Non-feedback transmission and dynamic resource allocation method for space-air-ground integration-oriented full-decoupling network

Abstract

The invention discloses a space-air-ground integration-oriented full-decoupling network non-feedback transmission and resource dynamic allocation method. A solution is provided for space-air-ground multi-node cooperation resource management. The method comprises the steps that a channel state information prediction model based on deep learning replaces traditional feedback signals with user geographical location information, and multiple-input-multiple-output transmission is achieved; and a many-to-one matching model is designed and is used for realizing adaptive allocation of spectrum resource blocks among space-air-ground heterogeneous nodes, so that the matching stability is ensured, and the method has the characteristics of low complexity and rapid convergence. For cooperative transmission of multiple nodes and resource allocation among heterogeneous nodes, the spectrum efficiency of the system is improved through non-feedback channel state information prediction and a resource allocation mechanism. Compared with a single connection mode and polling-based resource scheduling in a traditional network, the flexible resource allocation algorithm disclosed by the invention remarkably improves the network capacity and improves the user communication quality.

Description

Technical Field

[0001] The present invention belongs to the field of air-ground-integrated fully decoupled network transmission mechanism and resource allocation, and relates to an air-ground-integrated fully decoupled network feedback-free transmission and resource dynamic allocation method. Background Art

[0002] In recent years, space-air-ground integrated networks (SAGIN) have gradually become a key paradigm for achieving ubiquitous connectivity, high capacity, and strong reliability in 6G. Satellite projects represented by Starlink have launched products such as STARLINK WIFI routers, providing users with transmission rates of 8-25Mbps uplink and 40-220Mbps downlink. The system receives signals through low-orbit satellites and converts the signals into WiFi for user terminals. In addition, unmanned aerial vehicles (UAVs) play a key role in the low-altitude economy, providing enhancement and support services for ground communications. However, integrating these heterogeneous nodes into a unified network faces challenges in resource allocation and coordination between satellites, drones, and ground base stations. According to the non-terrestrial networks (NTN) standard of the 3rd Generation Partnership Project (3GPP), satellites use frequency division duplex (FDD) mode, while terrestrial 5G networks use time division duplex (TDD) mode. The difference between the two increases the complexity of network integration, highlighting the need to adjust terrestrial networks and develop new technologies to achieve heterogeneous integration of SAGIN.

[0003] From 4G to 5G, the core network architecture has achieved the separation of the control plane and the user plane, improving the flexibility of the network. However, on the radio access network (RAN) side of 5G, each base station still needs to be configured with control functions and user plane functions. In 2019, the team of Academician Yu Quan published a 6G fully decoupled radio access network (FD-RAN) titled "A Fully-Decoupled RAN Architecture for 6G Inspired by Neurotransmission" in the Journal of Communications and Information Networks. In this paper, the base station is physically decoupled into a control base station, an uplink base station, and a downlink base station. Through this decoupled design, spectrum resources can be flexibly allocated and more efficient collaboration between heterogeneous nodes can be promoted. In this context, this paper proposes an air-ground integrated FD-RAN architecture, which enables the ground network infrastructure to adopt FD-RAN and combines satellite and drone nodes. Achieving flexible collaboration and resource management between these heterogeneous nodes remains a key challenge.

[0004] After searching the existing literature, it was found that few documents proposed the base station feedback-free mechanism in the space-ground integrated fully decoupled network, as well as the dynamic resource joint scheduling of base stations, satellite WiFi router nodes and drones. Kai Yu et al. published "Fully-Decoupled Radio Access Networks: A Flexible Downlink Multi-Connectivity and Dynamic Resource Cooperation Framework" in "IEEE Transactions on Wireless Communications" and proposed a multi-base station joint transmission algorithm, which requires users to feedback the complete channel. However, the article did not take into account the overhead and real-time performance of feedback of the complete channel, especially after the base station is decoupled, the uplink and downlink are transmitted through different base stations, and the channel reciprocity cannot be used to obtain the complete channel for downlink transmission.

