet instance management request to each NSSMF module 103.
The NSSMF module 103 is configured to receive a Network slice subnet deployment requirement issued by the NSMF module 102, manage a Network slice subnet instance, receive a Network slice subnet deployment requirement issued by the NSNF, manage a Network slice subnet instance, arrange components of the Network slice subnet instance, map the Network slice requirement of the Network slice subnet to a Quality of Service (QoS) requirement of a Network Service, and issue a deployment request of the Network Service to a Network function Virtualization (NFV Virtualization, NFVO) system of a Network Function Virtualization (NFV) domain.
Fig. 2 is a flowchart illustrating a feasibility assessment method for a network slice according to an embodiment of the present invention. The method may be applied to the application environment in fig. 1. As shown in fig. 2, the method includes:
For example, when the user needs to create a slice, the creation request is triggered at the terminal, the terminal sends the creation request to the CSMF module, and the CSMF module receives the creation request of the slice.
When a creation request is triggered, a user needs to input creation requirement information of a slice based on application requirements, and when the creation request is sent, the creation requirement information is carried and sent to the CSMF module.
Wherein creating the requirement information may include: performance index information and service characteristic information. The performance index information refers to information for measuring a performance index of the network slice. The performance indicator information may or may not be specific data, for example, the performance indicator data includes performance (strong, medium, and weak), so that the user can describe the approximate performance information without knowing the specific data; or, the performance index information includes a time delay (0-10ms), a bandwidth (0-200Mbps), a throughput (0-100%), a packet loss rate (0-100%), a call drop rate (0-100%), a connection number (0-10), and the like, so that the user can limit the performance through the specific data. The service characteristic information refers to information for describing an application service scenario of the network slice. The service characteristic information may include subscriber size information (large, medium, small), quarantine information (strong, medium, weak), service scope information (large, medium, small), access mode information (ADSL, LAN, FTTH, PON), and so on.
And step 220, generating service level agreement index data according to the creation requirement information.
The Service Level Agreement (SLA) refers to an Agreement or contract that is agreed between an enterprise providing a Service and a client and is commonly approved by both parties with respect to the quality, level, performance, and the like of the Service. In the present embodiment, the SLA index data refers to index data generated from creation demand information sent by a user. After the CSMF module receives the creation request, the CSMF module generates SLA index data according to the creation requirement information in the creation request, and sends the SLA index data to the preprocessing module, so that the preprocessing module processes the SLA index data into a preset format.
The SLA index data comprises one or more of time delay, bandwidth, throughput rate, packet loss rate, call drop rate, connection number, user scale, isolation, service range and access mode. Specifically, step 220 includes:
step 221, generating one or more of time delay, bandwidth, throughput rate, packet loss rate, call drop rate and connection number according to the performance index requirement information;
step 222, generating one or more of user scale, isolation, service range and access mode according to the service characteristic information.
The corresponding relation between the performance index demand information and the SLA index data is preset, and therefore the SLA index data is determined according to the preset corresponding relation. For example, when the performance index requirement information is high performance, the corresponding time delay is a1, when the performance index requirement information is medium performance, the corresponding time delay is a2, and when the performance index requirement information is low performance, the corresponding time delay is a3, so that the time delay is generated according to the performance index requirement information. Similarly, the corresponding relation between the service characteristic information and the SLA index data is preset, so that the SLA index data is determined according to the preset corresponding relation.
And step 230, acquiring the resource status data of each sub-slice according to the creation request.
The number of the sub-slices may be several, and the sub-slices may include an access network sub-slice, a transmission network sub-slice, a core network sub-slice, and so on.
Wherein the resource status data of the access network sub-slice comprises radio resource status data. The radio resource status data may include: one or more of an idle RB, an idle sector, a maximum number of supported cells, a maximum throughput (DL + UL), a maximum number of RRC connection users, a single gNodeB maximum data radio bearer, an uplink-downlink ratio, a spectrum efficiency, an Xn traffic ratio, and the like.
