Wireless communication adaptive method and system based on data transmission state

Abstract

The invention relates to the technical field of wireless communication, and discloses a wireless communication adaptive method and system based on a data transmission state, and the method comprises the steps: obtaining multi-source data, carrying out the preprocessing of the multi-source data, obtaining a CSI compression matrix, predicting the channel coherence time, dynamically adjusting the CSI sampling interval, and defining a load-channel coupling factor; obtaining cross-layer data based on the CSI compression matrix, performing fusion through a rotation matrix to obtain a fusion matrix, and extracting a physical layer fusion feature and an application layer fusion feature to calculate a multi-target state score; establishing a 5G power compensation mechanism based on cross-layer data, calculating a four-dimensional influence tensor, performing tensor decomposition and optimal action selection, and decomposing T into a core tensor and a factor matrix; selecting an optimal parameter combination through modular product calculation; based on cross-layer data, a quantum entanglement feedback mechanism is introduced, data is fed back, entanglement state association cross-layer indexes are designed, a quantum gate is adjusted through entanglement state design, and a model is updated in real time in combination with incremental learning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and in particular to a wireless communication adaptive method and system based on data transmission state. BACKGROUND

[0002] In the prior art, the overall performance of the network is not comprehensively considered, the adaptive rate control method of the LoRa network only depends on the local link state between the terminal and the gateway, and the channel conflict and network congestion problem when multiple terminals concurrently transmit is not considered; in a complex scene, the existing method cannot dynamically adjust the communication parameters to adapt to the environmental changes such as multipath fading and shadowing effect, resulting in a decrease in transmission reliability; it is difficult to cope with unknown or dynamically changing interference sources by relying on a preset interference model or a fixed filtering algorithm, high-frequency communication in vehicle networking is easily affected by co-frequency interference and burst noise, but the existing patents do not fully combine machine learning or dynamic beamforming technology for interference identification and suppression; in high dynamic scenes such as unmanned aerial vehicle ad hoc networks, fixed beamforming cannot track the interference direction in real time, resulting in deterioration of signal quality; the resource allocation strategy is mostly based on static parameters, and cannot be dynamically adjusted according to real-time data transmission state, the OFDMA resource allocation of the LTE network does not consider the difference in service priority, resulting in insufficient QoS guarantee when delay-sensitive services and non-real-time services share resources, and multi-objective optimization is often simplified to single-objective optimization in the existing patents, resulting in unbalanced resource utilization; space-frequency adaptive filtering relies on complex matrix operations and frequency domain transformation, and has high requirements for hardware processing capacity, the antenna selection algorithm based on the MMSE criterion needs to calculate the array weight in real time, resulting in excessive consumption of DSP resources, and it is difficult to deploy in resource-limited devices, and the hardware integration of multi-band coordination technology is insufficient, resulting in an increase in device size and power consumption.

[0003] Therefore, it is necessary to provide a wireless communication adaptive method and system based on data transmission state. SUMMARY

[0004] The purpose of the present application is to provide a wireless communication adaptive method and system based on data transmission state, in order to solve the above-mentioned problems in the prior art, the present application realizes the following technical scheme:

[0005] In a first aspect, the present application provides a wireless communication adaptive method based on data transmission state, which specifically comprises the following steps:

[0006] Step one: obtaining multi-source data, pre-processing the multi-source data to obtain a CSI compression matrix, predicting the channel coherence time, dynamically adjusting the CSI sampling interval, and defining a load-channel coupling factor;

[0007] Step two: obtain cross-layer data based on the CSI compression matrix, fuse through the rotation matrix to obtain the fusion matrix, extract the physical layer fusion feature and the application layer fusion feature to calculate the multi-target state score;

[0008] Step three: based on the cross-layer data, establish a 5G power compensation mechanism, calculate a four-dimensional influence tensor, perform tensor decomposition and optimal action selection, decompose T into a core tensor and a factor matrix; select the optimal parameter combination through the modular product calculation;

[0009] Step four: based on cross-layer data, introduce a quantum entanglement feedback mechanism, feedback data and design entangled state correlation cross-layer indicators, adjust the quantum gate through the entangled state design, and update the model in real time combined with incremental learning.

