CN115225500A - Network slice allocation method and device - Google Patents
Network slice allocation method and device Download PDFInfo
- Publication number
- CN115225500A CN115225500A CN202210696882.4A CN202210696882A CN115225500A CN 115225500 A CN115225500 A CN 115225500A CN 202210696882 A CN202210696882 A CN 202210696882A CN 115225500 A CN115225500 A CN 115225500A
- Authority
- CN
- China
- Prior art keywords
- network slice
- target
- data
- network
- historical data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004891 communication Methods 0.000 claims abstract description 69
- 238000004364 calculation method Methods 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 101000979909 Homo sapiens NMDA receptor synaptonuclear signaling and neuronal migration factor Proteins 0.000 description 9
- 102100024546 NMDA receptor synaptonuclear signaling and neuronal migration factor Human genes 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000007726 management method Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 101100234408 Danio rerio kif7 gene Proteins 0.000 description 1
- 101100221620 Drosophila melanogaster cos gene Proteins 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 101100398237 Xenopus tropicalis kif11 gene Proteins 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 101150118300 cos gene Proteins 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Images
Classifications
-
- 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
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/06—Management of faults, events, alarms or notifications
-
- 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
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- 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
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the application provides a network slice allocation method and device. The network slice allocation method comprises the following steps: receiving a network slicing request about a target communication service sent by user equipment; acquiring historical data of target parameters of physical network equipment where a target network slice is located; obtaining input data of a fault prediction model based on the historical data; inputting the input data into the fault prediction model to obtain the fault probability corresponding to the physical network equipment; and distributing network slices for the target communication service according to the fault probability corresponding to the physical network equipment. The technical scheme provided by the embodiment of the application can solve the problem that a network slice allocation strategy in the prior art has certain defects.
Description
Technical Field
The application belongs to the technical field of communication, and particularly relates to a network slice allocation method and device.
Background
The network slice is a temporary logic network, and is a virtual network that divides a physical network of an operator into a plurality of virtual networks according to different communication service requirements (such as time delay, bandwidth, security, reliability and the like) so as to flexibly cope with different network application scenarios, provide differentiated services, and meet different service requirements.
In the process of implementing the present application, the inventor finds that at least the following problems exist in the prior art: in the prior art, when a network slice is allocated to a communication service, the network slice is generally allocated only according to the type and attribute information of the network slice. However, the network slice allocation policy in the prior art does not consider the physical network device, and the allocation policy needs to be adjusted.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for network slice allocation, so as to solve the problem that a network slice allocation policy in the prior art has certain defects.
In a first aspect, an embodiment of the present application provides a network slice allocation method, where the method includes:
receiving a network slicing request about a target communication service sent by user equipment;
acquiring historical data of target parameters of physical network equipment where a target network slice is located; wherein the target network slice is a network slice that has been historically used and satisfies the network slice request; the target parameters include: at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate;
obtaining input data of a fault prediction model based on the historical data;
inputting the input data into the fault prediction model to obtain the fault probability corresponding to the physical network equipment;
and distributing network slices for the target communication service according to the fault probability corresponding to the physical network equipment.
In a second aspect, an embodiment of the present application provides an apparatus for allocating network slices, where the apparatus includes:
the receiving module is used for receiving a network slicing request about a target communication service sent by user equipment;
the acquisition module is used for acquiring historical data of target parameters of physical network equipment where the target network slice is located; wherein the target network slice is a network slice that has been historically used and that conforms to the network slice request; the target parameters include: at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate;
the data processing module is used for obtaining input data of a fault prediction model based on the historical data;
the prediction module is used for inputting the input data into the fault prediction model to obtain the fault probability corresponding to the physical network equipment;
and the distribution module is used for distributing the network slices for the target communication service according to the fault probability corresponding to the physical network equipment.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, where the memory stores a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implement the steps in the network slice allocation method according to the first aspect.
In a fourth aspect, the present application provides a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps in the network slice allocation method according to the first aspect.
In the embodiment of the application, when a server receives a network slice request about a target communication service sent by user equipment, historical data of target parameters (such as at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate) of physical network equipment where a target network slice (i.e. a network slice which is used historically and satisfies the network slice request) is located is obtained based on the network slice request, then input data of a fault prediction model is obtained based on the historical data, then the input data is input into the model, the probability of a fault occurring in the physical network equipment where the target network slice is located is predicted, and finally the network slice is allocated to the target communication service according to the probability of the fault occurring in the physical network equipment. The smaller the failure probability is, the higher the reliability of the physical network device is, and the higher the reliability of the network slice deployed on the physical network device is, so that the network slice is allocated to the target communication service in combination with the failure probability of the physical network device, which is beneficial to reducing the occurrence of the situation that the target communication service cannot be normally performed due to the failure of the physical network device, optimizing the allocation strategy of the network slice, and improving the intelligence of the allocation strategy of the network slice.
Drawings
Fig. 1 is a schematic flowchart of a network slice allocation method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an example provided by an embodiment of the present application;
fig. 3 is a schematic block diagram of a network slice allocation apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the embodiments described below are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present application, it should be understood that the sequence numbers of the steps do not mean an absolute sequential execution order, and the execution order of the steps should be determined by the function and the inherent logic, so the sequence numbers of the steps should not be an absolute limitation to the implementation process of the embodiments of the present application.
The network slice allocation method provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
The embodiment of the application provides a network slice distribution method which is applied to a server, such as a base station server.
As shown in fig. 1, the network slice allocation method may include:
step 101: and receiving a network slicing request which is sent by the user equipment and relates to the target communication service.
Wherein, the network slicing request comprises: a network slice requirement parameter for the target communication service. Network slice requirement parameters as described herein may include, but are not limited to: slice type (eMBB, uRLLC, mMTC, etc.), slice performance requirements (e.g., latency, bandwidth, reliability, etc.), slice specification, geographic location, etc.
The user may request the network slice from the operator and provide the relevant parameters of the network slice required for the service through the user equipment.
Step 102: and acquiring historical data of target parameters of the physical network equipment where the target network slice is located.
Wherein the target network slice is a network slice that has been historically used and satisfies the network slice request (e.g., meets the network slice requirement parameters).
In this embodiment of the present application, the target parameter is related to reliability of the physical network device, for example, the target parameter may include: at least one of memory occupancy, CPU occupancy, and disk space occupancy. The reliability of the physical network device is higher when the values of the memory occupancy rate, the CPU occupancy rate and the disk space occupancy rate are lower, and conversely, the reliability of the physical network device is lower when the values are higher. Optionally, the target parameter may further include: at least one of historical traffic, instantaneous traffic, GPU occupancy, alarm duration when a fault occurs, and alarm level when a fault occurs for each port of the physical network device.
The historical data of the target parameter may include: and acquiring the numerical value of the target parameter every preset time within the past preset time period. It will be appreciated that the historical data may also include the time of acquisition of the data.
In the embodiment of the application, the server may determine, when receiving a network slicing request sent by the user equipment, physical network devices corresponding to network slices which have been used historically and satisfy the network slicing request, and then acquire historical data of target parameters of the physical network devices. Based on these historical data, the probability of failure of the predicted physical network device may be analyzed.
Wherein the number of physical network devices is at least one.
Step 103: based on the historical data, input data for a fault prediction model is obtained.
The failure prediction model described herein is used to predict the probability of failure of a physical network device, and is pre-trained.
In this step, input data of the fault prediction model may be obtained based on the historical data acquired in step 102. Since the target parameter is related to reliability of the physical network device, etc., input data of the model may be obtained based on historical data of the target parameter so that the model predicts a probability of failure of the physical network device.
Step 104: and inputting the input data into a fault prediction model to obtain the fault probability corresponding to the physical network equipment.
In this step, the input data obtained in step 103 may be input into a failure prediction model to predict the probability of failure of the physical network device.
Step 105: and distributing network slices for the target communication service according to the fault probability corresponding to the physical network equipment.
The smaller the failure probability is, the higher the reliability of the physical network device is, and the higher the reliability of the network slice deployed on the physical network device is, so in this embodiment of the present application, the network slice may be allocated to the target communication service in combination with the failure probability corresponding to the physical network device. For example, the target network slice corresponding to the physical network device with the lower failure probability is preferentially allocated to the target communication service, so that the situation that the target communication service cannot be normally performed due to the failure of the physical network device is reduced, and the allocation strategy of the network slice is optimized. In addition, the artificial intelligence model is added into the network slice distribution strategy, and the intellectualization of the network slice distribution strategy is improved.
As an alternative embodiment, at step 102: before obtaining the historical data of the target parameter of the physical network device where the target network slice is located, the network slice allocation method may further include:
determining a first network slice which is located in a preset area range of the current geographic position of the user equipment and used historically; and determining the network slices meeting the network slice request in the first network slices as target network slices.
In the embodiment of the application, when a target network slice is determined, network slices that have been used historically in a preset area range (for example, a circle with the current geographical position as a center and a preset distance as a radius) determined based on the current geographical position may be obtained based on the current geographical position of the user equipment, then network slices that meet a network slice request are screened from the network slices, and finally, the screened network slices are determined as the target network slices. The target network slice is determined in the mode, so that the determination range of the network slice can be reduced, the data processing amount is reduced, and the network slice is convenient to realize nearby distribution.
As an alternative embodiment, step 105: allocating a network slice to the target communication service according to the failure probability corresponding to the physical network device may include:
and sequentially determining whether the target network slices corresponding to the physical network equipment meet a first preset condition or not according to the sequence of the fault probability from small to large, and distributing the first target network slices meeting the first preset condition to the target communication service under the condition that the fault probability is smaller than the preset probability.
Wherein, the first preset condition includes: the target network slice is available and can carry the target communication traffic.
In the embodiment of the application, after the probability of failure of the physical network device where the target network slice is located is obtained, whether the target network slice corresponding to the physical network device is available or not can be sequentially determined according to the sequence from small to large of the probability of failure until a target network slice meeting a first preset condition is determined under the condition that the probability of failure is smaller than a preset probability, and then the target network slice is allocated to the target communication service.
For example, there are physical network devices A, B, C, the failure probability corresponding to physical network device a is 0.3, the failure probability corresponding to physical network device B is 0.4, the failure probability corresponding to physical network device C is 0.8, and the preset probability is 0.5. According to the sequence from small to large of the failure probability, whether a target network slice corresponding to the physical network equipment A is available is determined, and if the target network slice is available, whether the target network slice can bear the target communication service is determined. If the target network slice corresponding to the physical network device a is not available, or if the target network slice corresponding to the physical network device a is available but cannot carry the target communication service, continuously determining whether the target network slice corresponding to the physical network device B is available, if so, determining whether the target network slice can carry the target communication service, and so on until determining a target network slice meeting a first preset condition under the condition that the fault probability is less than 0.5, and then allocating the target network slice to the target communication service. Since the failure probability corresponding to the physical network device C is 0.8, which is greater than the preset probability 0.5, the target network slice corresponding to the physical network device C is not considered.
The preset probability generally takes a probability value with a smaller value, and the smaller the preset probability is, the less the physical network device corresponding to the target network slice allocated to the target communication service is prone to failure, and the higher the reliability is.
According to the embodiment of the application, the currently available network slice with low failure probability of the physical network equipment is preferentially allocated to the target communication service, so that optimal resource allocation is realized. In addition, the embodiment of the application preferentially allocates the existing and available network slices to the service demands, which is beneficial to improving the resource utilization rate and reducing the occurrence of executing the processing flow of creating a new network slice to meet the service demands.
Optionally, in the preceding step: in the process of sequentially determining whether the target network slice corresponding to the physical network device meets the first preset condition according to the sequence from small to large of the failure probability, the network slice allocation method may further include:
and when the failure probability is greater than or equal to the preset probability and the target network slice which meets the first preset condition is not provided, creating a second network slice which meets the network slice request, and distributing the second network slice to the target communication service.
In the embodiment of the application, in the process of sequentially determining whether the target network slice corresponding to the physical network device meets the first preset condition according to the sequence from small to large of the failure probability, if the failure probability is greater than or equal to the preset probability, a new network slice (i.e., a second network slice) meeting the network slice request can be innovated under the condition that the target network slice meeting the first preset condition is not found yet, and then the newly created network slice is allocated to the target communication service.
The failure probability of the physical network device is greater than or equal to the preset probability, which indicates that the physical network device has a high failure probability and poor reliability, and is not suitable for the target network slice corresponding to the physical network device to carry the target communication service, so as to avoid influencing the normal operation of the target communication service.
As an alternative embodiment, in step 101: after receiving a network slice request about a target communication service sent by a user equipment, the network slice allocation method may further include:
evaluating feasibility of a network slicing request for a target communication service; in case the network slicing request is available, step 102 is executed again: and acquiring historical data of target parameters of the physical network equipment where the target network slice is located.
In the embodiment of the application, after receiving a network slicing request about a target communication service sent by a user equipment, a server may first evaluate feasibility of the network slicing request, that is, evaluate whether a network slice required by the target communication service can be provided. If yes, continuing to execute step 102; if the network slice can not be provided, the request can be rejected, and a request failure message is fed back to inform the user that the corresponding network slice can not be provided. By evaluating the feasibility of the network slice request in advance, the situation that the corresponding network slice cannot be provided after a series of processing operations is found can be avoided, and the execution of invalid processing operations is reduced.
As an alternative embodiment, step 103: obtaining input data for a fault prediction model based on historical data may include:
and taking the historical data as input data of the fault prediction model, or taking target data obtained by interpolation calculation of the historical data as the input data of the fault prediction model.
The target data described herein may include: historical data and new data obtained by interpolation calculation.
In the embodiment of the application, historical data of target parameters of physical network equipment can be directly used as input data of a model; the historical data can be interpolated to obtain more data, and then the historical data and new data obtained by interpolation are used as input data of the model, so that the input data can be enriched, and the accuracy of model output is improved.
Optionally, before the step "target data obtained by performing interpolation calculation on historical data is used as input data of the failure prediction model", the network slice allocation method may further include:
based on a preset formula, respectively carrying out secondary interpolation calculation on the historical data of each target parameter; and then determining the historical data of the target parameters and the new data obtained by the secondary interpolation calculation as target data.
Wherein, the preset formula is as follows:
wherein x is i 、x i+1 、x i+2 Three acquisition moments of historical data respectively representing one target parameter; y is i Denotes x i Historical data of the target parameter, y, collected at the moment i+1 Denotes x i+1 Historical data of the target parameter, y, collected at the moment i+2 Denotes x i+2 Historical data of the target parameter collected at any moment; i is an integer greater than or equal to 1 and represents a serial number of the historical data acquisition time of the target parameter; x may be x i And x i+1 Between or x i+1 And x i+2 And y represents new data obtained after secondary interpolation calculation of the historical data of the target parameter.
Assuming that the target parameter is CPU occupancy rate, the historical data comprises: 12: CPU occupancy 21% and 12 acquired by 10: CPU occupancy 22% for 20 acquisition and 12: CPU occupancy rate of 30 acquisition 23%, then x 1 ＝12：10、y 1 ＝21％，x 2 ＝12：20、y 2 ＝22％，x 3 ＝12：30、y 3 =23%. When i =1, x may be 12:10 and 12:20, or 12:20 and 12:30, the preset time can be set according to actual requirements.
Optionally, the foregoing steps: the taking target data obtained by performing interpolation calculation on the historical data as input data of the fault prediction model may include:
acquiring normal data and abnormal data in the historical data of each target parameter; respectively carrying out interpolation calculation on the normal data and the abnormal data to obtain target data obtained by carrying out interpolation calculation on historical data of each target parameter; the target data is determined as input data to a fault prediction model.
Wherein, the normal data are: the size relation between the preset threshold values corresponding to the target parameters accords with the historical data of a second preset condition; the abnormal data is: and the size relation between the preset threshold values corresponding to the target parameters does not accord with the historical data of the second preset condition. Taking the CPU occupancy rate as an example, assuming that the preset threshold corresponding to the CPU occupancy rate is 90%, the second preset condition is: if the CPU occupancy rate is less than 90%, the CPU occupancy rate less than 90% belongs to normal data, and the CPU occupancy rate greater than or equal to 90% belongs to abnormal data. It is understood that the second preset condition may be set according to a specific target parameter. The preset threshold corresponding to the target parameter can also be set according to actual requirements. It should be noted that, when normal data and abnormal data are distinguished, the magnitude of the target parameter is compared with a preset threshold value according to the value of the target parameter in the historical data.
In the embodiment of the application, different thresholds can be set for different target parameters to distinguish normal data from abnormal data. And because the accuracy of the obtained result is poor when interpolation calculation is carried out between the data with larger difference, the normal data and the abnormal data can be distinguished for interpolation calculation, and the accuracy of the interpolation calculation result can be improved in a certain procedure.
As an alternative embodiment, in order to better understand the fault prediction model provided in the embodiments of the present application, the fault prediction model is further described below.
Firstly, after input data is input into a fault prediction model, the model can firstly carry out time sequence coding by utilizing a position encoding (positional encoding) technology according to a time dimension, and then utilizes an attention mechanism to discover characteristic association of the time sequence dimension, so that the value of a time sequence is fully mined, and more accurate fault probability prediction is carried out.
The time sequence coding formula is as follows: positionEncoding = cos2 (pos/N).
Description of the parameters: in the formula, N represents the time sequence length, pos represents the time sequence number, positionEncoding represents the time position sequence coding, and cos represents the cosine function.
The characteristic correlation formula of the time sequence dimension is as follows:
description of the parameters: q represents the query feature mapping in the model, K represents the feature mapping to be matched in the model, V represents the monitoring data mapping in the model, the input data is subjected to feature extraction of the model to obtain Q, K, V, and Q, K, V is continuously iterated in the model until the fitting of the input data is completed; d k A dimension representing K, such as 256, 512, 1024, or the like; t denotes a matrix transposition operation.
Secondly, aiming at the space dimension, the multi-space dimension feature of the input data is extracted by utilizing the multi-head attribute, so that the feature extraction of the input data is more sufficient.
The spatial dimension feature extraction formula is as follows:
MultiHead(Q，K，V)＝Concat(head1，…，headh)*WO。
description of the parameters: head = Attention (Qi, ki, vi), head represents the result obtained by the aforementioned time Attention, qi is the ith group query feature mapping, ki is the ith group to-be-matched feature mapping, and Vi is the ith group monitoring data mapping; multiHead stands for multi-feature fusion, concat for feature cascade fusion, and WO for feature fusion matrices.
Through the characteristic extraction process, the output result of the model can be more accurate.
Finally, in order to better understand the technical solutions provided in the embodiments of the present application, a specific embodiment is further explained as an example below.
From the perspective of an operator, the implementation process of the network slice is orchestration and deployment, and the corresponding functional entities may include: a Communication Services Management Function (CSMF), a slice management function (NSMF), a sub-slice management function (NSSMF), and a management and orchestration function (MANO), as shown in fig. 2.
1. The user may subscribe to the network slice with the operator and send the service requirements regarding the target communication service (i.e., network slice requirements) to the server. After receiving the service requirement, the server submits the service requirement to the CSMF.
2. The CSMF is responsible for converting the Service requirements into network slice related requirements, completing the conversion from the user requirements to a Service Level Agreement (SLA), and then submitting the network slice related requirements obtained by the conversion to the NSMF.
3. After receiving the network slice related requirements sent by the CSMF, the NSMF parses the network slice related requirements, such as to evaluate feasibility of the request. If the service cannot be provided, the request is deemed not to be feasible, and the request is rejected. If the service can be provided, the request is considered to be feasible.
In the case that the request is available, the server may perform obtaining the historical data, and predict, according to the historical data and through a fault prediction model, a probability that a physical network device where a target network slice that has been used historically and meets the service requirement is located fails.
The NSMF may then determine a target network slice (i.e., a network slice entity (NSI)) that may be assigned to the target communication traffic based on the probability of the physical network device failing, such as determining whether the target network slice is available and, if so, shared with other communication traffic. If an existing NSI is available and can be shared, then NSMF uses the existing NSI; otherwise, if the failure probability of the physical network device is greater than the preset probability, if the available NSI is not found yet, the NSMF creates a new NSI (i.e., a second network slice) according to the SLA.
After determining the network slice entity allocated to the target communication service, the NSMF may extract the network slice subnet related requirements from the network slice related requirements, and send the network slice subnet related requirements to the NSSMF.
4. The NSSMF is divided into a radio access network RAN, a transmission network TN and a core network CN, and the NSSMF can respectively complete the management and the arrangement of the sliced subnet examples (NSSI) of the radio network, the transmission network and the core network according to the requirement sent by the NSMF, apply for corresponding resources (namely the target network slice or the second network slice), and perform full-life cycle management on the sub-slices.
5. The NSMF associates an NSSI with a corresponding NSI.
6. The MANO completes the deployment of each sub-slice and the network, computing and storage resources relied upon on the network function virtualization infrastructure, and then notifies the user that the slice deployment is complete and communication services are available.
The above is a description of the network slice allocation method provided in the embodiment of the present application.
To sum up, according to the technical solution provided in the embodiment of the present application, when a server receives a network slice request about a target communication service sent by a user equipment, historical data of target parameters (such as at least one of memory occupancy, CPU occupancy, and disk space occupancy) of a physical network device where a target network slice (i.e., a network slice that has been used historically and satisfies the network slice request) is located is first obtained based on the network slice request, then input data of a failure prediction model is obtained based on the historical data, then the input data is input into the model, a probability of failure occurrence of the physical network device where the target network slice is located is predicted, and finally, a network slice is allocated to the target communication service according to the probability of failure occurrence of the physical network device. The smaller the failure probability is, the higher the reliability of the physical network device is, and the higher the reliability of the network slice deployed on the physical network device is, so that the network slice is allocated to the target communication service in combination with the failure probability of the physical network device, which is beneficial to reducing the occurrence of the situation that the target communication service cannot be normally performed due to the failure of the physical network device, optimizing the allocation strategy of the network slice, and improving the intelligence of the allocation strategy of the network slice.
With the above description of the network slice allocation method according to the embodiment of the present application, a network slice allocation apparatus according to the embodiment of the present application will be described below with reference to the accompanying drawings.
As shown in fig. 3, an embodiment of the present application further provides a network slice allocation apparatus, which is applied to an electronic device.
Wherein the network slice allocating apparatus may include:
a receiving module 301, configured to receive a network slice request sent by a user equipment regarding a target communication service.
Wherein the network slice request includes a network slice requirement parameter of the target communication service.
An obtaining module 302, configured to obtain historical data of a target parameter of a physical network device where the target network slice is located.
Wherein the target network slice is a network slice that has been historically used and satisfies the network slice request; the target parameters include: at least one of memory occupancy, CPU occupancy, and disk space occupancy.
And the data processing module 303 is configured to obtain input data of a fault prediction model based on the historical data.
The prediction module 304 is configured to input the input data into the fault prediction model, and obtain a fault probability corresponding to the physical network device.
An allocating module 305, configured to allocate a network slice to the target communication service according to the failure probability corresponding to the physical network device.
Optionally, the allocating module 305 may include:
and the determining unit is used for sequentially determining whether the target network slices corresponding to the physical network equipment meet a first preset condition according to the sequence of the fault probability from small to large.
Wherein the first preset condition comprises: the target network slice exists and can carry the target communication traffic.
And the first allocation unit is used for allocating a first target network slice meeting the first preset condition to the target communication service under the condition that the fault probability is smaller than the preset probability.
Optionally, the allocating module 305 may further include:
and the creating unit is used for creating a second network slice meeting the network slice request if the fault probability is greater than or equal to the preset probability and the target network slice meeting the first preset condition does not exist yet in the process of sequentially determining whether the target network slices corresponding to the physical network equipment meet the first preset condition according to the sequence from small fault probability to large fault probability.
A second allocating unit, configured to allocate the second network slice to the target communication service.
Optionally, the data processing module 303 may include:
and the data processing unit is used for taking the historical data as input data of the fault prediction model or taking target data obtained by interpolation calculation of the historical data as the input data of the fault prediction model.
Optionally, the data processing unit may include:
and the acquisition subunit is used for acquiring normal data and abnormal data in the historical data of each target parameter.
Wherein the normal data is: historical data with the size relation between preset threshold values corresponding to the target parameters meeting a second preset condition, wherein the abnormal data are as follows: and the size relation between the historical data and the preset threshold value does not accord with the historical data of the second preset condition.
And the data processing subunit is used for respectively carrying out interpolation calculation on the normal data and the abnormal data to obtain the target data obtained by carrying out interpolation calculation on the historical data.
A determining subunit, configured to determine the target data as input data of the fault prediction model.
Optionally, the apparatus may further include:
the first determination module is used for determining a first network slice which is located in a preset area range of the current geographic position of the user equipment and is used historically.
A second determining module, configured to determine, as the target network slice, a network slice in the first network slice that satisfies the network slice request.
Optionally, the apparatus may further include:
an evaluation module, configured to evaluate feasibility of the network slice request, and if the network slice request is feasible, the obtaining module 302 performs the step of obtaining historical data of the target parameter of the physical network device where the target network slice is located.
The network slice allocation device provided in the embodiment of the present application can implement each process implemented by the network slice allocation device in the method embodiment shown in fig. 1, and is not described here again to avoid repetition.
In the embodiment of the application, when a server receives a network slice request about a target communication service sent by user equipment, historical data of target parameters (such as at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate) of physical network equipment where a target network slice (i.e. a network slice which is used historically and satisfies the network slice request) is located is obtained based on the network slice request, then input data of a fault prediction model is obtained based on the historical data, then the input data is input into the model, the probability of a fault occurring in the physical network equipment where the target network slice is located is predicted, and finally the network slice is allocated to the target communication service according to the probability of the fault occurring in the physical network equipment. The smaller the failure probability is, the higher the reliability of the physical network device is, and the higher the reliability of the network slice deployed on the physical network device is, so that the network slice is allocated to the target communication service in combination with the failure probability of the physical network device, which is beneficial to reducing the occurrence of the situation that the target communication service cannot be normally performed due to the failure of the physical network device, optimizing the allocation strategy of the network slice, and improving the intelligence of the allocation strategy of the network slice.
The embodiment of the present application further provides an electronic device, which includes a processor and a memory, where the memory stores a program or an instruction that can be executed on the processor, and when the program or the instruction is executed by the processor, the steps of the network slice allocation method embodiment are implemented, and the same technical effect can be achieved, and in order to avoid repetition, details are not repeated here.
The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the foregoing network slice allocation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM, RAM, a magnetic disk, an optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (16)
1. A method for network slice allocation, the method comprising:
receiving a network slicing request about a target communication service sent by user equipment;
acquiring historical data of target parameters of physical network equipment where a target network slice is located; wherein the target network slice is a network slice that has been historically used and satisfies the network slice request; the target parameters include: at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate;
obtaining input data of a fault prediction model based on the historical data;
inputting the input data into the fault prediction model to obtain the fault probability corresponding to the physical network equipment;
and distributing network slices for the target communication service according to the fault probability corresponding to the physical network equipment.
2. The method according to claim 1, wherein the allocating network slices to the target communication service according to the failure probability corresponding to the physical network device comprises:
sequentially determining whether the target network slice corresponding to the physical network equipment meets a first preset condition or not according to the sequence of the fault probability from small to large; wherein the first preset condition comprises: the target network slice is available and can carry the target communication traffic;
and under the condition that the fault probability is smaller than the preset probability, distributing the first target network slice meeting the first preset condition to the target communication service.
3. The method according to claim 2, wherein in the process of sequentially determining whether the target network slice corresponding to the physical network device meets the first preset condition according to the sequence from small to large of the failure probability, the method further comprises:
when the failure probability is larger than or equal to a preset probability and a target network slice which meets the first preset condition does not exist yet, a second network slice which meets the network slice request is created;
allocating the second network slice to the target communication traffic.
4. The method according to claim 1, wherein obtaining input data for a failure prediction model based on the historical data comprises:
and taking the historical data as input data of the fault prediction model, or taking target data obtained by interpolation calculation of the historical data as the input data of the fault prediction model.
5. The method according to claim 4, wherein the using the target data obtained by interpolating the historical data as the input data of the failure prediction model comprises:
acquiring normal data and abnormal data in the historical data of each target parameter; wherein the normal data is: historical data with the size relation between preset threshold values corresponding to the target parameters meeting a second preset condition, wherein the abnormal data are as follows: historical data with the size relation with the preset threshold value not meeting the second preset condition;
performing interpolation calculation on the normal data and the abnormal data respectively to obtain the target data obtained by performing interpolation calculation on the historical data;
determining the target data as input data for the fault prediction model.
6. The network slice allocation method of claim 1, wherein prior to the obtaining of the historical data of the target parameter of the physical network device where the target network slice is located, the method further comprises:
determining a first network slice which is located in a preset area range of the current geographic position of the user equipment and is used historically;
and determining the network slices meeting the network slice request in the first network slices as the target network slices.
7. The network slice allocation method of claim 1, wherein after receiving the network slice request for the target communication service sent by the user equipment, the method further comprises:
evaluating feasibility of the network slice request;
and in the case that the network slice request is available, performing the step of obtaining historical data of the target parameter of the physical network device where the target network slice is located.
8. An apparatus for network slice distribution, the apparatus comprising:
the receiving module is used for receiving a network slicing request about a target communication service sent by user equipment;
the acquisition module is used for acquiring historical data of target parameters of physical network equipment where the target network slice is located; wherein the target network slice is a network slice that has been historically used and satisfies the network slice request; the target parameters include: at least one of memory occupancy rate, CPU occupancy rate and disk space occupancy rate;
the data processing module is used for obtaining input data of a fault prediction model based on the historical data;
the prediction module is used for inputting the input data into the fault prediction model to obtain the fault probability corresponding to the physical network equipment;
and the distribution module is used for distributing the network slices for the target communication service according to the fault probability corresponding to the physical network equipment.
9. The network slice assignment device of claim 8, wherein the assignment module comprises:
the determining unit is used for sequentially determining whether the target network slices corresponding to the physical network equipment meet a first preset condition according to the sequence of the fault probability from small to large; wherein the first preset condition comprises: the target network slice is available and can carry the target communication traffic;
and the first allocation unit is used for allocating a first target network slice meeting the first preset condition to the target communication service under the condition that the fault probability is smaller than the preset probability.
10. The network slice assignment device of claim 9, wherein the assignment module further comprises:
the creating unit is used for sequentially determining whether the target network slices corresponding to the physical network equipment meet a first preset condition or not according to the sequence of the fault probability from small to large, and if the fault probability is greater than or equal to the preset probability and no target network slice meeting the first preset condition exists, creating a second network slice meeting the network slice request;
a second allocating unit, configured to allocate the second network slice to the target communication service.
11. The network slice allocation apparatus of claim 8, wherein the data processing module comprises:
and the data processing unit is used for taking the historical data as input data of the fault prediction model or taking target data obtained by interpolation calculation of the historical data as the input data of the fault prediction model.
12. The network slice allocation apparatus of claim 11, wherein the data processing unit comprises:
the acquisition subunit is used for acquiring normal data and abnormal data in the historical data of each target parameter; wherein the normal data is: historical data with the size relation between preset threshold values corresponding to the target parameters meeting a second preset condition, wherein the abnormal data are as follows: historical data with the size relation with the preset threshold value not meeting the second preset condition;
the data processing subunit is used for respectively carrying out interpolation calculation on the normal data and the abnormal data to obtain the target data obtained by carrying out interpolation calculation on the historical data;
a determining subunit, configured to determine the target data as input data of the fault prediction model.
13. The network slice assignment device of claim 8, wherein the device further comprises:
the first determination module is used for determining a first network slice which is located in a preset area range of the current geographic position of the user equipment and is used historically;
and a second determining module, configured to determine, as the target network slice, a network slice in the first network slice that satisfies the network slice request.
14. The network slice assignment device of claim 8, wherein the device further comprises:
and the evaluation module is used for evaluating the feasibility of the network slice request, and the acquisition module executes the step of acquiring the historical data of the target parameters of the physical network device where the target network slice is located under the condition that the network slice request is feasible.