Wherein the resource status data of the transmission network sub-slice comprises transmission resource status data. Transmitting the resource status data may include: one or more of idle access layer bandwidth, idle aggregation layer bandwidth, idle core layer bandwidth, bearer network latency, single hop average latency, device forwarding latency, time synchronization requirements (e.g., 350ns), and the like.
The resource status data of the core network sub-slice comprises core network resource status data. The core network resource status data may include: one or more of idle CPU, idle memory, idle storage, etc.
In step 230, the NSMF module obtains the resource status data of each sub-slice according to the creation request, and sends the resource status data of each sub-slice to the preprocessing module, so that the preprocessing module processes the resource status data into a preset format.
And 240, inputting the service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model, and acquiring an evaluation result output by the preset evaluation model.
The preprocessing module inputs the processed service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model in the evaluation module, and the preset evaluation model outputs an evaluation result.
The evaluation result may include an access network sub-slice evaluation result, a transmission network sub-slice evaluation result, and a core network sub-slice evaluation result. Step 240 may specifically be: inputting the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate, the number of connections, the user scale, the isolation, the service range, the access mode, the wireless resource condition data, the transmission resource condition data and the core network resource condition data into a preset evaluation model, outputting an access network sub-slice evaluation result, a transmission network sub-slice evaluation result and a core network sub-slice evaluation result by the preset evaluation model, and acquiring the access network sub-slice evaluation result, the transmission network sub-slice evaluation result and the core network sub-slice evaluation result by a CSMF module.
And step 250, determining whether the section passes the feasibility evaluation according to the evaluation result.
And after the CSMF module obtains the evaluation result, the CSMF module judges whether the slice passes the feasibility evaluation according to the evaluation result. Specifically, step 250 may include:
251, respectively judging whether the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result pass or not;
step 252, if it is determined that the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result all pass, determining that the slicing passes the feasibility evaluation;
and step 253, if the self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result of any access network are determined not to pass, determining that the slicing does not pass the feasibility evaluation.
For example, the evaluation result may be a specific numerical value, assuming that output 1 indicates passing and output 0 indicates failing, and if the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result, and the core network sub-slicing evaluation result are all 1, determining that the slice passes the feasibility evaluation; and if one of the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result is 0, determining that the slice does not pass the feasibility evaluation.
And step 260, if the section is determined to pass the feasibility evaluation, creating the section according to the creation request.
When the CSMF module determines that the slice passes the feasibility evaluation, the CSMF module passes the creation request, and the CSMF module enables the NSMF module to control the NSSMF module to create the slice according to the creation request.
In some other embodiments, the method further comprises:
step 270, if the slice is determined not to pass the feasibility assessment, rejecting the creation request.
Wherein when the CSMF module determines that the slice does not pass the feasibility assessment, the CSMF module sends a message to the user rejecting the creation request and instructs the NSMF module not to respond to the creation request.
In some other embodiments, after rejecting the create request, the method further comprises:
step 281, determining the sub-slice which does not pass the evaluation result according to the evaluation result;
282, carrying out resource expansion on the sub-slices which do not pass the evaluation result;
step 283, after the resource expansion is completed, the sender of the creation request is notified.
And the CSMF module determines sub-slices which do not pass the evaluation result in the access network sub-slices, the transmission network sub-slices and the core network sub-slices according to the access network self-slice evaluation result, the transmission network sub-slice evaluation result and the core network sub-slice evaluation result. For example, assuming that output 1 indicates pass and output 0 indicates fail, and the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result, and the core network sub-slicing evaluation result are obtained as 0, 1, and 1, respectively, the CSMF module determines that the sub-slice whose evaluation result does not pass is the access network sub-slice.
After determining the sub-slice that the evaluation result does not pass, the CSMF module notifies the NSMF module to perform resource expansion on the sub-slice that the evaluation result does not pass, so that the sub-slice that the evaluation result does not pass can meet the SLA index data after the resource expansion.
After the resource expansion is completed, the NSMF module notifies the sender of the creation request, so that the sender of the creation request initiates the creation request again.
