CN114364027A - 5G network slice distribution processing method and device and computing equipment - Google Patents
5G network slice distribution processing method and device and computing equipment Download PDFInfo
- Publication number
- CN114364027A CN114364027A CN202011041662.5A CN202011041662A CN114364027A CN 114364027 A CN114364027 A CN 114364027A CN 202011041662 A CN202011041662 A CN 202011041662A CN 114364027 A CN114364027 A CN 114364027A
- Authority
- CN
- China
- Prior art keywords
- slice
- resource allocation
- slice resource
- allocation 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.)
- Pending
Links
Images
Abstract
The invention discloses a distribution processing method, a device and computing equipment of 5G network slices, wherein the method comprises the following steps: receiving a slice resource allocation request sent by at least one terminal; determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request; inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result; the target slice resource allocation result is a slice resource allocation result that minimizes the amount of remaining slice fragment resources among slice resource allocation results matching the slice resource allocation request. By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a 5G network slice allocation processing method, a device and computing equipment.
Background
The fifth generation mobile communication network (5G for short) mainly has 3 application scenarios, namely services such as eMBB enhanced mobile broadband service, mtc low-power-consumption mass-connected internet-of-things service, urrllc low-delay highly reliable autopilot, industrial automation, unmanned aerial vehicle transportation, and the like. The 5G technology is not only upgrading mobile network technology, but also makes application scenarios more complicated and diversified, and the application scenarios put higher demands on network architecture. In order to better support 5G network application scenes and simultaneously reduce network operation cost, 5G introduces a network slicing technology, a large amount of physical network basic equipment forms virtual logic network resources, the virtual logic network resources are divided into small virtual logic network units according to each application scene of the 5G network, information interaction and transmission are carried out among the virtual logic network units in an interface mode, resource logic isolation is carried out through various safety technologies, and a flexible deployment mode of networking on demand is realized.
In the prior art, 5G network slices are directly divided according to the requirements of tenants, the 5G network slices requested by different tenants are different, and after the 5G network is directly divided into a plurality of fragmented slices, a fragmentation phenomenon that residual slice resources cannot be reused exists, the 5G network slices cannot be dynamically and timely adjusted according to flexible and variable practical conditions, the complex application scenes of the 5G network slices cannot be met, various resources of the 5G network slices are wasted and even exhausted under severe conditions, and the problem of long request processing delay is solved.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a method, an apparatus and a computing device for 5G network slice allocation processing that overcome or at least partially solve the above problems.
According to an aspect of the present invention, there is provided a 5G network slice allocation processing method, including:
receiving a slice resource allocation request sent by at least one terminal;
determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request;
inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
and the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
Optionally, the method further comprises: calculating the slice fragment rate of the 5G network; judging whether the slicing fragment rate reaches a preset value; and if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
Optionally, calculating the slice fragmentation rate of the 5G network further comprises: judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices; and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments.
Optionally, the slice fragmentation rate is equal to a ratio of a sum of the amount of slice resources of the slice fragmentation to a maximum available amount of slice resources of the 5G network.
Optionally, inputting the initial slice resource allocation result into the slice resource allocation model, and predicting the target slice resource allocation result of the at least one terminal further includes:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
Optionally, the slice resources include one or more of: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
According to another aspect of the present invention, there is provided a 5G network slice allocation processing apparatus, including:
the receiving module is suitable for receiving a slice resource allocation request sent by at least one terminal;
a first resource allocation module, adapted to determine an initial slice resource allocation result of at least one terminal according to the slice resource allocation request;
the second resource allocation module is suitable for inputting the initial slice resource allocation result into the slice resource allocation model, predicting to obtain a target slice resource allocation result of the at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
and the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
Optionally, the apparatus further comprises:
the early warning module is suitable for calculating the slicing fragmentation rate of the 5G network; judging whether the slicing fragment rate reaches a preset value; and if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
Optionally, the early warning module is further adapted to:
judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices; and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments.
Optionally, the slice fragmentation rate is equal to a ratio of a sum of the amount of slice resources of the slice fragmentation to a maximum available amount of slice resources of the 5G network.
Optionally, the second resource allocation module is further adapted to:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
Optionally, the slice resources include one or more of: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
According to yet another aspect 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 used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the allocation processing method of the 5G network slice.
According to still another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform an operation corresponding to the allocation processing method of the 5G network slice.
According to the distribution processing method, the distribution processing device and the computing equipment of the 5G network slice, the slice resource distribution request sent by at least one terminal is received; determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request; inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result; the target slice resource allocation result is a slice resource allocation result that minimizes the amount of remaining slice fragment resources among slice resource allocation results matching the slice resource allocation request. By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred 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 flowchart illustrating a method for allocating 5G network slices according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for allocating 5G network slices according to another embodiment of the present invention;
FIG. 3 shows a schematic diagram of 5G network slice fragmentation;
fig. 4 is a schematic structural diagram of a 5G network slice allocation processing apparatus according to an embodiment of the present invention;
fig. 5 is 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. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of a 5G network slice allocation processing method provided by an embodiment of the present invention, which can be executed by any computing device with data processing capability, as shown in fig. 1, and the method includes the following steps:
step S110, receiving a slice resource allocation request sent by at least one terminal.
The tenant accesses the 5G network after being authenticated by the terminal equipment in the coverage range of the 5G network signal, and sends a request for applying for the network slice. The terminal equipment can be a smart phone, an automatic driving vehicle-mounted computer, an Internet of things radar sensor and the like.
Step S120, according to the slice resource allocation request, determining an initial slice resource allocation result of at least one terminal.
In the method of this embodiment, first, according to a slice resource allocation request corresponding to a terminal, an initial slice resource allocation result that can satisfy the slice resource allocation request is determined, where the slice resource allocation result is a slice resource allocation policy, and represents a slice resource amount of a network slice allocated to the terminal. Specifically, the 5G radio access network RAN determines a corresponding network slice allocation policy according to a user application scenario according to a service level agreement SLA.
Step S130, inputting the initial slice resource allocation result into the slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result. And the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
The remaining slice resource amount refers to the remaining available slice resource amount in the 5G network after the slice resource is allocated to the at least one terminal according to the target slice resource allocation result.
After the initial slice resource allocation result is determined and obtained directly according to the slice resource allocation request of the tenant, the initial slice resource allocation result is adjusted so that the finally obtained slice resource allocation result is optimal, and slice resources are allocated to the terminal according to the slice resource allocation result obtained through adjustment.
Specifically, an initial slice resource allocation result is adjusted in a machine learning manner, the initial slice resource allocation result is used as input of a slice resource allocation model, the slice resource allocation model finally outputs a target slice resource allocation result through continuous iteration, the finally output target slice resource allocation result can be matched with a slice resource allocation request, and after a network slice is allocated to the terminal according to the target slice resource allocation result, the residual slice fragment resource amount at the time is minimum.
According to the allocation processing method of the 5G network slice provided by the embodiment, a slice resource allocation request sent by at least one terminal is received; determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request; inputting the initial slice resource allocation result into a slice resource allocation model, and predicting to obtain a target slice resource allocation result of at least one terminal; and the target slice resource allocation result is the slice resource allocation result which minimizes the slice fragmentation rate in the slice resource allocation results matched with the slice resource allocation requests. By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
Fig. 2 is a flowchart illustrating a method for allocating 5G network slices according to another embodiment of the present invention, which can be executed by any computing device with data processing capability. As shown in fig. 2, the method comprises the steps of:
step S210, receiving a slice resource allocation request sent by at least one terminal.
The tenant accesses the 5G network after being authenticated by the terminal equipment in the coverage range of the 5G network signal, and sends a request for applying for the network slice. The terminal equipment can be a smart phone, an automatic driving vehicle-mounted computer, an Internet of things radar sensor and the like.
E.g. at tkTime of day, receiving UE terminal equipment
A transmitted slice resource allocation request, where k is a time identity.
Step S220, calculating the slicing fragmentation rate of the 5G network.
And judging the slicing fragmentation rate of the 5G network, namely judging the slicing fragmentation degree of the 5G network. The 5G network may refer to a whole or a local 5G network, for example, the 5G network may be a physically divided 5G network slice divided by administrative areas such as province or city by current communication carriers.
In an alternative manner, the specific implementation manner of this step is: judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices; and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments. The slice fragment refers to a slice resource that cannot be allocated for use any more, that is, a slice resource that cannot cover a slice resource allocation request of a terminal. Fig. 3 shows a schematic diagram of 5G network slice fragmentation, and as shown in fig. 3, slice fragmentation is usually a small amount of resources and cannot be allocated for use any more. In the method, whether a network slice which cannot match a received slice resource allocation request exists in a 5G network or not is judged, and then the slice fragmentation rate is calculated according to the slice resource amount of the slice fragments.
The specific calculation formula is as follows:
where k is the time stamp, r (P)k) Is tkThe slice fragmentation rate at the moment, the numerator of the right equation formula is the sum of the slice resource amounts of the respective slice fragments, and the denominator is the maximum available slice resource amount.
In step S230, it is determined whether the slice fragmentation rate reaches a predetermined value.
In practical application, the preset value can be adjusted according to actual requirements.
And step S240, if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
If the slicing fragmentation rate reaches a preset value, the situation that the 5G network is in a fragmentation state at the moment is indicated, and early warning information is generated and sent to the maintenance terminal. For example, the early warning information is generated and sent to the maintenance terminal through a H5 page, a short message, or a platform tool such as social software, so that a maintenance person at the maintenance terminal side can know the network fragmentation state and process the network fragmentation state in time.
Accordingly, the scheme for representing the early warning process by a calculation formula is as follows:
wherein r (P)k) Is tkThe slice fraction at time, δ, is a predetermined value, g (P)k) A value of 1 indicates that the warning information is transmitted, and 0 indicates that the warning information is not transmitted.
If all the remaining network slices in the wireless network are all slice fragments, at this time, the sum of the slice resource amount of each slice fragment is equal to the difference between the maximum available slice resource amount and the slice resource amount of the used slice, and the slice fragment rate is calculated according to the following formula:
the numerator of the right equation represents the maximum available slice resource amount minus the sum of the used slice resource amounts, that is, the slice resource amounts of the slice fragments which remain free and are not allocated for use any more, and the denominator represents the maximum available slice resource amount.
Further, if the current remaining network slices are all slice fragments, generating early warning information and informing a corresponding maintenance terminal, and ending the method without executing subsequent steps.
Step S250, determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request.
Determining an initial slice resource allocation strategy of each terminal according to the slice resource allocation request, wherein the slice resources comprise: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
E.g. corresponding to the allocated set of 5G network slices as
The maximum available slice resource amount is
The set of computing processor resources occupied by these network slices is
The maximum available computing processor resource is
The memory resources occupied by these network slices are aggregated into
The maximum available amount of memory resources is
The storage resources occupied by these network slices are set as
The maximum amount of available storage resources is
The network slices occupy a set of network bandwidths of
The maximum amount of available network bandwidth resources is
The calculation processor resource, memory resource, storage resource and network bandwidth resource occupied by the network slice are expressed by a mathematical method according to the following formula:
step S260, inputting the initial slice resource allocation result into the slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result, wherein the target slice resource allocation result is a slice resource allocation result which enables the residual slice fragment resource amount to be minimum in the slice resource allocation result matched with the slice resource allocation request.
The remaining slice resource amount refers to the remaining available slice resource amount in the 5G network after the slice resource is allocated to the at least one terminal according to the target slice resource allocation result.
The method comprises the steps of establishing a slice resource allocation model by taking the minimum fragmentation of the network slices as a target and according to constraint rules among the calculation processor resource amount, the memory resource amount, the storage resource amount, the network bandwidth resource amount and the available network slices, continuously and iteratively calculating how to allocate the network slices in a computer machine learning mode to enable the fragmentation to be minimum, solving an optimal target according to a combined optimization idea, if the minimum optimal fragmentation of the network slices is not reached, explaining that the model is not converged, continuously calculating and training a correction model, if the model is converged, stopping the iteration, and dynamically and automatically dividing the network slices according to an allocation strategy obtained by calculation to achieve the fragmentation management and optimization of the network slices.
Specifically, the method comprises the following steps: according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1; calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process; judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not; and if so, taking the nth slice resource allocation result as a target slice resource allocation result. In the first iteration process, the input quantity of the model is an initial slice resource allocation result, an initial residual slice fragment resource quantity is calculated according to the initial slice resource allocation result, and in the subsequent process, iteration is continuously performed on the basis of the initial residual slice fragment resource quantity until the model converges.
The step of judging whether the difference between the second remaining slice fragment resource amount and the first remaining slice fragment resource amount satisfies the model convergence condition may be: judging whether the difference value between the second residual slice fragment resource amount and the first residual slice fragment resource amount is larger than a preset difference value threshold value or not; if so, determining that the model convergence condition is not met; otherwise, determining that the model convergence condition is met. It can also be: and judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount is greater than a preset threshold value or not, wherein the iteration times do not exceed the preset iteration times, if so, determining that the model convergence condition is not met, otherwise, determining that the model convergence condition is met. In practical application, the preset difference threshold value and the preset iteration number can be adjusted according to actual needs.
Specifically, the goal of the slice resource allocation model is:
the constraint conditions are as follows:
the iterative process of machine learning of the slice resource allocation model is to firstly input the current network slicing strategy to calculate the initial fragment quantity f (P)k) Then, the combined and divided slice is re-optimized according to the constraint rule and the slice fragment quantity f' is calculated (P)k) By evaluating the function Δ f (P)k) Calculating a re-optimized combined slice fragment amount f' (P)k) And the last fragment amount f (P)k) The merit function is as follows:
Δf(Pk)＝f'(Pk)-f(Pk)
if the fragment amount f' (P) after slicing is re-optimized and combinedk) Than the last fragment amount f (P)k) If the size of the evaluation function is smaller, the better slicing strategy is accepted, otherwise, the size of the fragments after recombination is larger, the next combination iteration process needs to be abandoned and continued, and in the iteration process, the evaluation function delta f (P) is comparedk) With a predefined model convergence threshold ε if Δ f (P)k)>If epsilon does not reach the maximum iteration number limit lambda, the model is not converged and needs to be continuously iteratively trained to correct the model, namely, f' (P)k) Substitution of f (P)k) Recalculate the new f' (P)k) And otherwise, the model convergence is shown to terminate iteration, and a strategy of obtaining the minimum fragment of the slice in the calculation process of the output machine is used as an optimal distribution scheme.
According to the 5G network slice allocation processing method provided by the embodiment, on one hand, a slice resource allocation model is established by taking the minimization of network slice fragmentation as a target and according to the constraint rule between the resource amount of a calculation processor, the memory resource amount, the storage resource amount, the network bandwidth resource amount and the available network slice amount, how to allocate the network slices to minimize fragmentation is continuously and iteratively calculated in a computer machine learning manner, if the minimum and optimal target of network slice fragmentation is not reached, the model is not converged, the correction model is continuously calculated and trained, if the model is converged, the iteration is stopped, and the network slices are dynamically and automatically divided according to the optimal allocation strategy obtained by calculation, and through the method, the slice resource allocation result which can meet the terminal requirement and minimize slice fragmentation can be determined, the slice distribution is more reasonable, and the fragmentation of slice resources is avoided, so that the purpose of saving the slice resources is achieved. On the other hand, when the situation that a plurality of small spare fragmented slice resources are left but cannot be allocated for use any more is detected, at the moment, the fragmentation rate of the network slice is calculated, if the fragmentation rate of the network slice exceeds a predefined threshold value, the fragmentation of the 5G network slice at the moment is judged to be serious, early warning information is generated, and network operation and maintenance personnel are notified to process the fragmentation early warning in time through some platform tools, so that fragmentation early warning is realized.
Fig. 4 is a schematic structural diagram of an apparatus for allocating 5G network slices according to an embodiment of the present invention, and as shown in fig. 4, the apparatus includes:
a receiving module 41, adapted to receive a slice resource allocation request sent by at least one terminal;
a first resource allocation module 42 adapted to determine an initial slice resource allocation result of at least one terminal according to the slice resource allocation request;
the second resource allocation module 43 is adapted to input the initial slice resource allocation result to the slice resource allocation model, predict a target slice resource allocation result of the at least one terminal, and allocate slice resources to the at least one terminal according to the target slice resource allocation result;
and the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
In an optional manner, the apparatus further comprises:
the early warning module is suitable for calculating the slicing fragmentation rate of the 5G network; judging whether the slicing fragment rate reaches a preset value; and if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
In an optional manner, the early warning module is further adapted to: judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices; and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments.
In an alternative approach, the slice fragmentation rate is equal to the ratio of the sum of the amount of slice resources of the slice fragmentation to the maximum available amount of slice resources of the 5G network.
In an alternative manner, the second resource allocation module 43 is further adapted to:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
In an alternative approach, the slice resources include one or more of: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
An embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the allocation processing method of the 5G network slice in any method embodiment described above.
The executable instructions may be specifically configured to cause the processor to:
receiving a slice resource allocation request sent by at least one terminal;
determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request;
inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
and the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
In an alternative, the executable instructions cause the processor to:
calculating the slice fragment rate of the 5G network;
judging whether the slicing fragment rate reaches a preset value;
and if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
In an alternative, the executable instructions cause the processor to: judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices;
and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments.
In an alternative approach, the slice fragmentation rate is equal to the ratio of the sum of the amount of slice resources of the slice fragmentation to the maximum available amount of slice resources of the 5G network.
In an alternative, the executable instructions cause the processor to:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
In an alternative approach, the slice resources include one or more of the following: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
Fig. 5 is a schematic structural diagram of an embodiment of a computing device according to 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. 5, the computing device may include: a processor (processor)502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. The processor 502 is configured to execute the program 510, and may specifically execute relevant steps in the foregoing embodiment of the allocation processing method for 5G network slices of a computing device.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment 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 506 for storing a program 510. The memory 506 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 510 may specifically be used to cause the processor 502 to perform the following operations:
receiving a slice resource allocation request sent by at least one terminal;
determining an initial slice resource allocation result of at least one terminal according to the slice resource allocation request;
inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
and the target slice resource allocation result is the slice resource allocation result which minimizes the residual slice fragment resource amount in the slice resource allocation results matched with the slice resource allocation requests.
In an alternative, the program 510 causes the processor 502 to:
calculating the slice fragment rate of the 5G network;
judging whether the slicing fragment rate reaches a preset value;
and if the slicing fragmentation rate reaches a preset value, generating early warning information and informing a corresponding maintenance terminal.
In an alternative, the program 510 causes the processor 502 to:
judging whether slice fragments which cannot meet slice resource allocation requests exist in the current remaining network slices;
and if so, calculating the slicing fragment rate according to the slicing resource amount of the slicing fragments.
In an alternative approach, the slice fragmentation rate is equal to the ratio of the sum of the amount of slice resources of the slice fragmentation to the maximum available amount of slice resources of the 5G network.
In an alternative, the program 510 causes the processor 502 to:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after the slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets the model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
In an alternative approach, the slice resources include one or more of the following: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
By the method, the slice resource distribution result which can meet the terminal requirement and can minimize the residual slice fragment resource amount is determined based on the machine learning mode, so that slice distribution is more reasonable, slice resource fragmentation is avoided, and the purpose of saving slice resources is achieved.
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.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
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 distribution processing method of 5G network slices comprises the following steps:
receiving a slice resource allocation request sent by at least one terminal;
determining an initial slice resource allocation result of the at least one terminal according to the slice resource allocation request;
inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of the at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
wherein the target slice resource allocation result is a slice resource allocation result that minimizes the amount of remaining slice fragmentation resources among slice resource allocation results that match the slice resource allocation request.
2. The method of claim 1, wherein the method further comprises:
calculating the slice fragment rate of the 5G network;
judging whether the slicing fragmentation rate reaches a preset value;
and if the slicing fragmentation rate reaches the preset value, generating early warning information and informing a corresponding maintenance terminal.
3. The method of claim 2, wherein the calculating the slice fragmentation rate for the 5G network further comprises:
judging whether slice fragments which cannot meet the slice resource allocation request exist in the current remaining network slices or not;
and if so, calculating the slicing fragment rate according to the slicing resource quantity of the slicing fragments.
4. The method of claim 3, wherein the slice fragmentation rate is equal to a ratio of a sum of slice resource amounts of slice fragmentation to a maximum available slice resource amount of the 5G network.
5. The method of claim 1, wherein the inputting the initial slice resource allocation result into a slice resource allocation model, and predicting a target slice resource allocation result of the at least one terminal further comprises:
according to the slice resource allocation result of the (N-1) th time output by the slice resource allocation model in the iteration process, calculating the first residual slice fragment resource amount after slice resources are allocated according to the slice resource allocation result of the (N-1) th time; n is greater than 1;
calculating the second residual slice fragment resource amount after slice resources are distributed according to the nth slice resource distribution result output by the slice resource distribution model in the iteration process;
judging whether the difference value of the second residual slice fragment resource amount and the first residual slice fragment resource amount meets a model convergence condition or not;
and if so, taking the nth slice resource allocation result as a target slice resource allocation result.
6. The method of any of claims 1-5, wherein the slice resources include one or more of: the system comprises a computing processor resource occupied by the slice, a memory resource occupied by the slice, a storage resource occupied by the slice, and a network bandwidth resource occupied by the slice.
7. An allocation processing apparatus for a 5G network slice, comprising:
the receiving module is suitable for receiving a slice resource allocation request sent by at least one terminal;
a first resource allocation module, adapted to determine an initial slice resource allocation result of the at least one terminal according to the slice resource allocation request;
the second resource allocation module is suitable for inputting the initial slice resource allocation result into a slice resource allocation model, predicting to obtain a target slice resource allocation result of the at least one terminal, and allocating slice resources for the at least one terminal according to the target slice resource allocation result;
wherein the target slice resource allocation result is a slice resource allocation result that minimizes the amount of remaining slice fragmentation resources among slice resource allocation results that match the slice resource allocation request.
8. The apparatus of claim 1, wherein the apparatus further comprises:
the early warning module is suitable for calculating the slicing fragmentation rate of the 5G network; judging whether the slicing fragmentation rate reaches a preset value; and if the slicing fragmentation rate reaches the preset value, generating early warning information and informing a corresponding maintenance terminal.
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 used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the allocation processing method of the 5G network slice in any one of claims 1-6.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the allocation processing method of the 5G network slice according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041662.5A CN114364027A (en) | 2020-09-28 | 2020-09-28 | 5G network slice distribution processing method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041662.5A CN114364027A (en) | 2020-09-28 | 2020-09-28 | 5G network slice distribution processing method and device and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114364027A true CN114364027A (en) | 2022-04-15 |
Family
ID=81089626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011041662.5A Pending CN114364027A (en) | 2020-09-28 | 2020-09-28 | 5G network slice distribution processing method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114364027A (en) |
-
2020
- 2020-09-28 CN CN202011041662.5A patent/CN114364027A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108449286B (en) | Network bandwidth resource allocation method and device | |
| WO2019184445A1 (en) | Service resource allocation | |
| CN111711666B (en) | Internet of vehicles cloud computing resource optimization method based on reinforcement learning | |
| CN111355779B (en) | Service-based Internet of vehicles task unloading method and unloading device thereof | |
| CN109947574B (en) | Fog network-based vehicle big data calculation unloading method | |
| CN111352711B (en) | Multi-computing engine scheduling method, device, equipment and storage medium | |
| CN112887905B (en) | Task unloading method based on periodic resource scheduling in Internet of vehicles | |
| CN109144730B (en) | Task unloading method and device under small cell | |
| CN111711962A (en) | Cooperative scheduling method for subtasks of mobile edge computing system | |
| CN112559187A (en) | Method and system for dynamically allocating tasks to mobile edge computing server | |
| CN114449529A (en) | Resource allocation optimization method and device based on mobile edge calculation and storage medium | |
| CN104158860A (en) | Job scheduling method and job scheduling system | |
| CN116996938A (en) | Internet of vehicles task unloading method, terminal equipment and storage medium | |
| CN112437449A (en) | Joint resource allocation method and area organizer | |
| CN105335313A (en) | Basic data transmission method and apparatus | |
| CN108770014B (en) | Calculation evaluation method, system and device of network server and readable storage medium | |
| CN114364027A (en) | 5G network slice distribution processing method and device and computing equipment | |
| CN116820769A (en) | Task allocation method, device and system | |
| CN116567582A (en) | Vehicle task unloading method and device, electronic equipment and storage medium | |
| CN108900865B (en) | Server, and scheduling method and execution method of transcoding task | |
| EP2930617A1 (en) | Resource management method and device | |
| CN114138466A (en) | Task cooperative processing method and device for intelligent highway and storage medium | |
| Zhao et al. | Optimizing allocation and scheduling of connected vehicle service requests in cloud/edge computing | |
| CN114675845A (en) | Information age optimization method and device, computer equipment and storage medium | |
| KR20130063867A (en) | Method for utilizing network resource in machine-to-machine cloud environment communication and the system thereof |
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 |