Communication method and device based on extensible cellular-removed MIMO system, and medium

Abstract

The invention discloses a communication method and device based on an extensible cellular MIMO system, and a medium, and relates to the technical field of communication. The communication method based on the extensible cellular-removed MIMO system comprises the following steps: determining a first target access end through large-scale fading information between a user side and a plurality of access ends, then establishing service association between the user side and the first target access end, determining the user side as a user whose association cannot be cancelled by the first target access end, and on this basis, establishing service association between the user side and the first target access end. The user side determines a second target access side according to self service demand information, then the user side establishes service association with the second target access side, the user side is determined as a user capable of canceling association by the second target access side, the number of the first target access side is one, and the number of the second target access side is one or more. By executing the operation, the service quality of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication method, device and medium based on a scalable decellularized MIMO system. Background Art

[0002] Scalable decellularized massive multiple-input multiple-output (MIMO) system is a new wireless communication architecture that can achieve more reliable coverage and provide users with stable service quality due to its high macro diversity gain, ideal propagation conditions and channel hardening effect.

[0003] In the de-cellular MIMO system in the related art, all access points are connected to a single central processing unit, and all access points serve all users together, so that the front-end signaling overhead and computational complexity increase linearly with the increase in the number of users. At the same time, it cannot be guaranteed that every user accessing the network can continue to receive services from the access point, and there is a risk of users exiting the network midway. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a communication method, device and medium based on a scalable decellularized MIMO system, aiming to dynamically select the most suitable access point for each user to provide services, thereby improving the user's service quality.

[0005] To achieve the above object, an embodiment of the present application provides a communication method based on a scalable decellularized MIMO system, comprising the following steps:

[0006] The user end determines a first target access end according to large-scale fading information between the user end and the plurality of access ends;

[0007] The user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association;

[0008] The user end determines the second target access end according to its own service demand information;

[0009] The user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user from which the association can be cancelled;

[0010] The number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

[0011] In some embodiments, the method further comprises:

[0012] The access end jointly optimizes its own total transmission power and downlink power allocation through a power optimization model according to the acquired large-scale fading information between the access end and the served user end;

[0013] Determining a downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation;

[0014] The access end includes the first target access end and / or the second target access end, and the power optimization model is obtained through training based on a convolutional neural network.

[0015] In some embodiments, the power optimization model includes a stackable feature extraction network based on a residual network and two parallel output networks, and the training steps of the power optimization model include:

[0016] Determine an input tensor by using the acquired large-scale fading information, wherein the dimension of the input tensor is determined by the maximum number of service users of the communication system and the number of access terminals connected to the edge processor;

[0017] Inputting the input tensor into the feature extraction network to obtain large-scale fading information features;

[0018] Inputting the large-scale fading information feature into the convolutional neural network, and obtaining the total transmission power decision tensor and the downlink power allocation decision tensor of the access terminal itself through the parallel output network;

[0019] Based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor, the model parameters are optimized to complete the training.

[0020] In some embodiments, determining the downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation includes:

[0021] The downlink transmission power of the access end is determined by the total transmission power decision tensor, the downlink power allocation decision tensor, and the maximum transmission power of the access end.

[0022] In some embodiments, the access terminal includes a user that can cancel association, and the user terminal determines a first target access terminal according to large-scale fading information between the user terminal and multiple access terminals, including:

[0023] The user end determines the large-scale fading coefficients between itself and the plurality of access ends, determines the access end with the largest large-scale fading coefficient as the first access end and sends an association request;

[0024] If the number of user terminals served by the first access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the first access terminal as a first target access terminal;

[0025] If the number of user terminals served by the first access terminal is equal to the maximum number of serviceable users and the user whose association can be cancelled exists on the first access terminal, then, if the large-scale fading coefficient between the user terminal and the first access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, control the first access terminal to cancel the association of the associated user corresponding to the minimum large-scale fading coefficient, receive an association request sent by the user terminal, and determine the first access terminal as a first target access terminal;

[0026] If there is no user whose association can be cancelled at the first access terminal, the user terminal determines the access terminal with the second largest large-scale fading coefficient as a new first access terminal and sends an association request.

[0027] In some embodiments, the user terminal determines the second target access terminal according to its own service demand information, including:

[0028] The user end determines a large-scale fading coefficient between itself and a plurality of access ends, and determines an access end whose large-scale fading coefficient is greater than or equal to its own service demand information as a second access end;

[0029] The user terminal sends an association request to all the second access terminals;

[0030] If the number of user terminals served by the second access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the second access terminal as a second target access terminal;

[0031] If the number of user terminals served by the second access terminal is equal to the maximum number of serviceable users and there are users whose association can be cancelled on the second access terminal, then when the large-scale fading coefficient between the user terminal and the second access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, the second access terminal is controlled to cancel the association with the associated user corresponding to the minimum large-scale fading coefficient, and an association request sent by the user terminal is received, and the second access terminal is determined as a second target access terminal.

[0032] To achieve the above object, another aspect of an embodiment of the present application proposes a communication method based on a scalable decellularized MIMO system, which is applied to a user terminal. The communication method based on a scalable decellularized MIMO system includes the following steps:

[0033] Determine a large-scale fading coefficient between itself and a plurality of access terminals, determine the access terminal having the largest large-scale fading coefficient as a first access terminal and send an association request;

[0034] In the case of receiving the association permission message sent by the first access terminal, determining the first access terminal as a first target access terminal, wherein the first access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and a competition mechanism;

[0035] A user who has established a service association with the first target access terminal and is determined by the first target access terminal as a user who cannot cancel the association;

[0036] Determine the access terminal whose large-scale fading coefficient is greater than or equal to its own service demand information as the second access terminal;

[0037] Sending an association request to all of the second access terminals;

[0038] In the case of receiving the association permission message sent by the second access terminal, determining the second access terminal as the second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and the competition mechanism;

[0039] A user who has established a service association with the second target access terminal and is determined by the second target access terminal as a user whose association can be cancelled;

[0040] The number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

[0041] To achieve the above object, another aspect of an embodiment of the present application proposes a communication method based on a scalable decellularized MIMO system, which is applied to an access terminal. The communication method based on a scalable decellularized MIMO system includes the following steps:

[0042] receiving an association request sent by a user terminal, wherein the association request includes a corresponding large-scale fading coefficient;

[0043] Determining whether to provide association service for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of users that can be disassociated, and a competition mechanism;