[0005] In summary, the problems existing in the prior art are: (1) The traditional downlink multiple-input multiple-output (MIMO) transmission method based on channel feedback is no longer applicable to FD-RAN, and the feedback-free MIMO downlink transmission method needs to be redesigned. (2) Unlike the user-access node single connection mode of the existing mobile communication network and the spectrum resource block (RB) allocation method based on polling scheduling, the multi-user-multi-node-multi-resource block allocation in the air-ground integrated FD-RAN is an ultra-large-scale non-convex integer programming problem, which requires the design of a low-complexity 0-1 integer programming algorithm. The significance of solving the above technical problems is that the air-ground integrated network is one of the typical application scenarios of 6G, and the proposed solution is helpful to lay out the 6G network technology reserves and provide theoretical guidance and reference for the 6G architecture and algorithm design. Summary of the invention

[0006] Purpose of the invention: In view of the problems existing in the prior art, the purpose of the present invention is to provide a method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for air-ground integration, to realize a feedback-free MIMO transmission mechanism for downlink base stations, as well as flexible collaboration of multiple air-ground-ground heterogeneous nodes and dynamic allocation of spectrum resource blocks.

[0007] Technical solution: To achieve the above-mentioned invention object, the present invention adopts the following technical solution:

[0008] A method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration includes the following steps:

[0009] Step 1: The edge cloud collects channel state information (CSI) historical data, including user location and CSI information of corresponding spectrum resource blocks;

[0010] Step 2: The edge cloud uses a neural network to train CSI historical data for each spectrum resource block of each downlink base station. The input is the user location and the output is the CSI information.

[0011] Step 3: The control base station collects user access requests and real-time geographic locations and feeds them back to the edge cloud;

[0012] Step 4: The edge cloud dynamically allocates resources based on the user-heterogeneous node-spectrum resource block allocation algorithm of the many-to-one matching model, and sends the user location and resource block allocation decision to the downlink base station;

[0013] Step 5: The downlink base station predicts CSI information on the resource block to be transmitted;

[0014] Step 6: The downlink base station performs feedback-free MIMO transmission based on a closed-loop spatial division multiplexing mode.

[0015] Furthermore, the user-heterogeneous node-spectrum resource block allocation algorithm based on the many-to-one matching model constructs a spectrum resource block allocation problem and realizes dynamic resource allocation based on the many-to-one matching model; the spectrum resource block allocation problem aims to maximize the system throughput, and through constraints, ensures that each user is allocated to at least one node's spectrum resource block, each spectrum resource block can only be allocated to one user, and the total transmission rate of the WiFi nodes will not exceed the maximum downlink transmission rate of the satellite-to-satellite WiFi router.

[0016] Furthermore, the spectrum resource block allocation problem RAP is expressed as:

[0017]

[0018]

[0019]

[0020] Where X, Y, and Z represent the matching matrices of base station (BS)-resource block (RB) pairs, WiFi-RB pairs, and unmanned aerial vehicle (UAV)-RB pairs to users, respectively; B, S, and U represent the number of BS-RB pairs, WiFi-RB pairs, and UAV-RB pairs, respectively. They represent the BS-RB pair, WiFi-RB pair and UAV-RB pair set respectively, R B (X) represents the throughput of the BS-RB pair, R S (Y) represents the throughput of the satellite WiFi-RB pair, R U (Z) represents the throughput of the UAV-RB pair, M represents the total number of users, T S represents the maximum downlink throughput rate from satellite to WiFi; the two-dimensional 0-1 variable X(b,m) represents whether BS-RB serves user m for b, if yes, it takes 1, otherwise it takes 0; the two-dimensional 0-1 variable Y(s,m) represents whether WiFi-RB serves user m for s, if yes, it takes 1, otherwise it takes 0; the two-dimensional 0-1 variable Z(u,m) represents whether UAV-RB serves user m for u, if yes, it takes 1, otherwise it takes 0.

[0021] Furthermore, after the neural network on each spectrum resource block of each downlink base station is trained, the edge cloud sends the trained neural network to each downlink base station.

