CN116997012A - Network slice resource allocation method and device, electronic equipment and storage medium - Google Patents

Abstract

The disclosure provides a method, a device, an electronic device and a storage medium for allocating network slice resources, which comprise the following steps: acquiring a service request of a communication network; determining an access rate and a transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate; and distributing slice resources to the service request based on the resource distribution strategy. In the disclosure, a plurality of service requests to be processed by a communication network are firstly obtained, then the transmission rate and the access rate between the service requests and the communication network are determined, then a resource allocation strategy of the communication network is generated based on the transmission rate and the access rate, and finally the resource allocation strategy is used for allocating slice resources to the service requests.

Description

Network slice resource allocation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of converged communication technologies, and in particular, to a method and apparatus for allocating network slice resources, an electronic device, and a storage medium.

Background

With the rapid development of the power industry and the continuous increase of the number of power user terminals, the wireless network resources for carrying the power service are unbalanced to a certain extent. Therefore, how to alleviate the imbalance of the supply and demand of the wireless network resources becomes a problem to be solved.

In the prior art, this problem is usually solved using an allocation method of network slice resources. Which mainly slices wireless network resources, and then using the sliced network resources to bear the service request sent by the power user. However, the above method does not consider the influence of the type of the service request on the resource allocation process and the access situation of the power user terminal.

Disclosure of Invention

In view of the foregoing, an object of the present disclosure is to provide a method, an apparatus, an electronic device, and a storage medium for allocating network slice resources.

As one aspect of the present disclosure, there is provided a method for allocating network slice resources, including:

acquiring a service request of a communication network;

determining an access rate and a transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate;

and distributing slice resources to the service request based on the resource distribution strategy.

Optionally, the determining the access rate between the service request and the communication network includes:

determining a bandwidth requirement of the service request;

determining an access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests;

Wherein, the access rate is expressed as:

where eta represents the access rate,k is the total number of service requests, b _k Target bandwidth allocated for traffic request k for communication network, d _k Representing the bandwidth requirements of the service request.

Optionally, the determining a transmission rate between the service request and the communication network includes

Determining a target bandwidth allocated by the communication network for the service request;

determining a transmission rate between the service request and the communication network based on the target bandwidth;

wherein the transmission rate is expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, h, of a base station n where the communication network is located _k,m,n Indicating the channel gain between the base station n where the communication network is located and the service request k,representing the interference power of other base stations of the communication network.

Optionally, the generating a resource allocation policy based on the access rate and the transmission rate includes:

generating constraints for the communication network resource allocation based on the transmission rate and a total bandwidth of the communication network;

Generating a resource allocation function of the communication network based on the transmission rate and the access rate;

generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

Optionally, the generating the constraint condition of the communication network resource allocation based on the transmission rate and the total bandwidth of the communication network includes:

generating a first constraint of the communication network resource allocation based on the transmission rate; the method comprises the steps of,

generating a second constraint on the communication network resource allocation based on the total bandwidth;

wherein the first constraint is expressed as:

wherein ,v_k Representing the transmission rate of the service request k,representing a maximum transmission rate between the service request and the communication network;

the second constraint is expressed as:

0<b _k <B

wherein ,b_k Representing the target bandwidth allocated by the communication network for the traffic request k, and B represents the total bandwidth of the communication network.

Optionally, the determining a resource allocation function of the communication network resource based on the constraint condition and the access rate includes:

determining a maximum transmission efficiency of the service request based on the first constraint condition and the level of the service request;

Generating a resource allocation function based on the maximum transmission efficiency and the access rate;

wherein the maximum transmission efficiency is expressed as:

wherein D represents the maximum transmission efficiency, v _k Representing the transmission rate of the service request k,representing service requests and communication networksThe maximum transmission rate between the two, u represents the level of the service request;

the resource allocation function is expressed as:

ω＝max E{η _k ^D }

wherein ω represents the resource allocation function, η _k The access rate of the service request k is indicated, and D indicates the maximum transmission efficiency.

Optionally, the allocating slice resources to the service request based on the resource allocation policy includes:

determining an action cost function and a state cost function of the resource allocation strategy based on a reinforcement learning algorithm;

optimizing the resource allocation strategy based on the action function and the state function to obtain an optimized resource allocation strategy;

slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources;

based on the corresponding relation between the type of the service request and the network slice resource, distributing the slice resource to the service request;

wherein the action cost function is expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,>representing the result of the reinforcement learning algorithm traversing the action cost function;

the state-cost function is expressed as:

wherein ,representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,/a->Representing the result of the reinforcement learning algorithm traversing the state-cost function.