According to the method and the device, the creation request of the slice is received, the creation request comprises creation requirement information, service level agreement index data is generated according to the creation requirement information, the resource condition data of each sub-slice is obtained according to the creation request, the service level agreement index data and the resource condition data of each sub-slice are input into the preset evaluation model, the evaluation result output by the preset evaluation model is obtained, whether the slice passes feasibility evaluation or not is determined according to the evaluation result, if the slice passes the feasibility evaluation, the slice is created according to the creation request, SLA index data can be automatically generated according to the creation requirement information, the convenience of operation is improved, and the feasibility evaluation can be automatically carried out on the creation of the network slice, so that the evaluation efficiency is improved.
Fig. 3 is a flowchart illustrating a feasibility assessment method for network slicing according to another embodiment of the present invention. The difference from the above embodiment is that, as shown in fig. 3, the method further includes:
and 291, acquiring historical service level agreement index data and historical resource condition data of each sub-slice.
The historical service level agreement index data refers to SLA index data required by users in historical industries and can be acquired from the CSMF module. The historical resource status data refers to resource status data of each historical sub-slice, and can be acquired from the NSMF module.
And 292, training the preset neural network according to the historical service level agreement index data and the historical resource condition data of each sub-slice, and determining the trained preset neural network as a preset evaluation model.
Wherein, training preset neural network specifically includes: after acquiring historical service level protocol index data and historical resource condition data of each sub-slice, generating a data set, and manually marking the satisfying condition of each sub-slice for each data in the data set. And, the data set is divided into a training set and a test set, the training set is used for training the model, and the test set is used for testing the performance of the model. Meanwhile, input information in the training set and the test set is converted into a machine-recognizable form, non-numerical attribute information is converted into a numerical attribute, all attribute information is normalized to mean value 0 and variance 1, and therefore the convergence speed of the training model and the precision of the training model are improved.
As shown in fig. 4, the preset neural network may include: 1 input layer, 10 hidden layers (including 5 fully connected layers and 5 discarded layers), 1 output layer. Each circle in fig. 2 represents a neuron, each line has a different weight (weight), and the preset neural network learns the weight value autonomously through training.
The data dimension input by the input layer is n + m, namely the data dimension comprises n + m characteristics, specifically historical service level agreement index data (S)1……Sn) And historical resource status data (R) for each sub-slice1……Rn)。
Wherein, the 1 st, 2 nd full connection layer of hidden layer include 64 neurons, the 3 rd, 4 th full connection layer include 32 neurons, the 5 th full connection layer includes 16 neurons, the laser function that the full connection layer used is "relu". A discard layer (Dropout layer) is introduced after each fully connected layer to effectively avoid overfitting. Wherein the discard layer is configured to discard neurons with a probability p and to leave other neurons with a probability q of 1-p. In this embodiment, the probability p is 0.2, i.e., 20% of the neurons are randomly ignored and made ineffective.
Wherein, the output layer is composed of a full connection layer (Dense): the number of neurons is 3, and the laser function is set to "sigmoid". The output layer is used to output whether each sub-slice (access network sub-slice, transmission network sub-slice, and core network sub-slice) meets the requirements of the SLA index data, for example, output layer output 1 indicates satisfied, and output 0 indicates unsatisfied.
Wherein, training preset neural network specifically still includes: and calculating the error between the output result of the output layer and the satisfying condition of each manually marked sub-slice, and minimizing the error by training an objective function. The objective function may select a "binary _ cross" class two logarithmic loss function. The number of training rounds may be set to 1500(epochs 1500). The gradient descent optimization algorithm may select an adam optimizer (adam') to improve the learning speed of the conventional gradient descent. The preset neural network can find the optimal weight value which enables the target function to be minimum through gradient descent. The smaller the objective function is, the better the objective function is through training of the training set, the preset neural network is evaluated and verified through the test set after each training, and the weight of the preset neural network is derived after the preset neural network converges, so that the preset evaluation model is obtained.
According to the embodiment of the invention, the historical service level protocol index data and the historical resource condition data of each sub-slice are obtained, the preset neural network is trained according to the historical service level protocol index data and the historical resource condition data of each sub-slice, the trained preset neural network is determined as the preset evaluation model, the preset neural network can be trained according to the historical data to obtain the preset evaluation model, and therefore, the feasibility evaluation is automatically carried out on the creation of the network slice through the preset evaluation model, and the evaluation efficiency is improved.