[0010] As a further invention of the case, the method for predicting the channel coherence time is:

[0011] Obtain multi-source data for CSI dimension compression, use compressed sensing technology to reduce the calculation complexity of high-dimensional CSI, and calculate the CSI compression matrix through the following formula: The dimension is , wherein is a random measurement matrix, and , , is a wideband CSI matrix, is a sparse basis, and

[0012] Obtain the user moving speed and the carrier frequency to dynamically predict the channel variation period, predict the channel coherence time, and calculate the channel predicted coherence time through the formula: , wherein is an extended correction coefficient, and the preset value is 0.423, is the user moving speed, is the carrier frequency, is the angle expansion, is the base station beam width;

[0013] As a further invention of the case, the method for defining the load-channel coupling factor is:

[0014] Obtain the channel predicted coherence time, dynamically adjust the CSI sampling interval, if the channel predicted coherence time is less than the preset coherence time threshold, adjust the CSI sampling interval to 0.1ms, if the channel predicted coherence time is greater than or equal to the preset coherence time threshold, the CSI sampling interval remains unchanged;

[0015] ​​​Based on dynamically adjusting the CSI sampling interval, the load-channel coupling factor is defined by the formula:

[0016]

[0017] The load-channel coupling factor was calculated. ,and ,in, It is a natural constant. CPU load, Queue depth;

[0018] As a further invention of this case, the method for obtaining the fusion matrix is ​​as follows:

[0019] Analyze the TCP protocol stack and extract throughput. and round-trip delay Calculate latency jitter ,in, The maximum round-trip time is preset per unit time. This is the minimum round-trip delay per unit time. This is the average round-trip delay per unit time.

[0020] Obtain the QoS level identifier from the core network AMF module. ;

[0021] The feature dimension redundancy problem is solved by fusing through a rotation matrix, using the formula:

[0022]

[0023] The fusion matrix is ​​calculated. ,in, For physical layer fusion features, For application layer fusion features, Let be the angle of the rotation matrix. Bit error rate (BER) reflects the reliability of data transmission at the physical layer. For throughput, For round-trip time;

[0024] As a further invention of this case, the method for calculating the multi-objective state score is as follows:

[0025] By combining the fusion matrix, physical layer fusion features and application layer fusion features are extracted. A multi-objective state score is calculated to balance reliability, energy consumption, and mobility, using the formula:

[0026]

[0027] Calculate the multi-objective state score ,in, This is the level adjustment coefficient, and , For physical layer fusion features, For reference signal received power, For application layer fusion features, It is a velocity vector;

[0028] As a further invention of this case, the method for establishing the 5G power compensation mechanism is as follows:

[0029] When Wi-Fi overlapping basic service set interference is detected, 5G power compensation is triggered using the formula: Calculated 5G transmit power compensation value ,in, For the target throughput, This represents the measured throughput.

[0030] As a further invention of this case, the method for performing tensor decomposition and optimal action selection is as follows:

[0031] Constructing a four-dimensional influence tensor ,in, For real numbers, For the set of subcarrier spacings, For TTI length set, For MCS level set, For the set of transmit power;

[0032] Based on the obtained four-dimensional influence tensor, tensor decomposition and optimal action selection are performed. Tucker decomposition is used to reduce computational complexity, decomposing T into a core tensor and a factor matrix. ,in, To decompose the rank, To decompose the rank index, For subcarrier factor vectors, For slot factor vectors, For MCS factor vectors, This represents the power factor vector; the optimal parameter combination is selected through modulus product calculation, using the formula:

[0033]

[0034] The optimal parameter combination at time t is calculated. ,in, For action vectors, For TTI length set, For frequency dimension modular product operation, It is a frequency vector. For time-dimension modular product operations, In terms of time dimension, For the modular product operation of the level dimension, As a hierarchical dimension, For power dimension modular product operation, For power dimension;

[0035] As a further invention of this case, the method for designing entangled state correlation cross-layer indices is as follows:

[0036] Collect feedback data and define entangled states. Collect feedback data after actual transmission, and design a quantum entangled state correlation cross-layer index based on the feedback data, using the formula:

[0037]

[0038] Analysis yielded entangled state correlation cross-layer indices ,in, For the physical layer's bit error rate quantum state, For tensor product, For application layer latency jitter quantum states, For throughput quantum state, For round-trip time delay quantum states;

[0039] As a further invention of this case, the method for adjusting the quantum gate is as follows:

[0040] By combining entangled state design with quantum gate adjustment, error compensation can be achieved through the formula:

[0041]

[0042] The compensation quantum gate was calculated. ,in, For matrix exponential mapping, The imaginary unit, For multi-objective state scoring, Multi-objective state scoring The rate of change over time For Pauli y-matrix, For tensor product, The Pauli x matrix;

[0043] Through the formula: The final parameter compensation amount is calculated. ,in, For trace operation, Here is the density matrix. The square of the 2-norm of the multi-objective state rating gradient. For multi-objective state scoring gradients.