15. An electronic device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions when executed by the processor implementing the steps of the network slice allocation method of any of claims 1 to 7.
16. A readable storage medium, on which a program or instructions are stored, which when executed by a processor, implement the steps of the network slice allocation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210696882.4A CN115225500A (en) | 2022-06-20 | 2022-06-20 | Network slice allocation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210696882.4A CN115225500A (en) | 2022-06-20 | 2022-06-20 | Network slice allocation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115225500A true CN115225500A (en) | 2022-10-21 |
Family
ID=83608862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210696882.4A Pending CN115225500A (en) | 2022-06-20 | 2022-06-20 | Network slice allocation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115225500A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664110A (en) * | 2023-06-08 | 2023-08-29 | 湖北华中电力科技开发有限责任公司 | Electric power marketing digitizing method and system based on business center |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756656A (en) * | 2020-06-05 | 2020-10-09 | 深圳供电局有限公司 | Power communication network resource allocation method based on reliability and historical data |
| CN112636961A (en) * | 2020-12-15 | 2021-04-09 | 国网河南省电力公司信息通信公司 | Virtual network resource allocation method based on reliability and distribution strategy under network slice |
| US20210168031A1 (en) * | 2019-12-02 | 2021-06-03 | At&T Intellectual Property I, L.P. | Management of persistent network slices by a distributed learning system in a 5g or other next generation wireless network |
| CN113630733A (en) * | 2021-06-29 | 2021-11-09 | 广东电网有限责任公司广州供电局 | Network slice distribution method and device, computer equipment and storage medium |
-
2022
- 2022-06-20 CN CN202210696882.4A patent/CN115225500A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210168031A1 (en) * | 2019-12-02 | 2021-06-03 | At&T Intellectual Property I, L.P. | Management of persistent network slices by a distributed learning system in a 5g or other next generation wireless network |
| CN111756656A (en) * | 2020-06-05 | 2020-10-09 | 深圳供电局有限公司 | Power communication network resource allocation method based on reliability and historical data |
| CN112636961A (en) * | 2020-12-15 | 2021-04-09 | 国网河南省电力公司信息通信公司 | Virtual network resource allocation method based on reliability and distribution strategy under network slice |
| CN113630733A (en) * | 2021-06-29 | 2021-11-09 | 广东电网有限责任公司广州供电局 | Network slice distribution method and device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664110A (en) * | 2023-06-08 | 2023-08-29 | 湖北华中电力科技开发有限责任公司 | Electric power marketing digitizing method and system based on business center |
| CN116664110B (en) * | 2023-06-08 | 2024-03-29 | 湖北华中电力科技开发有限责任公司 | Electric power marketing digitizing method and system based on business center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020258920A1 (en) | Network slice resource management method and apparatus | |
| CN110601992B (en) | Data processing method and device of intelligent measurement terminal based on edge calculation | |
| CN113709048A (en) | Routing information sending and receiving method, network element and node equipment | |
| US11894992B2 (en) | Network component management method and network device | |
| CN110602717B (en) | Disaster recovery processing method for 5G network slice | |
| WO2017193850A1 (en) | Access scheduling method and device for terminal, and computer storage medium | |
| CN108632077B (en) | Power business data transmission modeling process and transmission channel determination method | |
| Gudkova et al. | Service failure and interruption probability analysis for licensed shared access regulatory framework | |
| CN111682962B (en) | Power data network fault recovery method, system and storage medium | |
| US11706630B2 (en) | Spectrum management device, system and method, and computer-readable storage medium | |
| CN110430068A (en) | A kind of Feature Engineering method of combination and device | |
| CN115225500A (en) | Network slice allocation method and device | |
| CN110855424B (en) | Method and device for synthesizing asymmetric flow xDR in DPI field | |
| CN108604996B (en) | Strategy transmission method and device in NFV system | |
| CN113342526A (en) | Dynamic management and control method, system, terminal and medium for cloud computing mobile network resources | |
| CN116016150A (en) | Early warning method and device for physical network, electronic equipment and storage medium | |
| CN106912066B (en) | A kind of calculation method and device of KPI Key Performance Indicator | |
| CN112867064A (en) | Load balancing method, device, storage medium and source base station | |
| WO2016070606A1 (en) | Prediction method and device for system capacity | |
| EP3096227A1 (en) | Resource allocation method in distributed clouds | |
| JP2022018901A (en) | Optimization method of wireless communication system, wireless communication system, and program for wireless communication system | |
| Skulysh et al. | Traffic aggregation nodes placement for virtual EPC | |
| CN115643558B (en) | Data processing method and device, electronic equipment and storage medium | |
| EP4170974A1 (en) | Slice service processing method and apparatus, network device, and readable storage medium | |
| CN113965475B (en) | Network slice engineering acceptance method and system |
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 |