Fig. 5 is a schematic structural diagram illustrating a feasibility assessment apparatus for network slicing according to an embodiment of the present invention. The apparatus may be applied to a computing device. As shown in fig. 5, the apparatus 300 includes: a creation request receiving module 310, an index data generating module 320, a resource status data obtaining module 330, an evaluating module 340, a determining module 350, and a creating module 360.
The creation request receiving module 310, the index data generating module 320, the determining module 350, and the creating module 360 may be provided in the CSMF module; the resource status data acquisition module 330 may be provided in the NSMF module.
The creation request receiving module 310 is configured to receive a creation request of a slice, where the creation request includes creation requirement information; the index data generating module 320 is configured to generate service level agreement index data according to the creation demand information; the resource status data obtaining module 330 is configured to obtain resource status data of each sub-slice according to the creation request; the evaluation module 340 is configured to input the service level agreement indicator data and the resource status data of each sub-slice into a preset evaluation model, and obtain an evaluation result output by the preset evaluation model; the determining module 350 is configured to determine whether the slice passes the feasibility evaluation according to the evaluation result; the creating module 360 is configured to create the slice according to the creating request if it is determined that the slice passes the feasibility evaluation.
In an optional manner, the creation requirement information includes performance index information and service characteristic information, and the service level protocol index data includes one or more of time delay, bandwidth, throughput rate, packet loss rate, call drop rate, number of connections, user size, isolation, service range, and access manner. The index data generation module 320 is specifically configured to: generating one or more of the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate and the connection number according to the performance index demand information; and generating one or more of the user scale, the isolation, the service range and the access mode according to the service characteristic information.
In an optional manner, each sub-slice includes an access network sub-slice, a transmission network sub-slice, and a core network sub-slice, resource status data of the access network sub-slice includes radio resource status data, resource status data of the transmission network sub-slice includes transmission resource status data, resource status data of the core network sub-slice includes core network resource status data, and the evaluation result includes the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result. The evaluation module 340 is specifically configured to: inputting the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate, the connection number, the user scale, the isolation, the service range, the access mode, the wireless resource status data, the transmission resource status data, and the core network resource status data into the preset evaluation model, and obtaining the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result output by the preset evaluation model.
In an optional manner, the determining module 350 is specifically configured to: respectively judging whether the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result pass or not; and if the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result are determined to pass, determining that the slices pass the feasibility evaluation.
In an optional manner, the apparatus 300 further comprises: and a model training module. The model training module is used for: acquiring historical service level protocol index data and historical resource condition data of each sub-slice; and training a preset neural network according to the historical service level agreement index data and the historical resource condition data of each sub-slice, and determining the trained preset neural network as the preset evaluation model.
In an optional manner, the apparatus 300 further comprises: the creation module is rejected. The rejection creation module may be provided at the CSMF module. The rejection creation module may be configured to reject the creation request if the slice is determined not to pass the feasibility assessment.
In an optional manner, the apparatus 300 further comprises: the device comprises a sub-slice determining module, a capacity expansion module and a notification module. The sub-slice determining module may be provided in the CSMF module, and the capacity expanding module and the notifying module may be provided in the NSMF module. The sub-slice determining module is used for determining the sub-slices which do not pass the evaluation result according to the evaluation result; the capacity expansion module is used for carrying out resource capacity expansion on the sub-slices which do not pass the evaluation result; and the notification module is used for notifying the sender of the creation request after the resource expansion is completed.
It should be noted that, the feasibility assessment apparatus for network slices provided in the embodiments of the present invention is an apparatus capable of executing the feasibility assessment method for network slices, and all embodiments of the feasibility assessment method for network slices are applicable to the apparatus and can achieve the same or similar beneficial effects.