[0044] Secondly, the wireless communication adaptive system based on data transmission status provided by the embodiments of the present invention specifically includes the following steps:

[0045] Multi-source data sensing module: acquires multi-source data, preprocesses the multi-source data to obtain the CSI compression matrix, predicts the channel coherence time, dynamically adjusts the CSI sampling interval, and defines the load-channel coupling factor.

[0046] Multi-objective evaluation module: It acquires cross-layer data based on the CSI compression matrix, obtains the fusion matrix by fusion through rotation matrix, and extracts physical layer fusion features and application layer fusion features to calculate multi-objective state scores;

[0047] Interference Co-processing Module: Based on cross-layer data, a 5G power compensation mechanism is established, a four-dimensional influence tensor is calculated, tensor decomposition and optimal action selection are performed, and T is decomposed into a core tensor and a factor matrix; the optimal parameter combination is selected through modular product calculation.

[0048] Adaptive update module: Based on cross-layer data, a quantum entanglement feedback mechanism is introduced. By feeding back data and designing entangled states to associate cross-layer indices, the quantum gate is adjusted through entangled state design, and the model is updated in real time by combining incremental learning.

[0049] The beneficial effects of this invention are:

[0050] 1. By fusing multi-source data, the computational complexity of high-dimensional CSI is reduced. At the same time, the channel coherence time is dynamically predicted to adjust the CSI sampling interval. A load-channel coupling factor is designed to enhance the CSI weight in congestion scenarios. Finally, a dynamic channel fingerprint database is constructed to provide accurate and real-time basic parameters for state awareness. By fusing physical layer and application layer features through rotation matrix, dimensional redundancy is eliminated. A multi-objective state scoring model is constructed to quantify the comprehensive performance of the system in multiple dimensions, achieving efficient fusion of cross-layer features and coordinated balance of multiple objectives.

[0051] 2. BDQN with output action value distribution is adopted to improve decision robustness, combined with a blockchain node dynamic weight aggregation strategy based on channel coherence time; a collaborative scheme is designed; a four-dimensional influence tensor is constructed, and optimal parameters are selected to balance throughput and anti-interference capability; a quantum entanglement feedback mechanism is introduced to link the quantum states of the physical layer and the application layer through tensor product, compressing feedback latency; a quantum gate is designed to achieve error compensation and trigger incremental learning, reducing computational overhead while avoiding model drift and ensuring the system's long-term adaptive capability. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart of the steps of a wireless communication adaptive method based on data transmission status provided in Embodiment 1 of the present invention;

[0054] Figure 2 This is a schematic diagram of a wireless communication adaptive system based on data transmission status provided in Embodiment 2 of the present invention. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0056] Example 1: As Figure 1 As shown in the figure, the wireless communication adaptive method based on data transmission state provided by this embodiment of the invention specifically includes the following steps:

[0057] Step 1: Acquire multi-source data, preprocess the multi-source data to obtain the CSI compression matrix, predict the channel coherence time, dynamically adjust the CSI sampling interval, and define the load-channel coupling factor.

[0058] In a specific embodiment, multi-source data is acquired, including: spatiotemporal data, frequency domain data, and network load data;

[0059] For spatiotemporal data, real-time three-dimensional coordinates are acquired through the user equipment's built-in Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU) modules. and velocity vector , used to characterize user mobility;

[0060] For frequency domain data, the wideband channel state information (CSI) matrix is ​​extracted from the base station baseband unit using a preset sampling interval. , For the set of complex numbers, Number of transmitting antennas The number of receiving antennas covers the Sub-6GHz and millimeter-wave bands;

[0061] For network load data, CPU utilization is collected through the OMC module of the base station operation and maintenance center. Cache queue depth It reflects the real-time network congestion status;

[0062] Multi-source data is preprocessed, and CSI dimension compression is performed based on the multi-source data. Compressed sensing technology is used to reduce the computational complexity of high-dimensional CSI, as shown in the following formula: The CSI compression matrix is ​​calculated. , dimension ,in, for Random measurement matrix, and , It is a wideband CSI matrix. for Sparse base, and Processing latency is controlled within a preset latency range;

[0063] Based on the dynamic prediction of channel change periods using user movement speed and carrier frequency, the channel coherence time is predicted using the formula: The channel prediction coherence time was calculated. ,in, To expand the correction factor, the default value is 0.423. For user mobility rate, For carrier frequency, To expand the angle, To reduce the coherence time prediction error in the millimeter-wave band by coupling mobility and beam characteristics to the base station beamwidth;

[0064] It should be noted that the classic model of channel coherence time is determined by Doppler spread, which is related to user movement speed and carrier frequency. In millimeter wave scenarios, angle spread represents the degree of dispersion of the signal angle of arrival, and base station beamwidth represents the angular range of the beam. Both angle spread and base station beamwidth have an impact on the time-varying characteristics of the channel.