[0022] Furthermore, the dynamic resource allocation is realized based on the many-to-one matching model. During the matching initialization process, the most suitable user is assigned to each node-resource block pair for connection based on the user preference list; during the matching exchange stage, two node-resource block pairs are traversed in sequence, and if the matched users are different, an exchange attempt is started; in each round of matching, three matching exchange strategies are tried for each user, so that only the strategy that improves the total throughput of the system will be accepted.

[0023] Furthermore, the dynamic resource allocation is realized based on the many-to-one matching model, and the specific steps are as follows:

[0024] Step 4.1: In the algorithm initialization phase, first input the physical layer throughput estimate of the user to each node-resource block pair;

[0025] Step 4.2: The user generates a preference list according to the physical layer throughput estimate from large to small;

[0026] Step 4.3: Each user initiates a request in turn, and the user requests the best node-resource block pair;

[0027] Step 4.4: The node-resource block pair accepts the request if and only if no other matches are received;

[0028] Step 4.5: When each user is assigned a node-resource block pair, the matching exchange phase begins;

[0029] Step 4.6: In the matching and exchange phase, traverse the two node-resource block pairs in order. If the matched users are different, start the exchange attempt;

[0030] Step 4.7: Calculate the current total system throughput;

[0031] Step 4.8: Exchange attempt 1: Exchange two users with matching node-resource block pairs;

[0032] Step 4.9: Check whether the previous user matches other resource blocks. If so, make an exchange attempt 2: let both node-resource blocks match the previous user at the same time, otherwise skip this step;

[0033] Step 4.10: Check whether the next user matches other resource blocks. If so, perform exchange attempt 3: let the two node-resource blocks match the next user at the same time, otherwise skip this step;

[0034] Step 4.11: Compare exchange attempts 1-3 with the initial throughput and select the best strategy to update the match;

[0035] Step 4.12: Perform the next round of matching and exchange until all traversals are completed.

[0036] Furthermore, in the air-ground integrated fully decoupled network, users are served by multiple air-ground heterogeneous nodes simultaneously, and spectrum resource blocks are dynamically allocated among the heterogeneous nodes; the air-ground heterogeneous nodes include drone nodes, satellite WiFi routers and fully decoupled network downlink base stations.

[0037] Furthermore, downlink base station transmission relies on channel state information to determine the transmission parameters of each resource block, including: rank indicator RI, channel quality indicator CQI and precoding matrix indicator PMI; the base station determines the specific parameters of downlink MIMO transmission based on these parameters; referring to the 3GPP standard, the bit rate is calculated based on CQI, the number of transmission streams is calculated based on RI, and the physical layer throughput estimate is calculated in combination with the predicted or fed-back CSI.

[0038] Based on the same inventive concept, the present invention provides a fully decoupled network feedback-free transmission and resource dynamic allocation system for air-ground integration, including an edge cloud, a control base station, and a downlink base station;

[0039] The edge cloud is used to collect channel state information (CSI) historical data, including user positions and CSI information of corresponding spectrum resource blocks; for each spectrum resource block of each downlink base station, a neural network is used to train the CSI historical data, with the input being the user position and the output being the CSI information; and a user-heterogeneous node-spectrum resource block allocation algorithm based on a many-to-one matching model is used to dynamically allocate resources, and send the user position and resource block allocation decision to the downlink base station;

[0040] The control base station is used to collect user access requests and real-time geographic locations and feed them back to the edge cloud;

[0041] The downlink base station is used to predict CSI information on the resource block to be transmitted; and perform feedback-free MIMO transmission based on a closed-loop space division multiplexing mode.

[0042] Beneficial effects: Compared with the prior art, the beneficial effects of the present invention are as follows: First, the feedback-free transmission and dynamic resource allocation method of the fully decoupled network for air-ground-ground integration can effectively improve the capacity and resource utilization of the air-ground-ground integrated network system; secondly, considering the specific mode of uplink and downlink decoupling in the fully decoupled network, the present invention proposes a CSI prediction method based on deep learning and a downlink base station feedback-free transmission mechanism; finally, facing the collaboration and resource allocation problems between users and multiple air-ground-ground heterogeneous access nodes on multiple spectrum resource blocks, the present invention proposes a multi-heterogeneous node collaboration and spectrum resource block allocation algorithm based on a many-to-one matching model, which can effectively improve system performance. Compared with the spectrum resource block allocation based on polling scheduling and the single-user-single-node connection method with power balancing in traditional networks, the flexible multi-node collaboration and efficient dynamic resource allocation algorithm can effectively improve network capacity and improve the service quality of mobile user communications. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a scenario diagram of the air-ground-integrated fully decoupled network feedback-free transmission and resource dynamic allocation method for which the embodiment of the present invention is directed.

[0044] Figure 2 It is a flow chart of the CSI prediction based on deep learning and downlink base station feedback-free MIMO transmission mechanism proposed in an embodiment of the present invention.

[0045] Figure 3 It is a step diagram of a user-heterogeneous node-spectrum resource block allocation algorithm based on a many-to-one matching model proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the embodiments of the present invention are described in detail below in conjunction with the accompanying drawings: This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given. It should be understood that the specific examples described here are only used to explain the present invention, but the protection scope of the present invention is not limited to the following embodiments.

[0047] The embodiment of the present invention discloses a method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration, which mainly involves CSI prediction based on deep learning and downlink base station feedback-free MIMO transmission mechanism, as well as multi-heterogeneous node collaboration and spectrum resource block allocation algorithm based on a many-to-one matching model. A channel state information prediction model based on deep learning is adopted, and the traditional feedback signal is replaced by the user's geographic location information to realize feedback-free MIMO transmission of downlink base stations. In a fully decoupled network for space-ground integration, users can be served by multiple space-ground heterogeneous nodes at the same time, and spectrum resource blocks can be dynamically allocated between heterogeneous nodes to improve system performance.

[0048] The 6G fully decoupled network architecture considered in this embodiment is as follows: Figure 1 As shown in the figure, it consists of multiple downlink base stations (DBS), satellite WiFi routers, drones, and multiple users at random locations. For the downlink transmission of the air-ground integrated FD-RAN, we define matrices X, Y, and Z to represent the matching of base station (BS)-resource block (RB) pairs, WiFi-RB pairs, and unmanned aerial vehicle (UAV)-RB pairs to users, respectively. The two-dimensional 0-1 variable X(b,m) indicates whether the BS-RB pair b serves user m. If yes, X(b,m) takes 1, otherwise X(b,m) takes 0. Similarly, a two-dimensional 0-1 variable Y(s,m) is defined to indicate whether the WiFi-RB pair s serves user m. If yes, Y(s,m) takes 1, otherwise Y(s,m) takes 0. A two-dimensional 0-1 variable Z(u,m) is defined to indicate whether the UAV-RB pair u serves user m. If yes, Z(u,m) takes 1, otherwise Z(u,m) takes 0.

[0049] According to the 3GPP physical layer standard, for the feedback-based MIMO transmission mode, namely closed-loop spatial multiplexing (CLSM), the downlink base station transmission relies on channel state information (CSI) to determine the transmission parameters of each resource block (RB), including: 1. Rank Indicator (RI): The recommended number of spatial multiplexing data streams, indicating the number of parallel data streams supported by the current channel. 2. Channel Quality Indicator (CQI): The recommended channel coding rate and modulation scheme to adapt to the current channel quality. 3. Precoding Matrix Indicator (PMI): The recommended precoding matrix index, which is used to select the optimal precoding matrix in the codebook designed by the terminal. The base station can determine the specific parameters of the downlink MIMO transmission based on these parameters. Referring to the 3GPP standard, the code rate can be calculated based on the CQI, and the number of transmission streams can be calculated based on the RI. Therefore, the physical layer throughput estimate can be calculated in combination with the predicted or fed-back CSI.

[0050] In the air-ground integrated FD-RAN downlink transmission scenario, first of all, for the downlink base station, since it is impossible to obtain real-time CSI information feedback from users, we propose a set of CSI prediction based on deep learning and downlink base station feedback-free MIMO transmission mechanism. The flow chart is as follows: Figure 2As shown. First, the edge cloud collects CSI historical data, including user location and CSI information of the corresponding spectrum resource block. Next, the edge cloud uses a neural network (such as a fully connected layer neural network or other deep neural network) to train the CSI historical data for each spectrum resource block. The input is the user location and the output is the CSI information. The control base station collects user access requests and real-time geographic location and feeds them back to the edge cloud. The edge cloud dynamically allocates resources and sends the user location and resource block allocation decision to the downlink base station. Then, the downlink base station predicts the CSI information on the resource block to be transmitted. Finally, the downlink base station performs feedback-free MIMO transmission based on a closed-loop spatial division multiplexing mode.

[0051] Therefore, the multi-heterogeneous node collaboration and spectrum resource block allocation problem (RAP) of the air-ground integrated FD-RAN can be modeled as:

[0052]

[0053]

[0054]

[0055] Where B, S, and U represent the number of BS-RB pairs, WiFi-RB pairs, and UAV-RB pairs, respectively. They represent the BS-RB pair, WiFi-RB pair and UAV-RB pair set respectively, R B (X) represents the throughput of the BS-RB pair, R S (Y) represents the throughput of the satellite WiFi-RB pair, R U (Z) represents the throughput of the UAV-RB pair, M represents the total number of users, T S represents the maximum downlink throughput rate from satellite to WiFi. In the objective function, R B (X(b,m)) represents the physical layer’s estimated throughput based on CSI when BS-RB pair b serves user m. The WiFi-RB throughput R is derived from the user’s CSI feedback. S (Y(s,m)) and UAV-RB throughput R U (Z(u,m)). Constraint (C1) ensures that each user is assigned to at least one node’s RB to guarantee the minimum quality of service. Constraint (C2) ensures that each RB can only be assigned to one user to avoid interference between nodes. Constraint (C3) represents the maximum downlink transmission rate from satellite to satellite WiFi router.

[0056] Considering that all variables in this problem are 0-1 variables, we use a many-to-one matching model algorithm to solve it, which has the characteristics of low complexity and fast convergence. In the matching initialization process, based on the user preference list, the most suitable user is assigned to each node-resource block pair for connection; in the matching exchange phase, two node-resource block pairs are traversed in order, and if the matched users are different, an exchange attempt is started; in each round of matching, three matching exchange strategies are tried for each user, and only the strategy that improves the total throughput of the system will be accepted.

[0057] The corresponding algorithm execution process is as follows Figure 3 The specific steps are as follows:

[0058] Step 1: In the algorithm initialization phase, the physical layer throughput estimate of the user to each node-resource block pair is first input.

[0059] Step 2: The user generates a preference list based on the physical layer throughput estimate from large to small.

[0060] Step 3: Next, each user initiates a request in turn, and the user requests the best node-resource block pair.

[0061] Step 4: A node-resource block pair accepts the request if and only if no other matches are received.

[0062] Step 5: When there are enough resources, it means that each user is equipped with a node-resource block pair, and the matching exchange phase begins.

[0063] Step 6: In the matching exchange phase, traverse the two node-resource block pairs in order. If the matched users are different, start the exchange attempt.

[0064] Step 7: First, calculate the current total system throughput.

[0065] Step 8: Swap Attempt 1: Swap the users whose two node-resource block pairs match.

[0066] Step 9: Check whether the previous user matches other resource blocks. If so, make an exchange attempt 2: let the two node-resource blocks match the previous user at the same time, otherwise skip this step.

[0067] Step 10: Check whether the next user matches other resource blocks. If so, make an exchange attempt 3: let the two node-resource blocks match the previous user at the same time, otherwise skip this step.

[0068] Step 11: Compare exchange attempts 1-3 with the initial throughput and select the best strategy to update the match.

[0069] Step 12: Then proceed to the next round of matching and exchange until all traversals are completed.