According to the method and the device, the creation request of the slice is received, the creation request comprises creation requirement information, service level agreement index data is generated according to the creation requirement information, the resource condition data of each sub-slice is obtained according to the creation request, the service level agreement index data and the resource condition data of each sub-slice are input into the preset evaluation model, the evaluation result output by the preset evaluation model is obtained, whether the slice passes feasibility evaluation or not is determined according to the evaluation result, if the slice passes the feasibility evaluation, the slice is created according to the creation request, SLA index data can be automatically generated according to the creation requirement information, the convenience of operation is improved, and the feasibility evaluation can be automatically carried out on the creation of the network slice, so that the evaluation efficiency is improved.
Fig. 6 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the computing device.
As shown in fig. 6, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402, configured to execute the program 410, may specifically perform relevant steps in the above-described feasibility assessment method embodiment for network slicing.
In particular, program 410 may include program code comprising computer-executable instructions.
The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may be specifically invoked by the processor 402 to cause the computing device to perform the operations in the feasibility assessment method of network slicing in the above-described embodiments.
According to the method and the device, the creation request of the slice is received, the creation request comprises creation requirement information, service level agreement index data is generated according to the creation requirement information, the resource condition data of each sub-slice is obtained according to the creation request, the service level agreement index data and the resource condition data of each sub-slice are input into the preset evaluation model, the evaluation result output by the preset evaluation model is obtained, whether the slice passes feasibility evaluation or not is determined according to the evaluation result, if the slice passes the feasibility evaluation, the slice is created according to the creation request, SLA index data can be automatically generated according to the creation requirement information, the convenience of operation is improved, and the feasibility evaluation can be automatically carried out on the creation of the network slice, so that the evaluation efficiency is improved.
An embodiment of the present invention provides a computer-readable storage medium, where at least one executable instruction is stored, and when the executable instruction is executed on a content transmission network device, the feasibility assessment apparatus/device of a network slice performs the feasibility assessment method of the network slice in any of the above method embodiments. The executable instructions may be specifically configured to cause the computing device to perform the operations in the feasibility assessment method of network slicing in the above-described embodiments.
According to the method and the device, the creation request of the slice is received, the creation request comprises creation requirement information, service level agreement index data is generated according to the creation requirement information, the resource condition data of each sub-slice is obtained according to the creation request, the service level agreement index data and the resource condition data of each sub-slice are input into the preset evaluation model, the evaluation result output by the preset evaluation model is obtained, whether the slice passes feasibility evaluation or not is determined according to the evaluation result, if the slice passes the feasibility evaluation, the slice is created according to the creation request, SLA index data can be automatically generated according to the creation requirement information, the convenience of operation is improved, and the feasibility evaluation can be automatically carried out on the creation of the network slice, so that the evaluation efficiency is improved.
The embodiment of the invention provides a feasibility evaluation device of a network slice, which is used for executing the feasibility evaluation method of the network slice.
Embodiments of the present invention provide a computer program that can be invoked by a processor to cause a computing device to perform a feasibility assessment method of a network slice in any of the above-described method embodiments.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions that, when run on a computer, cause the computer to perform the feasibility assessment method of network slicing in any of the above-described method embodiments.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A feasibility assessment method for network slicing, comprising:
receiving a creation request of a slice, wherein the creation request comprises creation demand information;
generating service level agreement index data according to the creation demand information;
acquiring resource condition data of each sub-slice according to the creation request;
inputting the service level protocol index data and the resource condition data of each sub-slice into a preset evaluation model, and acquiring an evaluation result output by the preset evaluation model;
determining whether the slice passes feasibility evaluation according to the evaluation result;
and if the section is determined to pass the feasibility evaluation, creating the section according to the creation request.
2. The method according to claim 1, wherein the creation requirement information includes performance index information and service characteristic information, and the service level protocol index data includes one or more of delay, bandwidth, throughput rate, packet loss rate, call drop rate, connection number, user size, isolation, service range, and access mode;
generating service level agreement index data according to the creation demand information specifically comprises:
generating one or more of the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate and the connection number according to the performance index demand information;
and generating one or more of the user scale, the isolation, the service range and the access mode according to the service characteristic information.