[0044] Based on the large-scale fading information obtained between the associated user terminals, the total transmission power and downlink power allocation of the system are jointly optimized through the power optimization model;

[0045] determining a downlink transmission power based on the total transmission power and the downlink power allocation;

[0046] Among them, the access end includes a first target access end and / or a second target access end, the number of the first target access end is 1, the number of the second target access end is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

[0047] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0048] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0049] The embodiments of the present application include at least the following beneficial effects:

[0050] The present application provides a communication method, device and medium based on an extensible decellularized MIMO system. The scheme determines a first target access terminal through large-scale fading information between a user terminal and multiple access terminals. After that, the user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association. On this basis, the user terminal determines a second target access terminal according to its own service demand information. After that, the user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user that can cancel the association, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more; thus, the user terminal determines the first target access terminal through large-scale fading information, and can The service access terminal is selected based on the attenuation characteristics of the signal at a macroscopic scale, so as to ensure the service stability of the user terminal. On the basis that the user terminal establishes a service association with the first target access terminal and is determined by the first target access terminal as a user that cannot cancel the association, it is ensured that the user terminal can obtain continuous and stable service from an access point, thereby avoiding the risk of the access terminal exiting the network midway; on this basis, the user terminal determines the second target access terminal according to its own service demand information, so as to be able to expand the access points serving it according to the service quality required by itself, thereby forming its own access point service cluster, that is, the number of the second target access terminals is one or more, ensuring that one or more suitable access points are dynamically selected for each user terminal to provide services, thereby improving the service quality of the user.

[0051] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0053] Figure 1 is a schematic diagram of a communication system based on a scalable decellularized MIMO system provided by some embodiments of the present application;

[0054] Figure 2 is a flow chart of a communication method based on an expandable decellularized MIMO system provided by some embodiments of the present application;

[0055] Figure 3 is a schematic diagram of a system structure of a first-stage association based on a scalable decellularized MIMO system provided by some embodiments of the present application;

[0056] Figure 4 is a schematic diagram of a system structure of a second-stage association based on a scalable decellularized MIMO system provided in some embodiments of the present application;

[0057] Figure 5 It is a schematic diagram of a communication process based on a scalable decellularized MIMO system provided by some embodiments of the present application;

[0058] Figure 6 is a schematic block diagram of modules of a communication device based on an expandable decellularized MIMO system provided by some embodiments of the present application;

[0059] Figure 7 is a schematic block diagram of modules of another communication device based on a scalable decellularized MIMO system provided by some embodiments of the present application;

[0060] Figure 8 It is a schematic diagram of the hardware structure of the communication based on the scalable de-cellularized MIMO system provided by some embodiments of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the reference to "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0062] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0063] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0065] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0066] In order to make the inventive concept of the present application easy to understand, before describing the embodiments of the present application in detail, the English abbreviations (terms) / related concepts involved in the embodiments of the present application are first described. The English abbreviations (terms) / related concepts involved in the embodiments of the present application are subject to the following explanations.

[0067] MIMO: MIMO (Multiple Input Multiple Output) is a wireless communication technology that uses multiple antennas at the transmitting and receiving ends to improve communication performance and data transmission rate. MIMO technology can send multiple data streams on the same frequency band, thereby effectively improving spectrum efficiency and communication system capacity.

[0068] Large-scale fading coefficient: In wireless communications, signals will attenuate during propagation due to factors such as increased distance and obstacles. This attenuation is called path loss, which can be quantified by a coefficient. The large-scale fading coefficient is usually used to describe the average power attenuation of the signal on a macro scale. This coefficient is related to factors such as the distance between the user and the access point and the environment.

[0069] Access point: In wireless communication systems, an access point (such as a base station, Wi-Fi hotspot, etc.) is a device fixed in the network that is used to communicate with mobile user devices.

[0070] Decellularized massive MIMO system is a new wireless communication architecture. Thanks to its high macro diversity gain, ideal propagation conditions and channel hardening effect, it can achieve more reliable coverage and provide users with stable service quality. It is expected to become a basic component of the sixth generation of wireless networks. However, in the traditional decellularized massive MIMO system, all access points are connected to a single central processing unit, and all access points serve all users together, which is impractical because the signaling overhead and computational complexity of the front end increase linearly with the number of users. In addition, in the decellularized massive MIMO system, due to the dense distribution of access points and users, the system environment is highly susceptible to interference. Therefore, effective power allocation is crucial to suppress interference and improve the overall system performance.

[0071] In the related art, there is a user association technology that combines a user-centric approach with a decellularized large-scale multi-input multi-output system, in which each access point selects a limited number of users to provide services. In addition, there is a downlink power control method based on a fully connected neural network, where each model is deployed in an edge processor and can perform power control tasks using only locally collected large-scale fading information.

[0072] However, in the related communication architecture, since the access point will only select users with the best channel environment to provide services, and some users with poor channel quality may not be able to get the services of the access point, it is impossible to guarantee that every user accessing the network can continue to get the services of the access point, which may cause some users to lose connection during the communication process, and there is a risk of users exiting the network midway. In addition, the preparation of training data and the training process of the model for power control through machine learning methods require a lot of computing resources. At the same time, due to the limitations of network design, it is difficult for the system to achieve the optimal solution for the downlink power allocation problem. In addition, the single model of this method cannot adapt to the scenario where the number of associated users in the system changes dynamically.

[0073] In view of this, the present application proposes a communication method, device and medium based on a scalable decellularized MIMO system. In an embodiment of the present application, a first target access terminal is determined through large-scale fading information between a user terminal and multiple access terminals. After that, the user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association. On this basis, the user terminal determines a second target access terminal according to its own service demand information. After that, the user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user that can cancel the association, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more; thus, the user terminal determines the first target access terminal through large-scale fading information. The access terminal can select a service access terminal based on the attenuation characteristics of the signal at a macroscopic scale, thereby ensuring the service stability of the user terminal. On the basis that the user terminal establishes a service association with the first target access terminal and is determined by the first target access terminal as a user that cannot cancel the association, it is ensured that the user terminal can obtain continuous and stable services from an access point, thereby avoiding the risk of the access terminal exiting the network midway; on this basis, the user terminal determines the second target access terminal according to its own service demand information, thereby being able to expand the access points that serve it according to the service quality required by itself, thereby forming its own access point service cluster, that is, the number of the second target access terminals is one or more, ensuring that one or more suitable access points are dynamically selected for each user terminal to provide services, thereby improving the user's service quality.

[0074] The communication method based on the scalable decellularized MIMO system provided in the embodiment of the present application relates to the field of communication technology. It can be applied to the electronic device provided in the present application. The electronic device can be a user terminal, an access point or an edge server.

[0075] In some embodiments, the terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, etc., but is not limited thereto.

[0076] The access point may be a macro base station, a micro base station, a pico base station, a micro-pixel base station, a distributed access point, massive MIMO, multi-user MIMO or beamforming MIMO, etc., but is not limited thereto.

[0077] The edge server can be configured as an independent physical server, or as a server cluster or distributed system consisting of multiple physical servers. It can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in the blockchain network.

[0078] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0079] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0080] Before introducing the communication method of the scalable decellularized MIMO system proposed in the present application, a communication system on which the implementation of the communication method proposed in the present application relies is briefly introduced.

[0081] Please refer to Figure 1 , Figure 1 It is a schematic diagram of a communication system based on a scalable de-cellularized MIMO system provided in some embodiments of the present application. Figure 1 In the figure, two users are shown by way of example, wherein each of the two users has a service cluster, each service cluster includes three access points, the access points can provide services to user 1 or user 2 respectively, or can provide services to user 1 and user 2 at the same time, the access points are associated with the edge processor, and the corresponding computing tasks are executed by the edge processor.

[0082] The following will describe in detail the implementation steps of a communication method based on a scalable de-cellularized MIMO system provided by an embodiment of the present application in conjunction with the accompanying drawings.

[0083] Please refer to Figure 2, Figure 2 A flow chart of a communication method based on a scalable decellularized MIMO system provided for some embodiments of the present application. It should be noted that the steps shown in the flow chart 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 flow chart, in some cases, the steps shown or described can be executed in an order different from that here.

[0084] The method of the embodiment of the present application comprises the following steps:

[0085] Step 201: The user end determines a first target access end according to large-scale fading information between the user end and multiple access ends;

[0086] Step 202: The user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association;

[0087] Step 203: The user terminal determines a second target access terminal according to its own service demand information;

[0088] Step 204: the user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user from which the association can be cancelled;

[0089] The number of first target access terminals is 1, and the number of second target access terminals is 1 or more.

[0090] In steps 201 to 204 shown in the embodiment of the present application, the first target access terminal is determined by large-scale fading information, and the service access terminal can be selected based on the macro-scale attenuation characteristics of the signal, so as to ensure the service stability of the user terminal. On the basis that the user terminal establishes a service association with the first target access terminal and is determined by the first target access terminal as a user that cannot cancel the association, it is ensured that the user terminal can obtain continuous and stable service from an access point, thereby avoiding the risk of the access terminal exiting the network midway; on this basis, the user terminal determines the second target access terminal according to its own service demand information, so as to be able to expand the access points serving it according to the service quality required by itself, thereby forming its own access point service cluster, that is, the number of the second target access terminals is one or more, ensuring that one or more suitable access points are dynamically selected for each user terminal to provide service, thereby improving the service quality of the user.

[0091] The specific implementation methods of the above steps are introduced below.

[0092] In step 201, the user terminal determines a first target access terminal according to large-scale fading information between the user terminal and multiple access terminals.

[0093] Please refer to Figure 3In the actual system, the user (user end) will periodically transmit the synchronization signal, and the access point (access end) can calculate the large-scale fading coefficient of each user locally according to the received signal strength (it should be understood that the user end can also calculate the large-scale fading coefficient of the corresponding access point according to the received broadcast information). Let the number of access points in the communication system be M, and the access point set be For the mth access point, the set of users it serves is defined as in Whether a user is served by an access point can be determined by large-scale fading information. The method proposed in the embodiment of the present application can be composed of two stages, and the first stage is first introduced here: In the first stage, at least one access point is allocated to each user in the system to ensure that its basic service requirements are met.

[0094] Optionally, the large-scale fading information may include a large-scale fading coefficient (path loss), shadow fading, penetration loss or received signal strength, but is not limited thereto.

[0095] Exemplarily, the user end can measure the large-scale fading coefficient according to the synchronization signal periodically broadcast in the communication system, wherein the synchronization signal periodically broadcast exists in the standard of the cellular network, such as the primary synchronization signal and the secondary synchronization signal in 5G. It can be understood that the user end will receive the broadcast signals sent by multiple access terminals, and therefore, the large-scale fading information between the multiple access terminals can be calculated. On this basis, the user end will select the access point m with the largest large-scale fading coefficient. k Send an association request and upon receiving access point m k If the association permission message is returned, the access point m k Determined as the first target access end.

[0096] In some embodiments, the access terminal includes users whose association can be cancelled, and the user terminal can determine the first target access terminal according to the large-scale fading information between the user terminal and the multiple access terminals. Exemplarily, the user terminal determines the large-scale fading coefficient between itself and the multiple access terminals, determines the access terminal with the largest large-scale fading coefficient as the first access terminal and sends an association request; if the number of user terminals served by the first access terminal is less than the maximum number of serviceable users, then the association request sent by the user terminal is received, and the first access terminal is determined as the first target access terminal; if the number of user terminals served by the first access terminal is equal to the maximum number of serviceable users and there are users whose association can be cancelled on the first access terminal, then if the large-scale fading coefficient between the user terminal and the first access terminal is greater than the smallest large-scale fading coefficient among the users whose association can be cancelled, the first access terminal is controlled to cancel the association of the associated user corresponding to the smallest large-scale fading coefficient, and receives the association request sent by the user terminal, and determines the first access terminal as the first target access terminal; if there is no user whose association can be cancelled on the first access terminal, the user terminal determines the access terminal with the second largest large-scale fading coefficient as the new first access terminal and sends an association request.

[0097] Optionally, in the first stage, for the kth user newly joining the system, first measure its large-scale fading coefficient β with the surrounding neighboring access points m，k , then user k moves to access point m with the largest large-scale fading coefficient k Send an association request, where m k The following calculation is obtained:

[0098]

[0099] When access point m k When the number of served users is less than the maximum number of serviceable users, the association request of user k is accepted and the association permission information is returned to user k; if access point m k The number of users served is equal to the maximum number of serviceable users, and access point m k When there are users who can cancel the association, the competition mechanism is triggered. This mechanism is to ensure that every new user joining the network can get the service. The principle of the competition mechanism is that the access point will cancel the association with the user with the smallest large-scale fading coefficient in the set of users who can cancel the service, and then associate with user k (it should be understood that the access point will compare the large-scale fading coefficients of the requesting user and the user with the smallest large-scale fading coefficient. Only when the large-scale fading coefficient of the requesting user is greater than the smallest large-scale fading coefficient of the access point that can cancel the service, will it choose to associate with the requesting user for service); if the access point m k If there is no user that can cancel the association, user k moves to the neighboring access points except access point m. kThe access point with the largest large-scale fading coefficient sends an association request and repeats the above process.

[0100] The embodiment of the present application determines the first target access terminal by using large-scale fading information between multiple access terminals, thereby ensuring that the user has at least one stable access point to serve him / her and avoiding the risk of the user exiting the network midway. In addition, by determining the access point to serve him / her based on the large-scale fading information, the access channel environment of the user can be fully guaranteed and the service quality can be improved.

[0101] In step 202, the user terminal establishes a service association with a first target access terminal, and the user terminal is determined by the first target access terminal as a user from which the association cannot be cancelled.

[0102] Exemplarily, after the first target access terminal is determined, the user terminal may establish a service association with the first target access terminal. At this time, the first target access terminal provides communication services for the user.

[0103] It should be understood that in the technical solution provided in the present application, users of the access end service include two types, namely, users of non-cancellable services and users of cancelable services.

[0104] After the user determines the access point as the first target access point, the first target access point determines the requested user as a user that cannot be disassociated, thereby ensuring that there is at least one stable access point to serve the user and avoiding the risk of the user exiting the network midway.

[0105] Figure 3 In the example, user 1 determines the associated service with one access point; user 2 determines the associated service with another access point. At this time, the service clusters of user 1 and user 2 each include one access point. In this case, the user end will further expand its own service cluster.

[0106] In step 203, the user terminal may determine the second target access terminal according to its own service demand information.

[0107] You can refer to Figure 4 , exemplarily, the service cluster can be further expanded according to the service requirements of each user to optimize the system performance. The service cluster of each user is composed of two non-intersecting subsets, wherein the first subset is determined in the first stage of the method, and the users in it cannot be disassociated; the second subset is determined in the second stage of the method, and the users served can be disassociated. The method assumes that the processing capacity of each access point is limited, that is, each access point can only serve a limited number of users, and therefore has a limit on the maximum number of users served.

[0108] It should be understood that there may be multiple access points around the user terminal. By measuring large-scale fading information, multiple access points meet the conditions for serving it. Therefore, the user terminal can determine the access points that meet the conditions for serving it as second target access terminals and send association requests to all second target access terminals.

[0109] In some implementations, a user terminal first determines a large-scale fading coefficient between itself and a plurality of access terminals, and determines an access terminal whose large-scale fading coefficient is greater than or equal to its own service demand information as a second access terminal; the user terminal sends an association request to all second access terminals; if the number of user terminals served by the second access terminal is less than the maximum number of serviceable users, the association request sent by the user terminal is received, and the second access terminal is determined as a second target access terminal; if the number of user terminals served by the second access terminal is equal to the maximum number of serviceable users and there are users whose association can be cancelled at the second access terminal, then if the large-scale fading coefficient between the user terminal and the second access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, the second access terminal is controlled to cancel the association of the associated user corresponding to the minimum large-scale fading coefficient, and the association request sent by the user terminal is received, and the second access terminal is determined as the second target access terminal.

[0110] Optionally, in the second stage, user k will expand his access point service cluster according to his service needs. User k tries to select all the access points that meet β m，k >ε, where ε represents the service demand of each user. If the number of users served by access point m does not reach the maximum number of users served, the association request of user k is accepted; if the number of users served by access point m reaches the maximum number of users served and there are users who can cancel the association, the competition mechanism is triggered.

[0111] Exemplarily, the competition mechanism may be that when the large-scale fading coefficient between user k and access point m is greater than the user with the smallest large-scale fading coefficient among the disassociated users, the access point will disassociate from the user with the smallest large-scale fading coefficient among the disassociated users, and establish an association with user k. The competition mechanism in the second stage is to ensure that each access point selects a user with a better channel condition to provide service.

[0112] Figure 4In the example, user 1 determines associated services with three access points; user 2 determines associated services with three access points. At this time, the service clusters of user 1 and user 2 each include three access points, and the three access points provide communication services for user 1 and user 2 respectively. It should be understood that in the embodiments provided in the present application, there may be access points that provide services for both user 1 and user 2. In this case, the presence of multiple access points to serve users can further improve the service quality of users, thereby improving the communication experience and usage satisfaction of users.

[0113] It should be understood that the first and second phases of the method provided in the embodiment of the present application are performed separately, and the first phase is performed first and then the second phase. The first phase completes the operation of the user's initial access to the network, and the second phase is to expand its service cluster. In addition, the selection between the user end and the access end is bidirectional. The user will send an association request to all access points whose large-scale fading coefficients are greater than its service requirements; the access point that receives the association request will decide whether to accept the user's association request at the local end.

[0114] In the embodiment of the present application, the first stage is to complete the operation of the user's initial access to the system, and the second stage is to further optimize the user's service quality. The operation period of the second stage can be determined by the complexity of the method, wherein the time complexity is related to the number of access points M in the communication system and the maximum number of accessible users of the access points. Since the maximum number of accessible users is usually a fixed value, the operation period is related to the number of access points M in the system. The more access points there are, the longer the operation period.

[0115] The embodiment of the present application determines the second target access terminal through the service demand information of the user terminal itself, and can further expand its service cluster according to the service demand of each user, improve the user's service quality, and thus optimize the overall performance of the communication system.

[0116] The embodiment of the present application introduces a competition mechanism in the user association method, comprehensively considers the user service requirements and the access point workload, and can dynamically select the most suitable access point for each user to provide services; and in the entire association process, only the local end needs to choose whether to associate with the requesting user according to its own access user situation, which further simplifies the calculation process, reduces signaling overhead, and saves computing resources.

[0117] In step 204, the user terminal establishes a service association with a second target access terminal, and the user terminal is determined by the second target access terminal as a user whose association can be cancelled, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

[0118] Exemplarily, after the second target access terminal is determined, the user terminal may establish a service association with the second target access terminal. At this time, the second target access terminal provides communication services for the user.

[0119] There are usually multiple second target access terminals, such as 2, 3 or 5, and this application does not impose any limitation on this.

[0120] By establishing service associations with multiple second target access terminals, the user terminal can expand the range of access points serving it, which is equivalent to establishing an access point cluster serving it, wherein each access terminal in the cluster serves the user.

[0121] Serving one user by multiple access points can be achieved, for example, through joint transmission. In addition, it can also be achieved through cross-site carrier aggregation, coordinated beamforming or coordinated multi-point access, which is not limited in this application.

[0122] It should be understood that in the technical solution provided in the present application, users of the access end service include two types, namely, users of non-cancellable services and users of cancelable services.

[0123] After the user determines the access terminal as the second target access terminal, the second target access terminal determines the requested user as a user whose association can be cancelled, thereby ensuring that more users in the system receive better services and further improving the performance of the communication system.

[0124] Through the above method, the user's service cluster can include an access point with the largest large-scale fading selected for the user in the first stage, and an access point that meets the user's service needs in the second stage. When the user's position is fixed, the cluster in the system is also fixed and will not change dynamically; when the user's position moves, the user's wireless channel environment will also change accordingly, so the large-scale fading coefficient will also change. On this basis, when the change is greater than the preset threshold, the first stage and / or second stage association operation can be re-triggered. Which stage is triggered specifically can be determined based on the preset threshold. It should be understood that after the first stage association operation is re-triggered, the second stage association operation is often re-triggered, unless the comprehensive evaluation shows that the service effect provided by the user's service cluster can meet the user's current needs.

[0125] In some embodiments of the present application, the communication method based on the scalable de-cellularized MIMO system also includes: the access end jointly optimizes its own total transmission power and downlink power allocation through a power optimization model based on the large-scale fading information between the access end and the served user end; the downlink transmission power of the access end is determined based on the total transmission power and the downlink power allocation; wherein the access end includes a first target access end and / or a second target access end, and the power optimization model is obtained through training based on a convolutional neural network.

[0126] According to the service relationship between the access point and the user determined by the above-mentioned user association algorithm, each edge processor can complete the power allocation task for all users in the system by relying only on the large-scale fading information collected locally. At the same time, each access point only performs power allocation operations on the users it serves. In this way, the signaling overhead is reduced as much as possible and computing resources are saved. Among them, the power control algorithm can maximize the downlink communication rate as the optimization goal, has real-time and robustness, and can flexibly adapt to system scenarios with different numbers of associated users.

[0127] The power optimization method can be designed based on convolutional neural networks to jointly optimize the total transmission power of the access point and the power allocation strategy of the downlink. The power optimization model is deployed in the edge processor, which aims to perform efficient power allocation tasks through learning and optimization to maximize the long-term downlink data rate within the entire communication network.

[0128] Optionally, the power optimization model includes a stackable feature extraction network based on a residual network and two parallel output networks, and the training steps of the power optimization model may be:

[0129] An input tensor is determined by obtaining large-scale fading information, and a dimension of the input tensor is determined by a maximum number of service users of the communication system and a number of access terminals connected to the edge processor;

[0130] Input the input tensor into the feature extraction network to obtain large-scale fading information features;

[0131] The large-scale fading information features are input into the convolutional neural network, and the total transmission power decision tensor and the downlink power allocation decision tensor of the access end itself are obtained through the parallel output network;

[0132] Based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor, the model parameters are optimized and the training is completed.

[0133] Exemplarily, the large-scale fading information collected locally in the edge processor can be processed by a stackable feature extraction network based on a residual network. It should be understood that the communication system includes multiple edge processors, and the large-scale fading information collected by the nth edge processor can be modeled as a tensor Among them, M n and T represent the number of access points connected to the edge processor n and the number of input samples, respectively. The operation of the feature extraction network is shown in the following formula:

[0134] C=ConvBlock(B n ; {W, b});

[0135] Where ConvBlock represents the feature extraction network, W and b represent the weight and bias parameters in the feature extraction network respectively, and C represents the output value of the feature extraction network, which can be regarded as the feature of the extracted large-scale fading information. It should be understood that the network proposed in this application is constructed based on the maximum number of users in the system, and the maximum number of users K can be flexibly set according to the configuration of the actual system. Usually, the configuration of the system is determined, and the maximum number of users is also determined. Therefore, the configuration of the neural network in this application is also determined.

[0136] In the power optimization model, the data dimension of each processing is fixed to M n ×K, where M n and K are usually constants when the network system structure is determined.

[0137] In the actual communication system architecture, the embodiment of the present application uses the zero-filling operation of the convolutional neural network during the operation and calculation process, so that the input and output of the network can adapt to the dynamically changing number of associated users in the system. This improves the flexibility of distributed downlink power allocation. Therefore, on this basis, only a single training is required to efficiently handle scenarios with different numbers of associated users and meet the power allocation requirements in a dynamic network environment.

[0138] That is to say, in the actual model training process, it is not necessary to train for all situations, but only for the maximum number of users that the system can accommodate. Such training can handle scenarios with different numbers of associated users, thereby saving data resources. It is not necessary to collect data in scenarios related to various users, and the number of training times is reduced, further saving computing resources.

[0139] On this basis, the embodiment of the present application uses two parallel output networks to learn two decision variables, which are used to optimize the total transmit power and downlink power allocation of the access point respectively. The operation of the output network can be expressed as:

[0140] Y P =δ(FCB(C);θP )

[0141] Y η =δ(FCB(C);θ η );

[0142] Among them, FCB represents the output layer; δ is the activation function, which aims to normalize the output of the neural network to meet the power control constraint so that the total power of each power allocation does not exceed the maximum transmission power of each access point, θ represents the set of weights and biases in the network, C represents the output value of the feature extraction network, the subscripts P and η are used to refer to the two types of parameters in the network respectively, and Y represents the output tensor of the output network.

[0143] The dimensions of the output tensors are and That is, the output tensor dimension of the output layer is also designed to be constant, which means that the neural network proposed in this application can effectively deal with the problem of variable model input and output dimensions caused by changes in the number of associated users in the system. Through this design, the neural network can flexibly adapt to dynamically changing user association scenarios under the premise of fixed input and output dimensions.

[0144] The model parameters are optimized based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor.

[0145] For example, the neural network can be trained by an unsupervised learning strategy, with the goal of maximizing the total transmission rate of the downlink of the entire network. The loss function can be expressed as:

[0146]

[0147] In the formula, Θ is the total parameter of neural network learning; R k is the downlink transmission rate of user k. During the training process, the gradient descent strategy is used to update the parameters.

[0148] This completes the training of the power optimization model.

[0149] In some implementations, the downlink transmission power of the access terminal may be determined by a total transmission power decision tensor, a downlink power allocation decision tensor, and a maximum transmission power of the access terminal.

[0150] Exemplarily, the downlink transmission power of the access terminal can be expressed as:

[0151] P = diag(P max Y P )·Y η ;

[0152] In the above formula, P maxRepresents the maximum transmission power of each access point. diag(·) can generate a diagonal matrix with the input vector as the diagonal element. The power control task is completed according to the maximum transmission power of each access point combined with the operation between the decision variables of the downlink power allocation.

[0153] The embodiment of the present application adopts a distributed computing method, and can complete the operation only by relying on the information collected locally by the access point, without the need for centralized processing, thereby simplifying the calculation process, collaboratively optimizing the total transmission power and downlink power allocation of the access point, obtaining the optimal solution to the power control problem, and improving network performance; adopting a neural network that supports variable input and output dimensions (through the targeted design of the input and output layers of the neural network, a single model can flexibly adapt to scenarios with different numbers of associated users), only a single training is required to adapt to scenarios with different numbers of associated users, significantly enhancing the versatility and scalability of the system.

[0154] The present application also proposes a communication method based on a scalable decellularized MIMO system applied to a user terminal.

[0155] The communication method based on the scalable decellularized MIMO system applied to the user end includes:

[0156] First, determine the large-scale fading coefficients between itself and multiple access terminals, determine the access terminal with the largest large-scale fading coefficient as the first access terminal and send an association request;

[0157] In the case where the user terminal receives the association acceptance message sent by the first access terminal, the first access terminal is determined as the first target access terminal, wherein the first access terminal may determine whether to provide the association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel the association, and the competition mechanism (as exemplified in the above embodiment, it may include a triggering operation of the competition mechanism);

[0158] Afterwards, the user terminal establishes a service association with the first target access terminal and is determined by the first target access terminal as a user whose association cannot be cancelled;

[0159] Determine an access terminal whose large-scale fading coefficient is greater than or equal to its own service demand information as a second access terminal;

[0160] Sending an association request to all second access terminals;

[0161] In the case of receiving the association permission message sent by the second access terminal, determining the second access terminal as the second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and the competition mechanism (as exemplified in the above embodiment, it may include a triggering operation of the competition mechanism);

[0162] A user who establishes a service association with a second target access terminal and is determined by the second target access terminal as a user who can cancel the association;

[0163] The number of first target access terminals is 1, and the number of second target access terminals is 1 or more.

[0164] For example, when a user newly joins a communication network, the user will first measure the large-scale fading information between the user and the surrounding access points, and then send an association request to the access point with the largest large-scale fading information. After determining to associate, the user will further expand the number of access points that serve him / her, that is, will send association requests to multiple sites that meet the service requirements. When receiving consent to the association, multiple access points will provide communication services to the user, thereby improving the user's service quality.

[0165] The embodiment provided in the present application builds a service cluster consisting of limited access points for each user through a user association method, thereby effectively reducing the fronthaul requirements and computational complexity of the system and building a scalable de-cellular system.

[0166] The present application also proposes a communication method based on a scalable decellularized MIMO system applied to an access terminal.

[0167] The communication method based on the scalable decellularized MIMO system applied to the access terminal includes:

[0168] First, receiving an association request sent by a user terminal, the association request including a corresponding large-scale fading coefficient;

[0169] Determine whether to provide association service for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of users that can be disassociated, and the competition mechanism;

[0170] Based on the large-scale fading information obtained between the associated user terminals, the total transmission power and downlink power allocation of the system are jointly optimized through the power optimization model;

[0171] determining a downlink transmission power based on the total transmission power and the downlink power allocation;

[0172] Among them, the access end includes a first target access end and / or a second target access end, the number of the first target access end is 1, the number of the second target access end is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

[0173] In an actual communication system, the access point will calculate the large-scale fading coefficient of each user locally based on the received signal strength. The users served by the access point can be divided into two types, one of which is the user type that cannot cancel the service, and the other is the user type that can cancel the service.

[0174] When the access point receives an association request sent by a user, the access point first queries whether the number of users served by the access point has reached the maximum number of users. If the maximum number of users has not been reached, the access point receives the user's association request. If this is the first association request after the user accesses the network, the access point classifies the user into a non-cancellable service type; if this is not the first association request after the user accesses the network, the access point classifies the user into a cancellable service type.

[0175] When the access point receives an association request sent by a user, the access point first queries whether the number of users it serves has reached the maximum number of users. If the maximum number of users has been reached and there are users whose association can be cancelled at this time, the competition mechanism will be started or triggered. When the large-scale fading information (which can be a large-scale fading coefficient) between the requesting user and the access point is greater than the user with the smallest large-scale fading coefficient among the users whose association can be cancelled, the access point will cancel the association with the user with the smallest large-scale fading coefficient among the users whose association can be cancelled, and establish an association with the requesting user. At this time, the competition mechanism can ensure that each access point will select users with better channel conditions to provide services. If this is the first association request after the user accesses the network, the access point will classify the user as a non-cancellable service type; if this is not the first association request after the user accesses the network, the access point will classify the user as a cancellable service type.

[0176] When the access point receives an association request from a user, the access point first queries whether the number of users it serves has reached the maximum number of users. If the maximum number of users has been reached and there are no users whose association can be cancelled at the access point, the access point will reject the association request of the requesting user.

[0177] The access point can also jointly optimize its total transmission power and downlink power allocation through the power optimization model based on the large-scale fading information obtained between the associated user end. It should be understood that in order to save and balance computing resources, power optimization is usually performed by the edge processor on the access end side to achieve distributed computing.

[0178] Each edge processor can complete the power allocation task for the access point connected to it only by relying on the large-scale fading information collected locally. At the same time, each access point only performs power allocation operations for the users it serves. The power control algorithm optimizes the downlink communication rate to maximize the downlink communication rate. It has real-time and robustness and can flexibly adapt to system scenarios with different numbers of associated users.

[0179] Power control is mainly achieved through a power optimization model, wherein the training method of the power optimization model can be found in the above and will not be repeated here.

[0180] After obtaining the total transmission power and downlink power allocation output by the power optimization model, the downlink transmission power can be determined in combination with the maximum transmission power of each access point. The specific determination method can refer to the above and will not be repeated here.