[0065] Based on the obtained channel prediction coherence time, the CSI sampling interval is dynamically adjusted. If the channel prediction coherence time is less than the preset coherence time threshold, the CSI sampling interval is adjusted to 0.1ms. If the channel prediction coherence time is greater than or equal to the preset coherence time threshold, the CSI sampling interval remains unchanged.

[0066] Based on dynamically adjusting the CSI sampling interval, the load-channel coupling factor is defined by the formula:

[0067]

[0068] The load-channel coupling factor was calculated. ,and ,in, It is a natural constant. CPU load, The higher the CPU load, the greater the load-channel coupling factor. The greater the queue depth, the greater the load-channel coupling factor, which enhances the weight of CSI in congestion scenarios and solves the problem of load and channel state disconnection.

[0069] Function 1: By integrating spatiotemporal and frequency multi-dimensional information to construct a dynamic channel fingerprint database, and through channel coherence time prediction and load-channel coupling modeling, it solves the problems of traditional static initialization, perception lag and low channel reliability, and provides accurate basic environmental parameters for state perception.

[0070] Step 2: Obtain cross-layer data based on the CSI compression matrix, fuse the data using a rotation matrix to obtain a fusion matrix, extract physical layer fusion features and application layer fusion features to calculate multi-objective state scores;

[0071] In a specific embodiment, cross-layer data is obtained based on the CSI compression matrix. The cross-layer data includes: physical layer data, application layer data, and cross-domain data.

[0072] Specifically, for physical layer data, the real-time bit error rate (BER) is calculated using baseband CRC check, and the reference signal received power is collected. The sampling frequency is synchronized with CSI;

[0073] For application layer data, parse the TCP protocol stack and extract throughput. and round-trip delay Calculate latency jitter ,in, The maximum round-trip time is preset per unit time. This is the minimum round-trip delay per unit time. This is the average round-trip delay per unit time.

[0074] For cross-domain data, the QoS level identifier is obtained from the core network AMF module. 1 is the highest priority and 9 is the lowest priority;

[0075] Features from physical layer data and application layer data are fused using a rotation matrix to address feature dimensionality redundancy, as shown by the formula:

[0076]

[0077] The fusion matrix is ​​calculated. ,in, For physical layer fusion features, For application layer fusion features, Let be the angle of the rotation matrix. Bit error rate (BER) reflects the reliability of data transmission at the physical layer. For throughput, For round-trip time;

[0078] Based on the obtained fusion matrix, physical layer fusion features and application layer fusion features are extracted. A multi-objective state score is calculated to balance reliability, energy consumption, and mobility, using the formula:

[0079]

[0080] Calculate the multi-objective state score ,in, This is the level adjustment coefficient, and , For physical layer fusion features, For reference signal received power, For application layer fusion features, Using velocity vectors, the system's performance in terms of reliability, energy consumption, and mobility is quantified.

[0081] Step 3: Establish a 5G power compensation mechanism based on cross-layer data, calculate the four-dimensional influence tensor, perform tensor decomposition and optimal action selection, decompose T into core tensor and factor matrix; select the optimal parameter combination through modular product calculation;

[0082] In a specific embodiment, BDQN is deployed on the base station side to output the action value distribution instead of a single value, thereby improving decision robustness.

[0083] It should be noted that this refers to a Bayesian Deep Q-Network, which is an improved variant of the Deep Q-Network (DQN) in deep reinforcement learning. It models the parameter uncertainty of the Q-Network using a Bayesian method and outputs an action value distribution rather than a single scalar value.

[0084] Each base station is a blockchain node, and the strategies of each base station are aggregated through the blockchain node. The weights are dynamically allocated by the channel coherence time.

[0085] When Wi-Fi overlapping basic service set interference is detected, 5G power compensation is triggered using the formula: Calculated 5G transmit power compensation value ,in, For the target throughput, To measure the actual throughput, the upper limit of the 5G transmit power compensation value is 3dBm to avoid interference propagation. At the same time, the anti-interference capability is improved by adjusting the 5G subcarrier spacing, thus simultaneously solving the problems of throughput loss and cross-network interference.

[0086] Constructing a four-dimensional influence tensor ,in, For real numbers, For the set of subcarrier spacings, For TTI length set, For MCS level set, For the set of transmit power;

[0087] It should be noted that TTI represents the time interval for independent decoding and transmission in a wireless link. Its length is determined by the size of the data block passed from the higher layers to the wireless link layer, which directly affects the efficiency of data scheduling, transmission delay, and resource allocation. MCS represents the modulation and coding strategy, which is a core parameter used in wireless communication systems to balance data transmission rate and transmission reliability.

[0088] Four-dimensional influence tensor elements This indicates the normalized system performance under this parameter combination;

[0089] Based on the obtained four-dimensional influence tensor, tensor decomposition and optimal action selection are performed. Tucker decomposition is used to reduce computational complexity, decomposing T into a core tensor and a factor matrix. ,in, To decompose the rank, To decompose the rank index, For subcarrier factor vectors, For slot factor vectors, For MCS factor vectors, It is a power factor vector;

[0090] The optimal parameter combination is selected through modulus product calculation, using the formula:

[0091]

[0092] The optimal parameter combination at time t is calculated. ,in, For action vectors, For TTI length set, For frequency dimension modular product operation, It is a frequency vector. For time-dimension modular product operations, In terms of time dimension, For the modular product operation of the level dimension, As a hierarchical dimension, For power dimension modular product operation, For power dimension;

[0093] Design a heterogeneous adaptation layer to optimize execution logic for FPGA / ASIC / optoelectronic fusion chips;

[0094] For millimeter-wave optoelectronic chips, the beamwidth is coupled and adjusted with the MCS level, and the clock frequency is adjusted in conjunction with the chip temperature T.

[0095] Step 4: Based on cross-layer data, introduce a quantum entanglement feedback mechanism, use feedback data and design entangled states to correlate cross-layer indicators, adjust quantum gates through entangled state design, and update the model in real time by combining incremental learning;

[0096] In a specific embodiment, feedback data is collected and entangled states are defined. Feedback data after actual transmission is collected, including: physical layer bit error rate (BER), application layer latency jitter (J), and throughput. and round-trip delay Based on feedback data, a cross-layer index for quantum entangled state correlation is designed, using the formula:

[0097]

[0098] Analysis yielded entangled state correlation cross-layer indices ,in, For the physical layer's bit error rate quantum state, For tensor product, For application layer latency jitter quantum states, For throughput quantum state, As a round-trip time-delay quantum state, the entanglement property enables instantaneous correlation between physical layer and application layer indicators, compressing feedback latency;

[0099] Error compensation is achieved by adjusting quantum gates based on entangled states, using the formula:

[0100]

[0101] The compensation quantum gate was calculated. ,in, For matrix exponential mapping, The imaginary unit, For multi-objective state scoring, Multi-objective state scoring The rate of change over time For Pauli y-matrix, For tensor product, The Pauli x matrix;

[0102] Through the formula: The final parameter compensation amount is calculated. ,in, For trace operation, Here is the density matrix. The square of the 2-norm of the multi-objective state rating gradient. For multi-objective state scoring gradients;

[0103] If the final parameter compensation exceeds the preset compensation threshold three times consecutively, the BDQN model will be triggered to perform incremental learning, only updating the output layer weights, using the latest feedback data for training, reducing the learning rate, avoiding model drift, and ensuring the system's long-term adaptive capability.

[0104] Example 2: As Figure 2 As shown in the figure, an embodiment of the present invention provides a wireless communication adaptive system based on data transmission status, which specifically includes the following steps:

[0105] Multi-source data sensing module: acquires multi-source data, preprocesses the multi-source data to obtain the CSI compression matrix, predicts the channel coherence time, dynamically adjusts the CSI sampling interval, and defines the load-channel coupling factor.

[0106] Multi-objective evaluation module: It acquires cross-layer data based on the CSI compression matrix, obtains the fusion matrix by fusion through rotation matrix, and extracts physical layer fusion features and application layer fusion features to calculate multi-objective state scores;

[0107] Interference Co-processing Module: Based on cross-layer data, a 5G power compensation mechanism is established, a four-dimensional influence tensor is calculated, tensor decomposition and optimal action selection are performed, and T is decomposed into a core tensor and a factor matrix; the optimal parameter combination is selected through modular product calculation.