3. The method of claim 2, wherein the sub-slices comprise an access network sub-slice, a transmission network sub-slice, and a core network sub-slice, wherein the resource status data of the access network sub-slice comprises radio resource status data, the resource status data of the transmission network sub-slice comprises transmission resource status data, the resource status data of the core network sub-slice comprises core network resource status data, and the evaluation result comprises the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result;
the inputting the service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model, and obtaining an evaluation result output by the preset evaluation model specifically includes:
inputting the time delay, the bandwidth, the throughput rate, the packet loss rate, the call drop rate, the connection number, the user scale, the isolation, the service range, the access mode, the wireless resource status data, the transmission resource status data, and the core network resource status data into the preset evaluation model, and obtaining the access network sub-slice evaluation result, the transmission network sub-slice evaluation result, and the core network sub-slice evaluation result output by the preset evaluation model.
4. The method according to claim 3, wherein the determining whether the slice passes the feasibility evaluation according to the evaluation result specifically comprises:
respectively judging whether the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result pass or not;
and if the access network self-slicing evaluation result, the transmission network sub-slicing evaluation result and the core network sub-slicing evaluation result are determined to pass, determining that the slices pass the feasibility evaluation.
5. The method of claim 1, further comprising:
acquiring historical service level protocol index data and historical resource condition data of each sub-slice;
and training a preset neural network according to the historical service level agreement index data and the historical resource condition data of each sub-slice, and determining the trained preset neural network as the preset evaluation model.
6. The method according to any one of claims 1-5, further comprising:
rejecting the creation request if it is determined that the slice does not pass the feasibility assessment.
7. The method of claim 6, further comprising:
determining the sub-slices which do not pass the evaluation result according to the evaluation result;
performing resource expansion on the sub-slices which do not pass the evaluation result;
and after the resource expansion is completed, notifying a sender of the creation request.
8. A feasibility assessment apparatus for network slicing, comprising:
a creation request receiving module, configured to receive a creation request for a slice, where the creation request includes creation requirement information;
the index data generation module is used for generating service level protocol index data according to the creation demand information;
a resource status data acquisition module, configured to acquire resource status data of each sub-slice according to the creation request;
the evaluation module is used for inputting the service level agreement index data and the resource condition data of each sub-slice into a preset evaluation model and acquiring an evaluation result output by the preset evaluation model;
a determination module for determining whether the slice passes feasibility evaluation according to the evaluation result;
and the creating module is used for creating the slice according to the creating request if the slice is determined to pass the feasibility evaluation.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the network slice feasibility assessment method of any of claims 1-7.
10. A computer-readable storage medium having stored therein at least one executable instruction that, when executed on a computing device, causes the computing device to perform operations of the network slice feasibility assessment method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010209696.4A CN113438681B (en) | 2020-03-23 | 2020-03-23 | Network slice feasibility evaluation method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010209696.4A CN113438681B (en) | 2020-03-23 | 2020-03-23 | Network slice feasibility evaluation method and device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113438681A true CN113438681A (en) | 2021-09-24 |
| CN113438681B CN113438681B (en) | 2023-04-07 |
Family
ID=77752697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010209696.4A Active CN113438681B (en) | 2020-03-23 | 2020-03-23 | Network slice feasibility evaluation method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113438681B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114840348A (en) * | 2022-07-01 | 2022-08-02 | 石家庄学院 | Resource grade determination method and system for computer |
| WO2023155720A1 (en) * | 2022-02-18 | 2023-08-24 | 华为技术有限公司 | Method and apparatus for feasibility evaluation |