[0181] The embodiments provided in the present application innovatively introduce the dual considerations of competition mechanism and user service demand in the user association method, and at the same time combine the workload limit of the access point, comprehensively analyze the user demand and the resource situation of the access point, select the most suitable access point for each user, and build an efficient service cluster; use the power optimization model to collaboratively optimize the total transmission power of the access point and the downlink power allocation to achieve targeted power control; the trained power optimization model can be completely based on the large-scale fading information collected locally, without the need for additional communication interaction, and through localized processing, the distributed nodes can independently complete the joint user association and power allocation operations.

[0182] The following is a detailed description and explanation of the solution of the embodiment of the present invention in conjunction with a specific application example:

[0183] Please refer to Figure 5 , Figure 5 It is a schematic diagram of the communication process based on the scalable de-cellularized MIMO system provided by some embodiments of the present application. Figure 5 In the case where user k just accesses the communication network, he first sends an association request to the nearby access point with the maximum fading information. The access point determines whether to provide association services to the requesting user based on the situation of its own service users (whether the number of service users has reached the maximum number of service users, whether there are users whose services can be cancelled, etc.). If there is an access point that provides services to the requesting user, at this time, the edge processor on the access point side will perform power control calculations on the access point. The access point controls its own downlink transmission power according to the power control strategy and performs channel estimation and coding to provide communication services to the requesting user. It should be understood that Figure 5 The arrow in the figure only indicates the direction of communication at a single time, and does not indicate the direction of communication at both ends. Figure 5 The communication direction is clearly defined in the , but the signal can also be transmitted in the completely opposite direction, which depends on the sender of the signal in the actual communication process.

[0184] The implementation of the communication device based on the scalable de-cellularized MIMO system provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0185] For the communication method based on the scalable decellularized MIMO system provided in the above embodiment, the embodiment of the present application also provides a communication device (which may be a user end) based on the scalable decellularized MIMO system, which is used to implement the above method, such as Figure 6As shown, Figure 6 This is a schematic block diagram of a module of a communication device based on a scalable decellularized MIMO system according to an embodiment of the present application. The communication device based on a scalable decellularized MIMO system includes:

[0186] A first determination module, configured to determine a first target access terminal according to large-scale fading information between the plurality of access terminals;

[0187] A first service association establishing module, configured to establish a service association with a first target access terminal, wherein the user terminal is determined by the first target access terminal as a user that cannot cancel the association;

[0188] A second determination module, used to determine a second target access terminal according to its own service demand information;

[0189] A second service association establishing module, configured to establish a service association with a second target access terminal, wherein the user terminal is determined by the second target access terminal as a user from which the association can be cancelled;

[0190] The number of first target access terminals is 1, and the number of second target access terminals is 1 or more.

[0191] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0192] For the communication method based on the scalable decellularized MIMO system provided in the above embodiment, the embodiment of the present application also provides another communication device (which may be an access terminal) based on the scalable decellularized MIMO system, which is used to implement the above method, such as Figure 7 As shown, Figure 7 This is a schematic block diagram of another communication device based on a scalable decellularized MIMO system according to an embodiment of the present application. The another communication device based on a scalable decellularized MIMO system includes:

[0193] A receiving module, used for receiving an association request sent by a user terminal, wherein the association request includes a corresponding large-scale fading coefficient;

[0194] A determination module, used to determine whether to provide association services for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of users that can be disassociated, and the competition mechanism;

[0195] A joint optimization module, used to jointly optimize its own total transmission power and downlink power allocation through a power optimization model based on the large-scale fading information obtained between the associated user terminals;

[0196] A power control module, configured to determine a downlink transmission power based on the total transmission power and the downlink power allocation;

[0197] Among them, the access end includes a first target access end and / or a second target access end, the number of the first target access end is 1, the number of the second target access end is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

[0198] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0199] Reference Figure 8 The embodiment of the present application further provides an electronic device 800, the electronic device 800 includes a memory 801, one or more processors 802 ( Figure 8 Only one is shown) and a computer program stored in the memory and executable on the processor. Among them: the memory 801 is used to store software programs and units, and the processor 802 executes various functional applications and data processing by running the software programs and units stored in the memory to obtain the resources corresponding to the above-mentioned preset events. Optionally, the processor implements the above-mentioned communication method based on the scalable decellularized MIMO system by running the above-mentioned computer program stored in the memory.

[0200] The memory, as a non-transitory computer-readable medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network.

[0201] It can be understood that the contents of the above method embodiments are all applicable to the electronic device embodiment, the functions specifically implemented by the electronic device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0202] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the communication method based on the scalable de-cellularized MIMO system is implemented.

[0203] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0204] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by one or more processors, it can implement the steps of the communication method based on the scalable de-cellularized MIMO system.

[0205] It can be understood that the contents of the above method embodiments are all applicable to the present computer program product, the functions specifically implemented by the present computer program product embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0206] The communication method, device, electronic device, medium and computer program product based on the scalable decellularized MIMO system provided in the embodiments of the present application determine a first target access terminal through large-scale fading information between a user terminal and multiple access terminals, then the user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association. On this basis, the user terminal determines a second target access terminal according to its own service demand information, then the user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user that can cancel the association, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more; thus, the user terminal determines the first target access terminal through large-scale fading information. The access terminal can select a service access terminal based on the attenuation characteristics of the signal at a macroscopic scale, thereby ensuring the service stability of the user terminal. On the basis that the user terminal establishes a service association with the first target access terminal and is determined by the first target access terminal as a user that cannot cancel the association, it is ensured that the user terminal can obtain continuous and stable services from an access point, thereby avoiding the risk of the access terminal exiting the network midway; on this basis, the user terminal determines the second target access terminal according to its own service demand information, thereby being able to expand the access points that serve it according to the service quality required by itself, thereby forming its own access point service cluster, that is, the number of the second target access terminals is one or more, ensuring that one or more suitable access points are dynamically selected for each user terminal to provide services, thereby improving the user's service quality.