[0070] Based on the same inventive concept, an embodiment of the present invention discloses a fully decoupled network feedback-free transmission and resource dynamic allocation system for air-ground integration, including an edge cloud, a control base station, and a downlink base station; the edge cloud is used to collect channel state information (CSI) historical data, including user positions and CSI information of corresponding spectrum resource blocks; for each spectrum resource block of each downlink base station, a neural network is used to train the CSI historical data, the input is the user position, and the output is the CSI information; and a user-heterogeneous node-spectrum resource block allocation algorithm based on a many-to-one matching model is used to dynamically allocate resources, and send the user position and resource block allocation decision to the downlink base station; the control base station is used to collect user access requests and real-time geographic locations, and feed them back to the edge cloud; the downlink base station is used to predict CSI information on the resource blocks to be transmitted; feedback-free MIMO transmission is performed based on a closed-loop space division multiplexing mode.

[0071] The user-heterogeneous node-spectrum resource block allocation algorithm based on the many-to-one matching model constructs a spectrum resource block allocation problem and realizes dynamic resource allocation based on the many-to-one matching model; the spectrum resource block allocation problem aims to maximize the system throughput, and through constraints, ensures that each user is allocated to at least one node's spectrum resource block, each spectrum resource block can only be allocated to one user, and the total transmission rate of the WiFi nodes will not exceed the maximum downlink transmission rate of the satellite-to-satellite WiFi router.

[0072] For details of the specific implementation, please refer to the above method implementation, which will not be repeated here.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention. Anything not described in detail in the present invention is a well-known technology for those skilled in the art.

Claims

1. A method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration, characterized in that: The steps include: Step 1: The edge cloud collects channel state information (CSI) historical data, including the user location and the CSI information of the corresponding spectrum resource block; Step 2: The edge cloud uses a neural network to train CSI historical data for each spectrum resource block of each downlink base station. The input is the user location and the output is the CSI information. Step 3: The control base station collects user access requests and real-time geographic locations and feeds them back to the edge cloud; Step 4: The edge cloud dynamically allocates resources based on the user-heterogeneous node-spectrum resource block allocation algorithm of the many-to-one matching model, and sends the user location and resource block allocation decision to the downlink base station; Step 5: The downlink base station predicts CSI information on the resource block to be transmitted; Step 6: The downlink base station performs feedback-free MIMO transmission based on a closed-loop spatial division multiplexing mode.

2. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 1, characterized in that: The user-heterogeneous node-spectrum resource block allocation algorithm based on the many-to-one matching model constructs a spectrum resource block allocation problem and realizes dynamic resource allocation based on the many-to-one matching model; the spectrum resource block allocation problem aims to maximize the system throughput, and through constraints, ensures that each user is allocated to at least one node's spectrum resource block, each spectrum resource block can only be allocated to one user, and the total transmission rate of the WiFi nodes will not exceed the maximum downlink transmission rate of the satellite-to-satellite WiFi router.

3. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 2, characterized in that: The spectrum resource block allocation problem RAP is expressed as: Where X, Y, and Z represent the matching matrices of base station (BS)-resource block (RB) pairs, WiFi-RB pairs, and unmanned aerial vehicle (UAV)-RB pairs to users, respectively; B, S, and U represent the number of BS-RB pairs, WiFi-RB pairs, and UAV-RB pairs, respectively. They represent the BS-RB pair, WiFi-RB pair and UAV-RB pair set respectively, R B (X) represents the throughput of the BS-RB pair, R S (Y) represents the throughput of the satellite WiFi-RB pair, R U (Z) represents the throughput of the UAV-RB pair, M represents the total number of users, T S represents the maximum downlink throughput rate from satellite to WiFi; the two-dimensional 0-1 variable X(b, m) represents whether BS-RB serves user m for b, if yes, it takes 1, otherwise it takes 0; the two-dimensional 0-1 variable Y(s, m) represents whether WiFi-RB serves user m for s, if yes, it takes 1, otherwise it takes 0; the two-dimensional 0-1 variable Z(u, m) represents whether UAV-RB serves user m for u, if yes, it takes 1, otherwise it takes 0.

4. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 3 is characterized in that: After the neural network on each spectrum resource block of each downlink base station is trained, the edge cloud sends the trained neural network to each downlink base station.

5. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 2, characterized in that: The dynamic resource allocation is realized based on the many-to-one matching model. In the matching initialization process, the most suitable user is assigned to each node-resource block pair for connection based on the user preference list; in the matching exchange phase, two node-resource block pairs are traversed in order, and if the matched users are different, an exchange attempt is started; In each round of matching, three matching exchange strategies are tried for each user, and only the strategy that improves the total throughput of the system will be accepted.

6. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 5, characterized in that: The dynamic resource allocation is realized based on the many-to-one matching model, and the specific steps are as follows: Step 4.1: In the algorithm initialization phase, first input the physical layer throughput estimate of the user to each node-resource block pair; Step 4.2: The user generates a preference list according to the physical layer throughput estimate from large to small; Step 4.3: Each user initiates a request in turn, and the user requests the best node-resource block pair; Step 4.4: The node-resource block pair accepts the request if and only if no other matches are received; Step 4.5: When each user is assigned a node-resource block pair, the matching exchange phase begins; Step 4.6: In the matching and exchange phase, traverse the two node-resource block pairs in order. If the matched users are different, start the exchange attempt; Step 4.7: Calculate the current total system throughput; Step 4.8: Exchange attempt 1: Exchange two users with matching node-resource block pairs; Step 4.9: Check whether the previous user matches other resource blocks. If so, make an exchange attempt 2: let both node-resource blocks match the previous user at the same time, otherwise skip this step; Step 4.10: Check whether the next user matches other resource blocks. If so, perform exchange attempt 3: let the two node-resource blocks match the next user at the same time, otherwise skip this step; Step 4.11: Compare exchange attempts 1-3 with the initial throughput and select the best strategy to update the match; Step 4.12: Perform the next round of matching and exchange until all traversals are completed.

7. The method for non-feedback transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 1, characterized in that: In the air-ground integrated fully decoupled network, users are served by multiple air-ground heterogeneous nodes simultaneously, and spectrum resource blocks are dynamically allocated among the heterogeneous nodes; the air-ground heterogeneous nodes include drones, satellite WiFi routers and fully decoupled network downlink base stations.

8. The method for feedback-free transmission and dynamic resource allocation of a fully decoupled network for space-ground integration according to claim 1, characterized in that: Downlink base station transmission relies on channel state information to determine the transmission parameters of each resource block, including: rank indicator RI, channel quality indicator CQI and precoding matrix indicator PMI; the base station determines the specific parameters of downlink MIMO transmission based on these parameters; referring to the 3GPP standard, the code rate is calculated based on CQI, the number of transmission streams is calculated based on RI, and the physical layer throughput estimate is calculated in combination with the predicted or fed-back CSI.

9. A fully decoupled network feedback-free transmission and resource dynamic allocation system for space-ground integration, characterized in that: Including edge cloud, control base station, and downlink base station; The edge cloud is used to collect channel state information (CSI) historical data, including user positions and CSI information of corresponding spectrum resource blocks; for each spectrum resource block of each downlink base station, a neural network is used to train the CSI historical data, with the input being the user position and the output being the CSI information; and a user-heterogeneous node-spectrum resource block allocation algorithm based on a many-to-one matching model is used to dynamically allocate resources, and send the user position and resource block allocation decision to the downlink base station; The control base station is used to collect user access requests and real-time geographic locations and feed them back to the edge cloud; The downlink base station is used to predict CSI information on the resource block to be transmitted; Feedback-free MIMO transmission is performed based on closed-loop spatial division multiplexing mode.

10. The air-ground-space integrated fully decoupled network feedback-free transmission and resource dynamic allocation system according to claim 9, characterized in that: The user-heterogeneous node-spectrum resource block allocation algorithm based on the many-to-one matching model constructs a spectrum resource block allocation problem and realizes dynamic resource allocation based on the many-to-one matching model; the spectrum resource block allocation problem aims to maximize the system throughput, and through constraints, ensures that each user is allocated to at least one node's spectrum resource block, each spectrum resource block can only be allocated to one user, and the total transmission rate of the WiFi nodes will not exceed the maximum downlink transmission rate of the satellite-to-satellite WiFi router.

Images