| WO2023207534A1 (en) * | 2022-04-29 | 2023-11-02 | 华为技术有限公司 | Network management method, apparatus and system, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3396997A1 (en) * | 2017-04-28 | 2018-10-31 | NEC Laboratories Europe GmbH | Method and system for network slice allocation |
| CN109495907A (en) * | 2018-11-29 | 2019-03-19 | 北京邮电大学 | A kind of the wireless access network-building method and system of intention driving |
| CN109756357A (en) * | 2017-11-08 | 2019-05-14 | 中兴通讯股份有限公司 | A kind of network slice generation method and device and terminal |
| CN110138575A (en) * | 2018-02-02 | 2019-08-16 | 中兴通讯股份有限公司 | Network is sliced creation method, system, the network equipment and storage medium |
| US20190394655A1 (en) * | 2018-06-22 | 2019-12-26 | Huawei Technologies Co., Ltd. | Data analytics management (dam), configuration specification and procedures, provisioning, and service based architecture (sba) |
| US20200053834A1 (en) * | 2018-08-07 | 2020-02-13 | At&T Intellectual Property I, L.P. | Automated network design and traffic steering |
-
2020
- 2020-03-23 CN CN202010209696.4A patent/CN113438681B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3396997A1 (en) * | 2017-04-28 | 2018-10-31 | NEC Laboratories Europe GmbH | Method and system for network slice allocation |
| CN109756357A (en) * | 2017-11-08 | 2019-05-14 | 中兴通讯股份有限公司 | A kind of network slice generation method and device and terminal |
| CN110138575A (en) * | 2018-02-02 | 2019-08-16 | 中兴通讯股份有限公司 | Network is sliced creation method, system, the network equipment and storage medium |
| US20190394655A1 (en) * | 2018-06-22 | 2019-12-26 | Huawei Technologies Co., Ltd. | Data analytics management (dam), configuration specification and procedures, provisioning, and service based architecture (sba) |
| US20200053834A1 (en) * | 2018-08-07 | 2020-02-13 | At&T Intellectual Property I, L.P. | Automated network design and traffic steering |
| CN109495907A (en) * | 2018-11-29 | 2019-03-19 | 北京邮电大学 | A kind of the wireless access network-building method and system of intention driving |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023155720A1 (en) * | 2022-02-18 | 2023-08-24 | 华为技术有限公司 | Method and apparatus for feasibility evaluation |
| WO2023207534A1 (en) * | 2022-04-29 | 2023-11-02 | 华为技术有限公司 | Network management method, apparatus and system, and storage medium |
| CN114840348A (en) * | 2022-07-01 | 2022-08-02 | 石家庄学院 | Resource grade determination method and system for computer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113438681B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113438681B (en) | Network slice feasibility evaluation method and device and computing equipment | |
| CN107005480B (en) | System and method for SDT interworking with NFV and SDN | |
| CN107113232B (en) | NFV management arrangement method and device | |
| EP4235522A1 (en) | Federated learning method and apparatus, device, system, and computer-readable storage medium | |
| CN113133087B (en) | Method and device for configuring network slice for terminal equipment | |
| WO2022237086A1 (en) | Control method and apparatus based on machine learning model | |
| WO2021169294A1 (en) | Application recognition model updating method and apparatus, and storage medium | |
| CN109361547B (en) | Network slice link deployment method and device | |
| CN109995839B (en) | Load balancing method, system and load balancer | |
| CN113328953B (en) | Method, device and storage medium for network congestion adjustment | |
| WO2022225565A1 (en) | Performance testing of a test application in a network-as-a-service environment | |
| CN112202584B (en) | Alarm correlation method, device, computing equipment and computer storage medium | |
| CN113259145B (en) | End-to-end networking method and device for network slicing and network slicing equipment | |
| CN114116207A (en) | Flow control method, device, equipment and system | |
| CN110190988B (en) | Service deployment method and device | |
| WO2018114016A1 (en) | Apparatus and method for identifying network object groups | |
| CN113949666B (en) | Flow control method, device, equipment and system | |
| WO2021114968A1 (en) | Scheduling method and apparatus | |
| CN113825149B (en) | 5G slice network element function automatic cutting method and device and computing equipment | |
| CN113822453B (en) | Multi-user complaint commonality determining method and device for 5G slices | |
| CN113949633A (en) | 5G network slice disaster recovery pool resource management method and device based on machine learning | |
| CN112990425A (en) | Automatic classification method of 5G network slices, device thereof, electronic equipment and computer storage medium | |
| CN113825151B (en) | Method and device for predicting relationship between slice alarms based on relationship graph convolution network | |
| CN114629685B (en) | Industrial private network hard slicing service function chain deployment method, device and medium | |
| Zhang et al. | Supervised Learning Based Resource Allocation with Network Slicing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |