Local communication service resource isolation method and device, storage medium and electronic equipment

Abstract

The application discloses a local communication service resource isolation method and device, a storage medium and an electronic device, the method calculates resource demand and access value of a communication service based on access information of the communication service, abstracts the problem of resource allocation for the communication service based on the resource demand and the access value into a two-dimensional matrix packing problem based on an orthogonal frequency division multiple access technology, solves the two-dimensional matrix packing problem by using a pointer network and an Actor-Critic algorithm, and obtains a network slice allocation result of the communication service, so that the reasonable use of spectrum resources is realized by technologies such as OFDMA, meanwhile, the transmission of more valuable communication services is ensured by considering the resource demand and the access value during allocation, and finally, the logical isolation between communication services is realized by constructing a network slice during resource allocation of the communication services.

Description

Technical Field

[0001] The present invention relates to the field of computer and communication technology, and in particular to a method, device, storage medium and electronic equipment for isolating local communication service resources. Background Art

[0002] Currently, local communication networks are becoming increasingly diverse, with differentiated networks such as 5G and WLAN coexisting. Customized network slicing can effectively adapt to flexible business loads, ensure user service quality, and improve communication resource utilization.

[0003] While 5G network slicing technology is currently well-established, WLAN network slicing still faces numerous challenges. For example, current WLAN network slicing treats different access networks as separate network slices, making it impossible to construct network slices within the same access network. Furthermore, some network slicing solutions can only be applied within a collection of network slices, determining the target network slice and failing to construct appropriate network slices for specific applications. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a method, device, storage medium and electronic device for isolating local communication service resources to solve the technical problem in the prior art that WLAN network slicing cannot construct suitable network slices for specific applications of the same access network.

[0005] The technical solutions proposed by the present invention are as follows:

[0006] A first aspect of an embodiment of the present invention provides a method for isolating local communication service resources, including: obtaining access information of an electronic device communication service; calculating the resource requirements and access value of a required network slice based on the access information; abstracting the problem of allocating resources for the communication service based on the resource requirements and access value into a two-dimensional matrix packing problem based on orthogonal frequency division multiple access technology; using a pointer network and an Actor-Critic algorithm to solve the two-dimensional matrix packing problem to obtain a network slice allocation result for the communication service.

[0007] Optionally, the access information includes the transmission rate requirements, cache size and service priority of the electronic device communication service; the resource requirements and access value of the required network slice are calculated based on the access information, including: based on the relationship between the theoretical communication rate and the number of subcarriers, determining the spectrum resource requirements according to the transmission rate requirements; calculating the time domain resource requirements according to the cache size; calculating the access value according to the service priority, the spectrum resource requirements and the time domain resource requirements.

[0008] Optionally, the objective function of the two-dimensional matrix packing problem is to maximize the sum of the access values ​​of all communication services under preset resource constraints; the constraints of the two-dimensional matrix packing problem include that each object in the box is orthogonal to the box, the objects placed in the box cannot overlap, and the placement of the objects cannot exceed the edge set of the box.

[0009] Optionally, the pointer network and Actor-Critic algorithm are used to solve the two-dimensional matrix packing problem to obtain the network slice allocation result of the communication service, including: using the pointer network and Actor-Critic algorithm to solve the two-dimensional matrix packing problem to determine the communication service subset allocated to the time-frequency resources; matching the communication service of the electronic device with the communication service subset; when the communication service of the electronic device is in the communication service subset, constructing a network slice for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service, and allocating it to the communication service.

[0010] Optionally, a pointer network and an Actor-Critic algorithm are used to solve the two-dimensional matrix packing problem to determine the subset of communication services allocated to time-frequency resources, including: optimizing the parameters of the pointer network using the Actor-Critic algorithm; inputting an input set constructed by resource requirements and access value into the parameter-optimized pointer network to solve the two-dimensional matrix packing problem, and obtaining objects in the input set placed in the box, wherein the objects placed in the box are the subset of communication services allocated to time-frequency resources.

[0011] Optionally, obtaining access information of a communication service of an electronic device includes: sending a trigger frame to an electronic device within a signal range; and receiving access information of the communication service sent by the electronic device.

[0012] The second aspect of an embodiment of the present invention provides a local communication service resource isolation device, including: an information acquisition module for acquiring access information of the electronic device communication service; a demand calculation module for calculating the resource demand and access value of the required network slice based on the access information; a problem determination module for abstracting the problem of allocating resources for the communication service based on the resource demand and access value into a two-dimensional matrix packing problem based on orthogonal frequency division multiple access technology; an allocation module for solving the two-dimensional matrix packing problem using a pointer network and an Actor-Critic algorithm to obtain a network slice allocation result for the communication service.

[0013] Optionally, the access information includes the transmission rate requirement, cache size and service priority of the electronic device communication service; the calculation module is required to be specifically used to: determine the spectrum resource requirement according to the transmission rate requirement based on the relationship between the theoretical communication rate and the number of subcarriers; calculate the time domain resource requirement according to the cache size; calculate the access value according to the service priority, the spectrum resource requirement and the time domain resource requirement.

[0014] Optionally, the objective function of the two-dimensional matrix packing problem is to maximize the sum of the access values ​​of all communication services under preset resource constraints; the constraints of the two-dimensional matrix packing problem include that each object in the box is orthogonal to the box, the objects placed in the box cannot overlap, and the placement of the objects cannot exceed the edge set of the box.

[0015] Optionally, the allocation module includes: a solution module for using a pointer network and an Actor-Critic algorithm to solve the two-dimensional matrix packing problem, and determine the communication service subset allocated to the time-frequency resources; a matching module for matching the communication service of the electronic device with the communication service subset; and a slice construction module for constructing a network slice for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service when the communication service of the electronic device is in the communication service subset, and allocating it to the communication service.

[0016] Optionally, the solution module is specifically used to: optimize the parameters of the pointer network using the Actor-Critic algorithm; input the input set constructed by resource requirements and access value into the pointer network after parameter optimization, solve the two-dimensional matrix packing problem, and obtain the objects placed in the box in the input set, where the objects placed in the box are a subset of communication services allocated to time-frequency resources.

[0017] Optionally, the information acquisition module is specifically configured to: send a trigger frame to electronic devices within a signal range; and receive access information of a communication service sent by the electronic devices.

[0018] A third aspect of an embodiment of the present invention provides a local communication service resource isolation system, comprising: a wireless access point, wherein a slice controller is provided in the wireless access point, the wireless access point obtains access information of the electronic device communication service, and sends the access information to the slice controller; the slice controller calculates the resource requirements and access value of the required network slice based on the access information; based on orthogonal frequency division multiple access technology, the problem of allocating resources for the communication service based on the resource requirements and access value is abstracted into a two-dimensional matrix packing problem; the pointer network and the Actor-Critic algorithm are used to solve the two-dimensional matrix packing problem to obtain the network slice allocation result of the communication service.

[0019] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the local communication service resource isolation method as described in the first aspect of the embodiment of the present invention and any one of the first aspects.

[0020] A fifth aspect of an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the local communication service resource isolation method as described in the first aspect of the embodiment of the present invention and any one of the first aspects.

[0021] The technical solution provided by the present invention has the following effects:

[0022] The local communication service resource isolation method, device, storage medium, and electronic device provided in the embodiments of the present invention calculate the resource requirements and access value of the communication service based on the access information of the communication service. Based on orthogonal frequency division multiple access technology, the problem of allocating resources to the communication service based on resource requirements and access value is abstracted as a two-dimensional matrix packing problem. The pointer network and actor-critic algorithm are used to solve the two-dimensional matrix packing problem to obtain the network slice allocation result for the communication service. Thus, through technologies such as OFDMA, the rational utilization of spectrum resources is achieved. At the same time, when allocating resources, resource requirements and access value are considered to ensure the transmission of more valuable communication services. Finally, when allocating resources for the communication service, network slices are constructed to achieve logical isolation between communication services. In addition, this method allocates resources based on resource requirements for communication services on the same access network, solving the technical problem that WLAN network slicing cannot construct appropriate network slices for specific applications on the same access network. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a flowchart of a method for isolating local communication service resources according to an embodiment of the present invention;

[0025] Figure 2 is a diagram illustrating an example of the logical functions of a slice controller according to an embodiment of the present invention;

[0026] Figure 3This is a schematic diagram of an RU division method under a 20 MHz bandwidth according to an embodiment of the present invention;

[0027] Figure 4 is a structural block diagram of a local communication service resource isolation device according to an embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of the structure of a computer-readable storage medium provided according to an embodiment of the present invention;

[0029] Figure 6 is a schematic structural diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0031] The terms "first," "second," "third," "fourth," and the like in the specification and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] According to an embodiment of the present invention, a method for isolating local communication service resources is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] In this embodiment, a local communication service resource isolation method is provided, which can be used in electronic devices, etc. Figure 1 : is a flow chart of a method for isolating local communication service resources according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0034] Step S101: Obtain access information of the electronic device's communication service; specifically, the electronic device is an electronic device with data transmission requirements, that is, the electronic device needs to transmit communication services, then obtain access information of the communication services that the electronic device needs to transmit, and the access information includes access information such as the transmission rate requirements, cache size, and service priority of the electronic device's communication services.

[0035] In one embodiment, the access information is acquired by a wireless access point (AP). When acquiring the access information, the wireless access point sends a trigger frame to electronic devices within the signal range, and receives access information for communication services sent by the electronic devices. Specifically, the trigger frame sent requires the electronic device to report its own access information. When the electronic device receives the trigger frame, the electronic device with data transmission requirements sends its own access information such as transmission rate requirements, cache size, and service priority to the AP. After receiving the access information, the AP sends it to a slice controller set in the AP, and the slice controller allocates resources for the communication service based on the access information.

[0036] Step S102: Calculate the resource requirements and access value of the required network slice based on the access information. Specifically, before allocating resources to the communication service, the slice controller first calculates the resource requirements and access value of each communication service based on the access information of the communication service, thereby facilitating the allocation of corresponding network slices to the communication service based on resource requirements. The resource requirements are the communication resources required by the communication service, and the access value affects the resource allocation of the communication service. Services with higher access values ​​have a higher probability of obtaining a network slice, i.e., being allocated resources.

[0037] Step S103: Based on the orthogonal frequency division multiple access technology, the problem of allocating resources for communication services according to the resource requirements and access value is abstracted into a two-dimensional matrix packing problem. Specifically, when the slice controller allocates resources for communication services, it uses ΔT as the time window, and the allocated spectrum resources are the working bandwidth of the AP, which is recorded as BMHz. At the end of each time window, the slice controller will dynamically construct the network slice corresponding to the service based on the changes in the received communication services to realize resource allocation. In this embodiment, the working bandwidth can be 20MHz, 40MHz, 80MHz or 160MHz. Among them, if Figure 2As shown in the figure, when the slice controller allocates resources, it allocates them by scheduling the communication resources within the time window. Each time window includes multiple TXOPs (Transmission Opportunity). TXOP is the effective transmission time. During the TXOP time, the AP can perform data transmission and communication processes based on OFDMA and MU-MIMO (Multi-User Multiple-Input Multiple-Output). In addition to the TXOP time used for data transmission, there is also a necessary frame interaction time between TXOPs, namely the contention time. The contention time is used to exchange control information between the AP and the STA (Station). In the time domain resource allocation process, the contention time is ignored. The slice controller will uniformly manage and allocate the TXOPs within the window time ΔT.

[0038] It should be noted that this method is mainly applied to the IEEE 802.11ax protocol. This protocol introduces OFDMA (Orthogonal Frequency Division Multiple Access) technology. This technology subdivides spectrum resources into RUs (Resource Units). RUs can be 26 subcarrier RUs, 52 subcarrier RUs, 106 subcarrier RUs, 242 subcarrier RUs, 484 subcarrier RUs, and 996 subcarrier RUs, and each subcarrier has a bandwidth of 78.125 kHz. Figure 3 The RU division method under the 20MHz working bandwidth specified in the IEEE 802.11ax standard is shown. Figure 3 In the figure, the black part represents the data subcarriers used to transmit data, which constitute RUs of different specifications. In addition to the data subcarriers, there are pilot subcarriers between the data subcarriers for synchronization between the sender and the receiver. In addition, there are null subcarriers, guard subcarriers, and DC subcarriers. They are not used for data transmission and only play a protective role to resist interference from adjacent channels. Figure 3 In the figure, 5Guard and 6Guard respectively indicate that there are 5 subcarriers and 6 subcarriers from the edge as guard bands.

[0039] Resource allocation based on OFDMA technology enables different communication services to be transmitted over different TXOPs in the time domain, maintaining temporal independence. In the frequency domain, subcarrier orthogonality, along with guard and null subcarriers, allows RUs to mitigate interference from adjacent channels or subchannels. Therefore, network slices constructed using OFDMA-based resource allocation by the slice controller exhibit a degree of isolation, effectively shielding against interference from adjacent subcarriers.

[0040] Packing problems are common in logistics and transportation, such as loading trains, containers, and pallets, as well as in factory operations such as material cutting, finished product packaging, and facility layout planning. The two-dimensional rectangular packing problem (2D-RPP) primarily considers a two-dimensional situation where all target items are rectangular. The goal is to maximize the available area while allowing for orthogonal rotation when the rectangles are placed. The communication resource allocation problem in this embodiment is similar to the two-dimensional rectangular packing problem, where the allocated communication resources are equivalent to boxes, and each communication service is equivalent to an object that needs to be placed in the box. Thus, the communication resource allocation problem is abstracted into a two-dimensional rectangular packing problem.

[0041] Step S104: Using a pointer network and an actor-critic algorithm, the two-dimensional matrix packing problem is solved to obtain the network slice allocation results for the communication service. Specifically, solving the two-dimensional matrix packing problem involves allocating corresponding communication resources to more communication services with greater access value within the constraints of limited communication resources. Based on the allocated communication resources, the slice controller constructs corresponding network slices for the communication service. The actor-critic algorithm includes an actor network and a critic network, which are used for policy learning and value function learning, respectively. When using the pointer network and actor-critic algorithm for the solution, the actor-critic algorithm optimizes the parameters of the pointer network, which are then input into the pointer network. The pointer network then forms a scheduling strategy and outputs the allocation results.

[0042] The local communication service resource isolation method provided by an embodiment of the present invention calculates the resource requirements and access value of the communication service based on the access information of the communication service. Based on orthogonal frequency division multiple access technology, the problem of allocating resources for the communication service based on resource requirements and access value is abstracted into a two-dimensional matrix packing problem. The pointer network and the actor-critic algorithm are used to solve the two-dimensional matrix packing problem to obtain the network slice allocation result of the communication service. Thus, through technologies such as OFDMA, the rational utilization of spectrum resources is achieved. At the same time, when allocating resources, resource requirements and access value are considered to ensure the transmission of more valuable communication services. Finally, when allocating resources for the communication service, network slices are constructed to achieve logical isolation between communication services. In addition, this method allocates resources based on resource requirements for communication services on the same access network, solving the technical problem that WLAN network slicing cannot construct appropriate network slices for specific applications on the same access network.

[0043] In one embodiment, calculating the resource requirements and access value of the required network slice based on the access information includes the following steps:

[0044] Step S201: Based on the relationship between the theoretical communication rate and the number of subcarriers, determine the spectrum resource requirement according to the transmission rate requirement. The spectrum resource requirement is the number of subcarriers required for communication service transmission. Specifically, the theoretical communication rate is calculated using the following formula (1):

[0045]

[0046] Where, ms i and mb i are symbol bit length and code rate, respectively, which are determined by MCS (Modulation and Coding Scheme, modulation and coding strategy), N Subcarrier is the number of subcarriers, N stream is the number of spatial streams, Symbol is the symbol transmission time, and GI is the inter-frame interval. Subcarrier Related to spectrum resources.

[0047] Assume that the transmission rate requirement of communication service i is s i , the number of subcarriers of communication service i is NS i , the number of subcarriers should satisfy formula (3). In this embodiment, NS i Take the minimum value in (2) when formula (3) is satisfied.

[0048] N subcarrier ∈{26,52,106,242,484,996} formula (2)

[0049]

[0050] Step S202: Calculate the time domain resource requirement based on the cache size; wherein the time domain resource requirement is the time required for communication service transmission. Specifically, the time domain resource requirement is calculated using the following formula (4):

[0051] t i =BufferSize i *(Symbol+GI) / ms i *mb i *NS i *N stream Formula (4)

[0052] Where, BufferSize i Indicates the cache size of communication service i.

[0053] Step S203: Calculate access value based on the service priority, the spectrum resource requirement and the time domain resource requirement. Specifically, the access value is calculated using the following formula:

[0054]

[0055] In the formula, priority i Indicates the service priority of communication service i.

[0056] In one embodiment, when the resource allocation problem is abstracted as a 2D-RPP problem, the communication resources within the time window are equivalent to the box of the 2D-RPP problem, where the length of the box is ΔT and the height is B. The set of objects is the set of communication services N = {1, ..., n}, and the length of each object i∈N is t i , high is NS i , with a value of v i The position of each object in the Cartesian coordinate system is represented by its lower left corner (x i1 ,y i1 ) and the upper right corner (x i2 ,y i2 ) indicates that the parameter Indicates that the item has been placed in the box. Indicates that nothing is put in.

[0057] The objective function of the two-dimensional matrix packing problem is to maximize the sum of the access values ​​of all communication services under the preset resource constraints. Specifically, the objective function is expressed by the following formula (6):

[0058]

[0059] The constraints of the two-dimensional matrix bin packing problem include that each object in the bin is orthogonal to the bin, the objects placed in the bin cannot overlap, and the objects cannot be placed beyond the edge set of the bin. The constraints are shown in the following formulas (7) to (9):

[0060] (x i2 -x i1 ,y i2 -y i1 )∈{(t i ,NS i ),(NS i ,t i )}Formula (7)

[0061]

[0062] 0≤x i1 ≤x i2 ≤ΔT,0≤y i1 ≤y i2 ≤B formula (9)

[0063] Among them, since spectrum resources and time domain resources are two orthogonal dimensions, in the 2D-RPP problem, the object needs to be placed orthogonally to the box.

[0064] In one embodiment, a pointer network and an actor-critic algorithm are used to solve the two-dimensional matrix packing problem to obtain a network slice allocation result for a communication service, including the following steps:

[0065] Step S301: using a pointer network and an Actor-Critic algorithm to solve the two-dimensional matrix packing problem, and determining a subset of communication services allocated to time-frequency resources.

[0066] Specifically, a pointer network and an Actor-Critic algorithm are used to solve the two-dimensional matrix packing problem to determine the subset of communication services allocated to time-frequency resources, including: optimizing the parameters of the pointer network using the Actor-Critic algorithm; inputting an input set constructed by resource requirements and access value into the parameter-optimized pointer network to solve the two-dimensional matrix packing problem, and obtaining objects placed in the box in the input set, wherein the objects placed in the box are the subset of communication services allocated to time-frequency resources.

[0067] The pointer network consists of two parts: the encoder and the decoder, both of which are composed of long short-term memory networks (LSTM). When there are n communication services that need to be transmitted, the resource requirements corresponding to these communication services are expressed as: need = {x1, x2, ... x i …,x n}={(NS1,t1),(NS2,t2),…,(NS n ,t n )}, the access value is V = {v1,v2,…v i …,v n}. The resource requirements corresponding to these communication services are x i =(NS i ,t i ) and access value v i Encoded as a two-dimensional instance vector c i =(x i ,v i ). Then the sequence The input set is fed into the encoder. During decoding, the pointer network uses the Bahdanau attention mechanism at each step to point to the object (item) in the input sequence to be placed in the box. Once the volume of the object in the box exceeds the box boundary limit, the decoder stops outputting. The Bahdanau attention mechanism used by the decoder is as follows:

[0068]

[0069]

[0070] p(π(j)|π( <j),c)=softmax(u j )

[0071] e i is the hidden state of the encoder at step i, d j is the hidden state of the decoder at step j, vector V, matrix W1 and matrix W2 are the training parameters of the pointer network. is the pointer of the decoder in the pointer network pointing to the i-th instance in the input sequence at step j. The mask function in the formula is used to ensure that the object is not selected repeatedly. The Softmax function converts the vector u of length n into j Normalize it to the probability distribution on the input sequence c, and select the appropriate communication service output in the input sequence according to this probability distribution.

[0072] Before using the pointer network to select the service set, in order to maximize the value of the objective function, the Actor-Critic algorithm is used to optimize the parameters of the pointer network. The optimization process includes the following steps:

[0073] (1) Initialize the training set C in , set the number of training steps T and the number of batches N;

[0074] (2) Initialize the Actor network parameters θ and the Critic network parameters θ w ;

[0075] (3) Loop (4) to (10) T times:

[0076] (4) Loop (5) to (7) N times:

[0077] (5) Get input c from the training set i ∈C in

[0078] (6) Use θ to select the communication service subset π i

[0079] (7) Using θ w Calculate baseline values

[0080] (8) Calculate the gradient of the Actor objective function

[0081]

[0082] (9) Calculate the loss function of the Critic network

[0083]

[0084] (10) Using the gradient method to calculate θ and θ w to update.

[0085] In the Actor-Critic algorithm, the Actor network and the Critic network are used for strategy learning and value function learning respectively. w They represent the set of all weight and bias parameters in the Actor network and the Critic network respectively. These parameters are continuously updated through the optimization algorithm, so that the Actor network gradually tends to the optimal strategy.

[0086] Import the trained parameters θ into the pointer network to form the scheduling strategy p * (π * |c), in each time window, the resource requirements and access value of each communication service are encoded into a two-dimensional vector c i =(x i ,v i ), then The input is sent to the encoder of the pointer network; then, the Actor-Critic algorithm is used to calculate the output of the pointer network; during decoding, the pointer network uses the Bahdanau attention mechanism at each step to point to the object to be placed in the box in the input sequence. At this time, the communication service corresponding to the object placed in the box is the communication service that can obtain communication resources in this time window. The final output of the pointer network is the final selected subset of communication services that can obtain communication resources π.

[0087] Step S302: Matching the communication service of the electronic device with the communication service subset;

[0088] Step S303: When the communication service of the electronic device is in the communication service subset, a network slice is constructed for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service, and allocated to the communication service.

[0089] Specifically, the slice controller allocates communication resources, and the resource requirements of the communication services corresponding to the network slices are need={(NS1,t1),(NS2,t2),…,(NS n ,t n )}, when the communication service i is in the communication service subset π output by the pointer network, the slice controller constructs the spectrum resource occupancy as NS i , the time domain resource occupancy is t i and allocates the constructed network slices to the corresponding services.

[0090] The embodiment of the present invention also provides a local communication service resource isolation device, such as Figure 4 As shown, the device includes:

[0091] The information acquisition module is used to obtain access information of the electronic device communication service; the specific content can be found in the corresponding part of the above method embodiment, which will not be repeated here.

[0092] The demand calculation module is used to calculate the resource requirements and access value of the required network slice based on the access information; for specific content, please refer to the corresponding part of the above method embodiment and will not be repeated here.

[0093] The problem determination module is used to abstract the problem of allocating resources for communication services based on the resource requirements and access value into a two-dimensional matrix packing problem based on orthogonal frequency division multiple access technology; the specific content can be found in the corresponding part of the above method embodiment, which will not be repeated here.

[0094] The allocation module is used to solve the two-dimensional matrix packing problem using a pointer network and an actor-critic algorithm to obtain a network slice allocation result for the communication service. For details, please refer to the corresponding part of the above method embodiment and will not be repeated here.

[0095] Optionally, the access information includes the transmission rate requirement, cache size and service priority of the electronic device communication service; the calculation module is required to be specifically used to: determine the spectrum resource requirement according to the transmission rate requirement based on the relationship between the theoretical communication rate and the number of subcarriers; calculate the time domain resource requirement according to the cache size; calculate the access value according to the service priority, the spectrum resource requirement and the time domain resource requirement.

[0096] Optionally, the objective function of the two-dimensional matrix packing problem is to maximize the sum of the access values ​​of all communication services under preset resource constraints; the constraints of the two-dimensional matrix packing problem include that each object in the box is orthogonal to the box, the objects placed in the box cannot overlap, and the placement of the objects cannot exceed the edge set of the box.

[0097] Optionally, the allocation module includes: a solution module for using a pointer network and an Actor-Critic algorithm to solve the two-dimensional matrix packing problem, and determine the communication service subset allocated to the time-frequency resources; a matching module for matching the communication service of the electronic device with the communication service subset; and a slice construction module for constructing a network slice for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service when the communication service of the electronic device is in the communication service subset, and allocating it to the communication service.

[0098] Optionally, the solution module is specifically used to: optimize the parameters of the pointer network using the Actor-Critic algorithm; input the input set constructed by resource requirements and access value into the pointer network after parameter optimization, solve the two-dimensional matrix packing problem, and obtain the objects placed in the box in the input set, where the objects placed in the box are a subset of communication services allocated to time-frequency resources.

[0099] Optionally, the information acquisition module is specifically configured to: send a trigger frame to electronic devices within a signal range; and receive access information of a communication service sent by the electronic devices.

[0100] For a detailed description of the functions of the local communication service resource isolation device provided in the embodiment of the present invention, please refer to the description of the local communication service resource isolation method in the above embodiment.

[0101] An embodiment of the present invention also provides a local communication service resource isolation system, comprising: a wireless access point, wherein a slice controller is provided in the wireless access point, and the slice controller obtains access information of the electronic device communication service; calculates the resource requirements and access value of the required network slice based on the access information; based on orthogonal frequency division multiple access technology, abstracts the problem of resource allocation for the communication service based on the resource requirements and access value into a two-dimensional matrix packing problem; uses a pointer network and an Actor-Critic algorithm to solve the two-dimensional matrix packing problem to obtain a network slice allocation result for the communication service.

[0102] For a detailed functional description of the local communication service resource subsystem based on WLAN network slicing provided in an embodiment of the present invention, please refer to the description of the local communication service resource isolation method in the above embodiment.

[0103] The embodiment of the present invention also provides a storage medium, such as Figure 5 As shown, a computer program 601 is stored thereon, and when the instructions are executed by the processor, the steps of the local communication service resource isolation method in the above embodiment are implemented. The storage medium also stores audio and video stream data, feature frame data, interaction request signaling, encrypted data, and preset data size. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk drive (HDD) or a solid-state drive (SSD); the storage medium can also include a combination of the above types of memory.

[0104] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0105] The embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, the electronic device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected via a bus or other means. Figure 6 The bus connection is taken as an example.

[0106] The processor 51 may be a central processing unit (CPU). The processor 51 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0107] Memory 52, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the corresponding program instructions / modules in the embodiments of the present invention. Processor 51 executes the non-transitory software programs, instructions, and modules stored in memory 52 to perform various processor functions and data processing, thereby implementing the local communication service resource isolation method in the above-mentioned method embodiment.

[0108] The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store applications required for operating the device and at least one function; the data storage area may store data created by the processor 51, etc. In addition, the memory 52 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 52 may optionally include a memory remotely located relative to the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] The one or more modules are stored in the memory 52 and when executed by the processor 51, perform the following steps: Figure 1 - Local communication service resource isolation method in the embodiment shown in 3.

[0110] For details of the above electronic equipment, please refer to Figures 1 to 3 The corresponding descriptions and effects in the embodiments shown can be understood and will not be repeated here.

[0111] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for isolating local communication service resources, characterized in that: include: Obtaining access information for electronic equipment communication services; Calculate the resource requirements and access value of the required network slice based on the access information; Based on the orthogonal frequency division multiple access technology, the problem of allocating resources for communication services according to the resource demand and access value is abstracted into a two-dimensional matrix packing problem; Pointer network and Actor-Critic algorithm are used to solve the two-dimensional matrix packing problem and obtain the network slice allocation result of communication service.

2. The local communication service resource isolation method according to claim 1, characterized in that: The access information includes the transmission rate requirement, cache size and service priority of the electronic device communication service; Calculating resource requirements and access value of the required network slice based on the access information, including: Determining spectrum resource requirements based on the transmission rate requirement based on the relationship between the theoretical communication rate and the number of subcarriers; Calculating time domain resource requirements based on the cache size; The access value is calculated according to the service priority, the spectrum resource requirement and the time domain resource requirement.

3. The local communication service resource isolation method according to claim 1, characterized in that: The objective function of the two-dimensional matrix bin packing problem is to maximize the sum of the access values ​​of all communication services under preset resource constraints; the constraints of the two-dimensional matrix bin packing problem include that each object in the box is orthogonal to the box, the objects placed in the box cannot overlap, and the placement of objects cannot exceed the edge set of the box.

4. The local communication service resource isolation method according to claim 2, characterized in that: The pointer network and actor-critic algorithm are used to solve the two-dimensional matrix packing problem and obtain the network slice allocation results for communication services, including: The pointer network and the actor-critic algorithm are used to solve the two-dimensional matrix packing problem and determine the subset of communication services allocated to the time-frequency resources; Matching the communication service of the electronic device with the communication service subset; When the communication service of the electronic device is in the communication service subset, a network slice is constructed for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service, and allocated to the communication service.

5. The local communication service resource isolation method according to claim 4, characterized in that: The pointer network and the actor-critic algorithm are used to solve the two-dimensional matrix packing problem and determine the subset of communication services allocated to time-frequency resources, including: Actor-Critic algorithm is used to optimize the parameters of the pointer network; The input set constructed by resource demand and access value is input into the pointer network after parameter optimization, and the two-dimensional matrix packing problem is solved to obtain the objects placed in the box in the input set. The objects placed in the box are the subset of communication services allocated to time-frequency resources.

6. The local communication service resource isolation method according to claim 1, characterized in that: Obtain access information for electronic device communication services, including: Sending a trigger frame to electronic devices within the signal range; Receive access information for communication services sent by an electronic device.

7. A local communication service resource isolation device, characterized in that: include: An information acquisition module, used to obtain access information of electronic device communication services; A demand calculation module, configured to calculate the resource requirements and access value of the required network slice based on the access information; a problem determination module for abstracting the problem of allocating resources for communication services according to the resource requirements and access value into a two-dimensional matrix packing problem based on orthogonal frequency division multiple access technology; The allocation module is used to solve the two-dimensional matrix packing problem by using a pointer network and an Actor-Critic algorithm to obtain a network slice allocation result for the communication service.

8. The local communication service resource isolation device according to claim 7, characterized in that: The access information includes the transmission rate requirements, cache size and service priority of the electronic device communication service; the calculation module is specifically used to: determine the spectrum resource requirements according to the transmission rate requirements based on the relationship between the theoretical communication rate and the number of subcarriers; calculate the time domain resource requirements according to the cache size; calculate the access value according to the service priority, the spectrum resource requirements and the time domain resource requirements.

9. The local communication service resource isolation device according to claim 7, characterized in that: The objective function of the two-dimensional matrix bin packing problem is to maximize the sum of the access values ​​of all communication services under preset resource constraints; the constraints of the two-dimensional matrix bin packing problem include that each object in the box is orthogonal to the box, the objects placed in the box cannot overlap, and the placement of objects cannot exceed the edge set of the box.

10. The local communication service resource isolation device according to claim 8, characterized in that: The allocation module includes: a solution module, which is used to solve the two-dimensional matrix packing problem using a pointer network and an Actor-Critic algorithm to determine the communication service subset allocated to the time-frequency resources; a matching module, which is used to match the communication service of the electronic device with the communication service subset; and a slice construction module, which is used to construct a network slice for the communication service according to the spectrum resource requirements and time domain resource requirements corresponding to the communication service when the communication service of the electronic device is in the communication service subset, and allocate it to the communication service.

11. The local communication service resource isolation device according to claim 10, characterized in that: The solution module is specifically used to: optimize the parameters of the pointer network using the Actor-Critic algorithm; input the input set constructed by resource requirements and access value into the pointer network after parameter optimization, solve the two-dimensional matrix packing problem, and obtain the objects placed in the box in the input set. The objects placed in the box are the subset of communication services allocated to time-frequency resources.

12. The local communication service resource isolation device according to claim 7, characterized in that: The information acquisition module is specifically used to: send a trigger frame to electronic devices within the signal range; and receive access information of communication services sent by the electronic devices.

13. A local communication service resource isolation system, characterized in that: include: A wireless access point, wherein a slice controller is provided in the wireless access point, The wireless access point obtains access information of the electronic device communication service and sends the access information to the slice controller; The slice controller calculates the resource requirements and access value of the required network slice according to the access information; Based on orthogonal frequency division multiple access technology, the problem of allocating resources for communication services according to the resource demand and access value is abstracted into a two-dimensional matrix packing problem; the pointer network and actor-critic algorithm are used to solve the two-dimensional matrix packing problem to obtain the network slice allocation result of the communication service.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the local communication service resource isolation method according to any one of claims 1 to 6.

15. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the local communication service resource isolation method according to any one of claims 1 to 6 by executing the computer instructions.

Images