As a second aspect of the present disclosure, the present disclosure further provides an apparatus for allocating network slice resources, including:

a service request acquisition module configured to: acquiring a service request of a communication network;

an allocation policy generation module configured to: determining an access rate and a transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate;

A slice resource allocation module configured to: and distributing slice resources to the service request based on the resource distribution strategy.

Optionally, the determining the access rate between the service request and the communication network includes:

determining a bandwidth requirement of the service request;

determining an access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests;

wherein, the access rate is expressed as:

where eta represents the access rate,k is the total number of service requests, b _k Target bandwidth allocated for traffic request k for communication network, d _k Representing the bandwidth requirements of the service request.

Optionally, the determining a transmission rate between the service request and the communication network includes determining a target bandwidth allocated by the communication network for the service request;

determining a transmission rate between the service request and the communication network based on the target bandwidth;

wherein the transmission rate is expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, h, of a base station n where the communication network is located _k,m,n Indicating the channel gain between the base station n where the communication network is located and the service request k,representing the interference power of other base stations of the communication network.

Optionally, the generating a resource allocation policy based on the access rate and the transmission rate includes:

generating constraints for the communication network resource allocation based on the transmission rate and a total bandwidth of the communication network;

generating a resource allocation function of the communication network based on the transmission rate and the access rate;

generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

Optionally, the allocating slice resources to the service request based on the resource allocation policy includes:

determining an action cost function and a state cost function of the resource allocation strategy based on a reinforcement learning algorithm;

optimizing the resource allocation strategy based on the action function and the state function to obtain an optimized resource allocation strategy;

slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources;

based on the corresponding relation between the type of the service request and the network slice resource, distributing the slice resource to the service request;

Wherein the action cost function is expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,>representing the result of the reinforcement learning algorithm traversing the action cost function;

the state-cost function is expressed as:

wherein ,representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,/a->Representing the result of the reinforcement learning algorithm traversing the state-cost function.

As a third aspect of the disclosure, the disclosure further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the above-mentioned network slice resource allocation method provided by the disclosure when executing the program.

As a fourth aspect of the disclosure, the disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the above.

As described above, in the present disclosure, a plurality of service requests to be processed by a communication network are first obtained, then a transmission rate and an access rate between the service requests and the communication network are determined, then a resource allocation policy of the communication network is generated based on the transmission rate and the access rate, and finally the service requests are allocated with slice resources by using the resource allocation policy.

Drawings

In order to more clearly illustrate the technical solutions of the present disclosure or related art, the drawings required for the embodiments or related art description will be briefly described below, and it is apparent that the drawings in the following description are only embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.

Fig. 1A is a schematic diagram of a method for allocating network slice resources according to an embodiment of the present disclosure.

Fig. 1B is a schematic diagram of a method for generating a resource allocation policy according to an embodiment of the present disclosure.

Fig. 1C is a schematic diagram of a slice resource allocation method according to an embodiment of the present disclosure.

Fig. 2 is a schematic structural diagram of a network slice resource allocation device according to an embodiment of the present disclosure.

Fig. 3 is a schematic structural diagram of an electronic device according to a network slice resource allocation method according to an embodiment of the present disclosure.

Detailed Description

For the purposes of promoting an understanding of the principles and advantages of the disclosure, reference will now be made to the embodiments illustrated in the drawings and specific language will be used to describe the same.

It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present disclosure should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present disclosure pertains. The terms "first," "second," and the like, as used in embodiments of the present disclosure, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.

With the rapid development of the power industry and the continuous increase of the number of power user terminals, the wireless network resources for carrying the power service are unbalanced to a certain extent. Therefore, how to alleviate the imbalance of the supply and demand of the wireless network resources becomes a problem to be solved.

In the prior art, this problem is usually solved using an allocation method of network slice resources. The method mainly comprises the steps of slicing wireless network resources, and then using the sliced network resources to bear service requests sent by power users. However, the above method does not consider the influence of the type of the service request on the resource allocation process and the access situation of the power user terminal.