[0207] The communication method, device, electronic device, medium and computer program product based on the scalable decellularized MIMO system provided in the embodiment of the present application, by introducing a competition mechanism, comprehensively considers the access point workload and user service requirements, and proposes a two-stage user association strategy. In the first stage, a preferred access point is assigned to each user according to the channel quality to ensure that the user obtains basic services; in the second stage, its service cluster is expanded based on the user's service needs, and at the same time, combined with the competition mechanism, the most suitable access point is dynamically selected for the user in the two stages, and finally an efficient service cluster is constructed. This method effectively improves the user's service quality and the resource utilization efficiency of the system. In addition, the existing downlink power control method fails to coordinately optimize the total transmission power of the access point and the downlink power allocation, and cannot adapt to the dynamic changes in the number of associated users in the system. To this end, the embodiment of the present application proposes a downlink power control algorithm based on a convolutional neural network. By designing two parallel output networks, the algorithm can simultaneously optimize the total transmission power and downlink power allocation of the access point. More importantly, the present invention innovatively designs a neural network structure with fixed input and output layer dimensions, so that a single neural network can flexibly adapt to system scenarios with different numbers of associated users with only one training. In addition, the method proposed in this application is completely based on large-scale fading information collected locally, without the need for additional communication interaction. Through localized processing, distributed nodes can independently complete joint user association and power allocation operations.

[0208] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0209] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0210] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to the exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.

[0211] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.

[0212] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the exemplary methods described herein) to be performed.

[0213] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by the hardware architecture and / or the platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages ​​include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages ​​or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.

[0214] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0215] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A communication method based on a scalable decellularized MIMO system, characterized in that: The following steps are involved: The user end determines a first target access end according to large-scale fading information between the user end and the plurality of access ends; The user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association; The user end determines the second target access end according to its own service demand information; The user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user from which the association can be cancelled; The number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

2. The communication method based on the scalable decellularized MIMO system according to claim 1, characterized in that: The method further comprises: The access end jointly optimizes its own total transmission power and downlink power allocation through a power optimization model according to the acquired large-scale fading information between the access end and the served user end; Determining a downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation; The access end includes the first target access end and / or the second target access end, and the power optimization model is obtained through training based on a convolutional neural network.

3. The communication method based on the scalable decellularized MIMO system according to claim 2, characterized in that: The power optimization model includes a stackable feature extraction network based on a residual network and two parallel output networks, and the training steps of the power optimization model include: Determine an input tensor by using the acquired large-scale fading information, wherein the dimension of the input tensor is determined by the maximum number of service users of the communication system and the number of access terminals connected to the edge processor; Inputting the input tensor into the feature extraction network to obtain large-scale fading information features; Inputting the large-scale fading information feature into the convolutional neural network, and obtaining the total transmission power decision tensor and the downlink power allocation decision tensor of the access terminal itself through the parallel output network; Based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor, the model parameters are optimized to complete the training.

4. The communication method based on the scalable decellularized MIMO system according to claim 3, characterized in that: The determining the downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation includes: The downlink transmission power of the access end is determined by the total transmission power decision tensor, the downlink power allocation decision tensor, and the maximum transmission power of the access end.

5. The communication method based on the scalable decellularized MIMO system according to claim 1, characterized in that: The access terminal includes a user whose association can be cancelled, and the user terminal determines a first target access terminal according to large-scale fading information between the user terminal and a plurality of access terminals, including: The user end determines the large-scale fading coefficients between itself and the plurality of access ends, determines the access end with the largest large-scale fading coefficient as the first access end and sends an association request; If the number of user terminals served by the first access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the first access terminal as a first target access terminal; If the number of user terminals served by the first access terminal is equal to the maximum number of serviceable users and the user whose association can be cancelled exists on the first access terminal, then, if the large-scale fading coefficient between the user terminal and the first access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, control the first access terminal to cancel the association of the associated user corresponding to the minimum large-scale fading coefficient, receive an association request sent by the user terminal, and determine the first access terminal as a first target access terminal; If there is no user whose association can be cancelled at the first access terminal, the user terminal determines the access terminal with the second largest large-scale fading coefficient as a new first access terminal and sends an association request.

6. The communication method based on the scalable decellularized MIMO system according to claim 1, characterized in that: The user terminal determines the second target access terminal according to its own service demand information, including: The user end determines a large-scale fading coefficient between itself and a plurality of access ends, and determines an access end whose large-scale fading coefficient is greater than or equal to its own service demand information as a second access end; The user terminal sends an association request to all the second access terminals; If the number of user terminals served by the second access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the second access terminal as a second target access terminal; If the number of user terminals served by the second access terminal is equal to the maximum number of serviceable users and there are users whose association can be cancelled on the second access terminal, then when the large-scale fading coefficient between the user terminal and the second access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, the second access terminal is controlled to cancel the association with the associated user corresponding to the minimum large-scale fading coefficient, and an association request sent by the user terminal is received, and the second access terminal is determined as a second target access terminal.

7. A communication method based on a scalable decellularized MIMO system, characterized in that: Applied to the user end, the communication method based on the scalable decellularized MIMO system includes the following steps: Determine a large-scale fading coefficient between itself and a plurality of access terminals, determine the access terminal having the largest large-scale fading coefficient as a first access terminal and send an association request; In the case of receiving the association permission message sent by the first access terminal, determining the first access terminal as a first target access terminal, wherein the first access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and a competition mechanism; A user who has established a service association with the first target access terminal and is determined by the first target access terminal as a user who cannot cancel the association; Determine the access terminal whose large-scale fading coefficient is greater than or equal to its own service demand information as the second access terminal; Sending an association request to all of the second access terminals; In the case of receiving the association permission message sent by the second access terminal, determining the second access terminal as the second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and the competition mechanism; A user who has established a service association with the second target access terminal and is determined by the second target access terminal as a user whose association can be cancelled; The number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

8. A communication method based on a scalable decellularized MIMO system, characterized in that: Applied to the access end, the communication method based on the scalable decellularized MIMO system comprises the following steps: receiving an association request sent by a user terminal, wherein the association request includes a corresponding large-scale fading coefficient; Determining whether to provide association service for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of users that can be disassociated, and a competition mechanism; Based on the large-scale fading information obtained between the associated user terminals, the total transmission power and downlink power allocation of the system are jointly optimized through the power optimization model; determining a downlink transmission power based on the total transmission power and the downlink power allocation; Among them, the access end includes a first target access end and / or a second target access end, the number of the first target access end is 1, the number of the second target access end is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the communication method based on the scalable de-cellularized MIMO system as described in any one of claims 1 to 6, 7 or 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the communication method based on a scalable de-cellularized MIMO system according to any one of claims 1 to 6, 7 or 8 is implemented.

Images