In order to solve the above problems, the present disclosure provides a method, an apparatus, an electronic device, and a storage medium for allocating network slice resources. By the method, a plurality of service requests to be processed by the communication network are firstly acquired in the disclosure, then the types of the service requests are clarified, the transmission rate and the access rate between the service requests and the communication network are determined, then the disclosure generates a resource allocation strategy of the communication network based on the transmission rate and the access rate, and finally network slice resources are allocated to the service requests of different types by using the resource allocation strategy.

In the present disclosure, the problem of network slice resource allocation in the prior art is abstracted into an optimization problem with access rate and transmission rate as optimization targets, and a corresponding resource allocation policy is finally generated. And then, in the present disclosure, the communication network is sliced according to the resource allocation policy, so as to obtain a plurality of network slice resources which can meet the requirements of the service request access rate and the transmission rate. Finally, the present disclosure matches corresponding network slice resources (i.e., network slice resources corresponding to the service request type) for the service request according to its different types.

In the disclosure, reasonable distribution of network resource slices is finally realized through the method. The access rate and the resource utilization rate of the communication network and the matching degree between the communication network and the service request are maximized while the power service communication requirement is met, and more reasonable network resource slice allocation in a power service scene is realized.

Having described the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are specifically described below.

Fig. 1A is a schematic diagram of a method for allocating network slice resources according to an embodiment of the present disclosure.

The method for allocating network slice resources shown in fig. 1A further includes the following steps:

step S10: a service request of a communication network is obtained.

In some alternative embodiments, the resource allocation method in this embodiment may be implemented by a resource allocation system. Specifically, the resource allocation system may first obtain a number of service requests from the user, and then analyze the service requests to obtain an analysis result (e.g., analyze a type of the service request, etc.). And finally, distributing corresponding network slice resources to different types of service requests according to the acquired analysis result.

In some alternative embodiments, the user request obtained by the resource allocation system may be a variety of different types of service requests. Because the types of service requests are different, the network resources required for these service requests are also different. Thus, the resource allocation system in this disclosure need only match the corresponding network slice resources for different types of service requests.

Step S20: and determining the access rate and the transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate.

Fig. 1B is a schematic diagram of a method for generating a resource allocation policy according to an embodiment of the present disclosure.

In some alternative embodiments, as shown in fig. 1B, step S20 specifically includes:

s201: based on the transmission rate and a total bandwidth of the communication network, constraints of the communication network resource allocation are generated.

In some alternative embodiments, the determining process of the transmission rate in step S201 specifically includes:

s2011: and determining a target bandwidth allocated by the communication network for the service request.

S2012: and determining the transmission rate between the service request and the communication network based on the target bandwidth.

S202: a resource allocation function of the communication network is generated based on the transmission rate and the access rate.

In some alternative embodiments, the determining the access rate in step S202 specifically includes:

s2021: and determining the bandwidth requirement of the service request.

S2022: an access rate between the service request and the communication network is determined based on the bandwidth requirement and the number of service requests.

In some alternative embodiments, the determining of the resource allocation function in step S202 specifically includes:

S2023: and determining the maximum transmission efficiency of the service request based on the first constraint condition and the level of the service request.

S2024: generating a resource allocation function based on the maximum transmission efficiency and the access rate.

In some alternative embodiments, after acquiring a number of service requests sent by a user, the resource allocation system may allocate corresponding network resources for the service requests. However, since network resources for wireless communication are limited, if network resources are allocated to service requests using existing resource allocation methods (e.g., equally dividing network resources, etc.), the allocable resources of the wireless communication network may be exhausted, and the network may be unstable. Therefore, it is necessary to perform slicing processing on the network resources of the communication network, and then allocate the sliced network resources to corresponding service requests.

In some alternative embodiments, in the process of slicing the communication network, the situation that the access rate and the transmission rate between the service request and the communication network are not considered may cause the problem of uneven resource allocation of the communication network (i.e. a larger amount of resources is allocated for the service request with less network resource requirements, and a smaller amount of resources is allocated for the service request with greater network resource requirements).

In some alternative embodiments, to solve this problem, the resource allocation system in the present disclosure may pre-analyze service requests to be accessed to the communication network, determine the access rate and the transmission rate between the service requests and the communication network, and then slice the communication network based on the access rate and the transmission rate. Finally, the resources after slicing can be allocated to the corresponding service requests. By doing so (i.e., taking into account the effects of access rate, transmission rate, etc.), the present disclosure can allocate more desirable slice resources for a service request (i.e., allocate the same amount of slice resources as required by the service request).

In some alternative embodiments, the foregoing detailed procedure is that the resource allocation system may determine the bandwidth requirement of the service request first, and then determine the access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests. And the resource allocation system may also determine a target bandwidth allocated by the communication network for the service request, and then determine a transmission rate between the service request and the communication network based on the target bandwidth. And then generates a resource allocation policy based on the obtained access rate and transmission rate.

In some alternative embodiments, the foregoing access rates may be expressed as:

where eta represents the access rate,k is the total number of service requests, b _k Target bandwidth allocated for traffic request k for communication network, d _k Representing the bandwidth requirements of the service request.

In some alternative embodiments, the foregoing transmission rate may be expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, h, of a base station n where the communication network is located _k,m,n Indicating the channel gain between the base station n where the communication network is located and the service request k,representing the interference power of other base stations of the communication network.

In some alternative embodiments, after determining the access rate and transmission rate between the service request and the communication network, the resource allocation system may then generate a resource allocation policy based on the access rate and transmission rate. In particular, the resource allocation system may generate constraints for allocation of resources of the communication network based on the transmission rate and the total bandwidth of the communication network. A resource allocation function of the communication network is then generated based on the transmission rate and the access rate. Finally, a resource allocation policy of the communication network is generated based on the constraint condition and the resource allocation function.

In some alternative embodiments, the foregoing constraint generating process may be specifically that the resource allocation system may generate the first constraint of the communication network resource allocation based on the transmission rate; and generating a second constraint on the communication network resource allocation based on the total bandwidth.

In some alternative embodiments, the aforementioned first constraint may be expressed as:

wherein ,v_k Representing the transmission rate of the service request k,representing the maximum transmission rate between the service request and the communication network.

In some alternative embodiments, the aforementioned second constraint may be expressed as:

0<b _k <B

wherein ,b_k Representing the target bandwidth allocated by the communication network for the traffic request k, and B represents the total bandwidth of the communication network.

In some alternative embodiments, the foregoing process of generating the resource allocation function may specifically be determining a maximum transmission efficiency of the service request based on the first constraint condition and the level of the service request, and then generating the resource allocation function based on the maximum transmission efficiency and the access rate.

In some alternative embodiments, the aforementioned maximum transmission efficiency may be expressed as:

wherein D represents the maximum transmission efficiency, v _k Representing the transmission rate of the service request k, Representing the maximum transmission rate between the service request and the communication network, u representing the level of the service request;

in some alternative embodiments, the foregoing resource allocation function may be expressed as:

ω＝max E{η _k ^D }

wherein ω represents the resource allocation function, η _k The access rate of the service request k is indicated, and D indicates the maximum transmission efficiency.

S203: generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

In some alternative embodiments, after deriving the resource allocation function, the resource allocation system may then use the resource allocation function and the constraints together as a resource allocation policy for the communication network resource allocation. And then use this resource allocation policy to allocate resources of the communication network (i.e., slice the communication network resources).

In some alternative embodiments, the aforementioned resource allocation policy is expressed as:

0<b _k <B

ω＝max E{η _k ^D }

wherein ,v_k Representing the transmission rate of the service request k,representing the maximum transmission rate between a service request and a communication network, b _k Representing a target bandwidth allocated by the communication network for the traffic request k, B representing a total bandwidth of the communication network, ω representing a resource allocation function, η _k The access rate of the service request k is indicated, and D indicates the maximum transmission efficiency.

Step S30: and distributing slice resources to the service request based on the resource distribution strategy.

Fig. 1C is a schematic diagram of a slice resource allocation method according to an embodiment of the present disclosure.

In some alternative embodiments, as shown in fig. 1C, step S30 specifically includes:

s301: an action cost function and a state cost function of the resource allocation strategy are determined based on a reinforcement learning algorithm.

S302: and optimizing the resource allocation strategy based on the action function and the state function to obtain the optimized resource allocation strategy.

S303: and slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources.

S304: and distributing the slicing resources to the service request based on the corresponding relation between the type of the service request and the network slicing resources.

In some alternative embodiments, the resource allocation system, after deriving the resource allocation policy, may then use the resource allocation policy to allocate resources of the communication network (i.e., slice the communication network). However, when performing resource allocation, the accuracy of the resource allocation process may be affected by the resource allocation action and the state of the communication network (i.e., the network after the resource allocation may still not meet the service request in the system), so the action cost function and the state cost function of the resource allocation policy are also obtained in the present disclosure, and then the resource allocation policy is optimized based on the two functions, and then the optimized resource allocation policy is used to perform slicing (resource partitioning) on the communication network.

In some alternative embodiments, the foregoing action cost function may be expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,>representing the result of the reinforcement learning algorithm traversing the action cost function;

in some alternative embodiments, the aforementioned state-cost function may be expressed as:

wherein ,representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,/a->Representing the result of the reinforcement learning algorithm traversing the state-cost function.

In some alternative embodiments, after the resource allocation system determines the action cost function and the state cost function of the resource allocation policy, the resource allocation system may optimize the resource allocation policy based on the action function and the state function, thereby obtaining an optimized resource allocation policy. And then slicing the communication network based on the optimized resource allocation strategy to finally obtain network slicing resources. It will be appreciated that the network slice resources in this disclosure are generated in consideration of the relationship between the service request and the communication network (e.g., access rate, transmission rate, etc.), and thus the network slice resources can be more satisfied with the service request and the requirements of the communication network.

In some alternative embodiments, after obtaining the network slice resources, the resource allocation system may establish a correspondence between the network slice resources and a predetermined type of service request (refer to step S10), and then allocate the corresponding network slice resources to the service request based on the correspondence (e.g. the type of service request is "search request", and then allocate the network slice resources for "search" for this request).

In some alternative embodiments, a resource allocation network framework is also designed in the present disclosure for implementing the resource allocation procedure in the present disclosure. Specifically, the resource allocation network framework in the present disclosure includes four layers of a control layer, a service layer, a slice layer, and a resource layer. It flexibly defines Virtual Network Functions (VNFs) of network slices by using Network Function Virtualization (NFV) and Software Defined Networking (SDN) technologies to implement virtualization of network resources and define open interfaces between the various layers.

In some optional embodiments, the foregoing resource layer refers to all available physical resources and virtual resources, where the physical resources are virtualized in the resource layer to become virtual resources, then an SDN controller in the control layer controls allocation of the virtual resources, and a slice controller is used to implement arrangement of the virtual resources to complete arrangement of slices, so as to implement customized services. The resource layer is not embodied in the algorithm design because only virtual resources are considered in the algorithm, and the virtualization process of physical resources is not considered.

In some alternative embodiments, the control layer is critical to achieving reasonable and efficient network resource allocation, including SDN controllers and slice controllers. The SDN controller is responsible for the management of network functions, namely, virtualized physical resources are allocated for services and slices according to the proposed reinforcement learning-based network resource allocation algorithm, and the allocation of network resources is completed. The slice controller is responsible for arranging slices for service adaptation according to service requirements and types and virtual resources distributed according to the SDN controller, and providing targeted slice services for the service.

In some alternative embodiments, the slice layer is an instance of a slice, and the slice controller in the control layer orchestrates the slicing of the traffic at the slice layer according to virtual resources and traffic types allocated to the traffic, and then associates the slice with the traffic and allocates resources to the traffic, thereby completing the resource allocation process.

In some alternative embodiments, the service layer uses an identifier-based service distinguishing method to transmit service information to the SDN controller of the control layer, where the specific principle of the method is as follows: because each service terminal can only bear one power service, when the communication network terminal receives a power service request, service identification can be added to the power service in a data packet, so that the received power service types are distinguished, and a basis is provided for the distribution of power service resource slices.

In some alternative embodiments, considering that only the upper layer protocol can parse the data packet, the meaningless data bits in the application layer data packet are considered to be used as the service identification bits, so that when the resource slice is allocated to the service, the service identification can be used as the basis for allocating the resource slice, and the suitability of the power service and the network resource slice is improved.

In some optional embodiments, after marking the service in the data packet according to different service types, the SDN controller of the control layer parses the service identification bit in the data packet, after parsing is completed, the service type information and the network resource slice information in the service identification are transmitted to the slice controller, and the slice controller allocates resource slices to the power service according to suitability of the service type and the resource slices, thereby improving the adaption accuracy of the power service and the resource slices.

In some alternative embodiments, the control layer, the slice layer and the service layer are the parts required to be considered by the proposed reinforcement learning-based network resource allocation algorithm, wherein the implementation of the algorithm is to be completed by the control layer, virtual network resources virtualized on physical resources in the resource layer are allocated according to the algorithm by the SDN controller, and the slice controller schedules slices.

In summary, in the present disclosure, a plurality of service requests to be processed by a communication network are first obtained, then the types of the service requests are clarified, the transmission rate and the access rate between the service requests and the communication network are determined, then a resource allocation policy of the communication network is generated based on the transmission rate and the access rate, and finally network slice resources are allocated to different types of service requests by using the resource allocation policy.

In the present disclosure, the problem of network slice resource allocation in the prior art is abstracted into an optimization problem with access rate and transmission rate as optimization targets, and a corresponding resource allocation policy is finally generated. And then, in the present disclosure, the communication network is sliced according to the resource allocation policy, so as to obtain a plurality of network slice resources which can meet the requirements of the service request access rate and the transmission rate. Finally, the present disclosure matches corresponding network slice resources (i.e., network slice resources corresponding to the service request type) for the service request according to its different types.

In the disclosure, reasonable distribution of network resource slices is finally realized through the method. The access rate and the resource utilization rate of the communication network and the matching degree between the communication network and the service request are maximized while the power service communication requirement is met, and more reasonable network resource slice allocation in a power service scene is realized.

Based on the same technical concept, the present disclosure further provides a device for allocating network slice resources, which corresponds to the method of any embodiment, and the method for allocating network slice resources according to any embodiment of the present disclosure may be implemented by using the device for allocating network slice resources provided by the present disclosure.

Fig. 2 is a schematic structural diagram of a network slice resource allocation device according to an embodiment of the present disclosure.

The allocation device of network slice resources shown in fig. 2 further comprises the following modules:

a service request acquisition module 10, an allocation policy generation module 20, and a slice resource allocation module 30;

wherein the service request acquisition module 10 is configured to: a service request of a communication network is obtained.

The allocation policy generation module 20 is configured to: and determining the access rate and the transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate. The method specifically comprises the following steps:

determining a bandwidth requirement of the service request;

determining an access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests;

Wherein, the access rate is expressed as:

/>

where eta represents the access rate,k is the total number of service requests, b _k Target bandwidth allocated for traffic request k for communication network, d _k Representing bandwidth requirements of the service request;

determining a target bandwidth allocated by the communication network for the service request;

determining a transmission rate between the service request and the communication network based on the target bandwidth;

wherein the transmission rate is expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, hk, of the base station n where the communication network is located _,m,n Indicating the channel gain between the base station n where the communication network is located and the service request k,representing interference power of other base stations of the communication network;

generating constraints for the communication network resource allocation based on the transmission rate and a total bandwidth of the communication network; comprising the following steps:

generating a first constraint of the communication network resource allocation based on the transmission rate; the method comprises the steps of,

generating a second constraint on the communication network resource allocation based on the total bandwidth;

Wherein the first constraint is expressed as:

wherein ,v_k Representing the transmission rate of the service request k,representing a maximum transmission rate between the service request and the communication network;

the second constraint is expressed as:

0<b _k <B

wherein ,b_k Representing a target bandwidth allocated by the communication network for the service request k, and B representing a total bandwidth of the communication network;

generating a resource allocation function of the communication network based on the transmission rate and the access rate; comprising the following steps:

determining a maximum transmission efficiency of the service request based on the first constraint condition and the level of the service request;

generating a resource allocation function based on the maximum transmission efficiency and the access rate;

wherein the maximum transmission efficiency is expressed as:

wherein D represents the maximum transmission efficiency, v _k Representing the transmission rate of the service request k,representing the maximum transmission rate between the service request and the communication network, u representing the level of the service request;

the resource allocation function is expressed as:

ω＝max E{η _k ^D }

wherein the method comprises the steps ofω represents the resource allocation function, η _k The access rate of the service request k is represented, and D represents the maximum transmission efficiency;

generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

The slice resource allocation module 30 is configured to: and distributing slice resources to the service request based on the resource distribution strategy. The method specifically comprises the following steps:

determining an action cost function and a state cost function of the resource allocation strategy based on a reinforcement learning algorithm;

optimizing the resource allocation strategy based on the action function and the state function to obtain an optimized resource allocation strategy;

slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources;

based on the corresponding relation between the type of the service request and the network slice resource, distributing the slice resource to the service request;

wherein the action cost function is expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,>representing the result of the reinforcement learning algorithm traversing the action cost function;

the state-cost function is expressed as:

wherein ,Representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,/a->Representing the result of the reinforcement learning algorithm traversing the state-cost function.

Based on the same technical concept, the present disclosure also provides an electronic device corresponding to the method of any embodiment, which includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the method for allocating network slice resources according to any embodiment.

Fig. 3 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 implement communication connections therebetween within the device via a bus 1050.

The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit ), microprocessor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing relevant programs to implement the technical solutions provided in the embodiments of the present disclosure.

The Memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. Memory 1020 may store an operating system and other application programs, and when the embodiments of the present specification are implemented in software or firmware, the associated program code is stored in memory 1020 and executed by processor 1010.

The input/output interface 1030 is used to connect with an input/output module for inputting and outputting information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.

Communication interface 1040 is used to connect communication modules (not shown) to enable communication interactions of the present device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).

Bus 1050 includes a path for transferring information between components of the device (e.g., processor 1010, memory 1020, input/output interface 1030, and communication interface 1040).

It should be noted that although the above-described device only shows processor 1010, memory 1020, input/output interface 1030, communication interface 1040, and bus 1050, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.

The electronic device of the foregoing embodiment is configured to implement the corresponding method for allocating network slice resources in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.

Based on the same technical concept, corresponding to the method of any embodiment, the disclosure further provides a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores computer instructions, where the computer instructions are configured to cause the computer to perform the method for allocating network slice resources according to any embodiment.

The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.

The storage medium of the foregoing embodiment stores computer instructions for causing the computer to execute the network slice resource allocation method according to any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein.

Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined under the idea of the present disclosure, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present disclosure as described above, which are not provided in details for the sake of brevity.

Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the embodiments of the present disclosure. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the embodiments of the present disclosure, and this also accounts for the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform on which the embodiments of the present disclosure are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.

While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

The disclosed embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalents, improvements, and the like, which are within the spirit and principles of the embodiments of the disclosure, are intended to be included within the scope of the disclosure.

Claims (14)

1. A method for allocating network slice resources, comprising:

acquiring a service request of a communication network;

determining an access rate and a transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate;

and distributing slice resources to the service request based on the resource distribution strategy.

2. The method of claim 1, wherein said determining an access rate between the service request and the communication network comprises:

determining a bandwidth requirement of the service request;

determining an access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests;

wherein, the access rate is expressed as:

where eta represents the access rate,k is the total number of service requests, b _k Target bandwidth allocated for traffic request k for communication network, d _k Representing the bandwidth requirements of the service request.

3. The method of claim 2, wherein said determining a transmission rate between said service request and said communication network comprises

Determining a target bandwidth allocated by the communication network for the service request;

determining a transmission rate between the service request and the communication network based on the target bandwidth;

wherein the transmission rate is expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, h, of a base station n where the communication network is located _k,m,n Indicating the base station n and the base station where the communication network is locatedThe channel gain between service requests k,representing the interference power of other base stations of the communication network.

4. The method of claim 3, wherein the generating a resource allocation policy based on the access rate and the transmission rate comprises:

generating constraints for the communication network resource allocation based on the transmission rate and a total bandwidth of the communication network;

Generating a resource allocation function of the communication network based on the transmission rate and the access rate;

generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

5. A method according to claim 3, wherein said generating constraints of said communication network resource allocation based on said transmission rate and a total bandwidth of said communication network comprises:

generating a first constraint of the communication network resource allocation based on the transmission rate; the method comprises the steps of,

generating a second constraint on the communication network resource allocation based on the total bandwidth;

wherein the first constraint is expressed as:

wherein ,v_k Representing the transmission rate of the service request k,representing a maximum transmission rate between the service request and the communication network;

the second constraint is expressed as:

0<b _k <B

wherein ,b_k Representing the target bandwidth allocated by the communication network for the traffic request k, and B represents the total bandwidth of the communication network.

6. The method of claim 5, wherein said determining a resource allocation function for the communication network resource based on the constraint and the access rate comprises:

Determining a maximum transmission efficiency of the service request based on the first constraint condition and the level of the service request;

generating a resource allocation function based on the maximum transmission efficiency and the access rate;

wherein the maximum transmission efficiency is expressed as:

wherein D represents the maximum transmission efficiency, v _k Representing the transmission rate of the service request k,representing the maximum transmission rate between the service request and the communication network, u representing the level of the service request;

the resource allocation function is expressed as:

ω＝max E{η _k ^D }

wherein ω represents the resource allocation function, η _k The access rate of the service request k is indicated, and D indicates the maximum transmission efficiency.

7. The method of claim 6, wherein the allocating of slice resources to the service request based on the resource allocation policy comprises:

determining an action cost function and a state cost function of the resource allocation strategy based on a reinforcement learning algorithm;

optimizing the resource allocation strategy based on the action function and the state function to obtain an optimized resource allocation strategy;

slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources;

Based on the corresponding relation between the type of the service request and the network slice resource, distributing the slice resource to the service request;

wherein the action cost function is expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,>representing the result of the reinforcement learning algorithm traversing the action cost function;

the state-cost function is expressed as:

wherein ,representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an environmental state s, γ representing a discount factor, P (s' |s, a) representing a conditional probability,/a->Representing the result of the reinforcement learning algorithm traversing the state-cost function.

8. A network slice resource allocation apparatus, comprising:

a service request acquisition module configured to: acquiring a service request of a communication network;

an allocation policy generation module configured to: determining an access rate and a transmission rate between the service request and the communication network, and generating a resource allocation strategy based on the access rate and the transmission rate;

A slice resource allocation module configured to: and distributing slice resources to the service request based on the resource distribution strategy.

9. The apparatus of claim 8, wherein said determining an access rate between the service request and the communication network comprises:

determining a bandwidth requirement of the service request;

determining an access rate between the service request and the communication network based on the bandwidth requirement and the number of service requests;

wherein, the access rate is expressed as:

where eta represents the access rate,k is the total number of service requests, b _k For communication networksThe target bandwidth allocated to service request k is allocated to network d _k Representing the bandwidth requirements of the service request.

10. The apparatus of claim 9, wherein said determining a transmission rate between said service request and said communication network comprises

Determining a target bandwidth allocated by the communication network for the service request;

determining a transmission rate between the service request and the communication network based on the target bandwidth;

wherein the transmission rate is expressed as:

wherein ,v_k Representing the transmission rate of service request k, b _k Target bandwidth, σ, allocated for traffic request k for communication network ² Representing thermal noise power, P, of service request _n Representing the transmission power, h, of a base station n where the communication network is located _k,m,n Indicating the channel gain between the base station n where the communication network is located and the service request k,representing the interference power of other base stations of the communication network.

11. The apparatus of claim 10, wherein the generating a resource allocation policy based on the access rate and the transmission rate comprises:

generating constraints for the communication network resource allocation based on the transmission rate and a total bandwidth of the communication network;

generating a resource allocation function of the communication network based on the transmission rate and the access rate;

generating a resource allocation policy of the communication network based on the constraint condition and the resource allocation function.

12. The apparatus of claim 11, wherein the allocating of slice resources to the service request based on the resource allocation policy comprises:

determining an action cost function and a state cost function of the resource allocation strategy based on a reinforcement learning algorithm;

optimizing the resource allocation strategy based on the action function and the state function to obtain an optimized resource allocation strategy;

Slicing the communication network based on the optimized resource allocation strategy to obtain network slicing resources;

based on the corresponding relation between the type of the service request and the network slice resource, distributing the slice resource to the service request;

wherein the action cost function is expressed as:

wherein ,representing an action cost function, a representing an action to perform a service request, s representing an environmental state of the communication network, r (s, a) representing a prize value obtained after taking the action a in the environmental state s, γ representing a discount factor, P(s) ^′ S, a) represents conditional probability, +.>Representing the result of the reinforcement learning algorithm traversing the action cost function;

the state-cost function is expressed as:

wherein ,representing a state cost function, s representing the environmental state of the communication network, a representing the action of executing a service request,/->Representing an action function, r (s, a) representing a prize value obtained after action a is taken in an ambient state s, gamma representing a discount factor, P(s) ^′ S, a) represents conditional probability, +.>Representing the result of the reinforcement learning algorithm traversing the state-cost function.

13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the program is executed by the processor.

14. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.