[0108] Adaptive update module: Based on cross-layer data, a quantum entanglement feedback mechanism is introduced. By feeding back data and designing entangled states to associate cross-layer indices, the quantum gate is adjusted through entangled state design, and the model is updated in real time by combining incremental learning.

[0109] The above provides a detailed description of one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and should not be considered as limiting the scope of the present invention. The above formulas are all dimensionless numerical calculations, and the formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world situation. The preset parameters in the formulas are set by those skilled in the art based on actual conditions and historical experience, and can be adjusted according to actual conditions. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. All equivalent changes and improvements made in accordance with the scope of the present invention should still fall within the patent coverage of the present invention.

Claims

1. A wireless communication adaptive method based on data transmission state, characterized in that, Includes the following steps: Acquire multi-source data, preprocess the multi-source data to obtain the CSI compression matrix, predict the channel coherence time, dynamically adjust the CSI sampling interval, and define the load-channel coupling factor. Cross-layer data is obtained based on the CSI compression matrix, and a fusion matrix is ​​obtained by fusing the data through a rotation matrix. The physical layer fusion features and the application layer fusion features are extracted to calculate the multi-objective state score. A 5G power compensation mechanism is established based on cross-layer data. The four-dimensional influence tensor is calculated, and tensor decomposition and optimal action selection are performed. T is decomposed into core tensor and factor matrix. The optimal parameter combination is selected by modulus calculation. Based on cross-layer data, a quantum entanglement feedback mechanism is introduced. By feeding back data and designing entangled states to correlate cross-layer indices, the quantum gate is adjusted through entangled state design, and the model is updated in real time by combining incremental learning.

2. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for predicting the channel coherence time is as follows: Multi-source data is acquired and CSI dimension compression is performed. Compressed sensing technology is used to reduce the computational complexity of high-dimensional CSI, as shown in the following formula: The CSI compression matrix was calculated. , dimension ,in, for Random measurement matrix, and , It is a wideband CSI matrix. for Sparse base, and By obtaining user movement speed and carrier frequency, the channel change period is dynamically predicted, and the channel coherence time is predicted using the formula: The channel prediction coherence time was calculated. ,in, To expand the correction factor, the default value is 0.

423. For user mobility rate, For carrier frequency, To expand the angle, This refers to the base station beamwidth.

3. The adaptive wireless communication method based on data transmission status according to claim 1, characterized in that, The method for defining the load-channel coupling factor is as follows: The channel prediction coherence time is obtained, and the CSI sampling interval is dynamically adjusted. If the channel prediction coherence time is less than the preset coherence time threshold, the CSI sampling interval is adjusted to 0.1ms. If the channel prediction coherence time is greater than or equal to the preset coherence time threshold, the CSI sampling interval remains unchanged. Based on dynamically adjusting the CSI sampling interval, the load-channel coupling factor is defined by the formula: The load-channel coupling factor was calculated. ,and ,in, It is a natural constant. CPU load, This represents the queue depth.

4. The adaptive wireless communication method based on data transmission status according to claim 1, characterized in that, The method for obtaining the fusion matrix is ​​as follows: Analyze the TCP protocol stack and extract throughput. and round-trip delay Calculate latency jitter ,in, The maximum round-trip delay is preset per unit time. This is the minimum round-trip delay within a preset unit of time. This is the average round-trip delay per unit time. Obtain the QoS level identifier from the core network AMF module. ; The feature dimension redundancy problem is solved by fusing through a rotation matrix, using the formula: The fusion matrix is ​​calculated. ,in, For physical layer fusion features, For application layer fusion features, Let be the angle of the rotation matrix. Bit error rate (BER) reflects the reliability of data transmission at the physical layer. For throughput, For round-trip time delay.

5. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for calculating the multi-objective state score is as follows: By combining the fusion matrix, physical layer fusion features and application layer fusion features are extracted. A multi-objective state score is calculated to balance reliability, energy consumption, and mobility, using the formula: Calculate the multi-objective state score ,in, This is the level adjustment coefficient, and , For physical layer fusion features, For reference signal received power, For application layer fusion features, This is the velocity vector.

6. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for establishing the 5G power compensation mechanism is as follows: When Wi-Fi overlapping basic service set interference is detected, 5G power compensation is triggered using the formula: Calculated 5G transmit power compensation value ,in, For the target throughput, This represents the measured throughput.

7. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for tensor decomposition and optimal action selection is as follows: Constructing a four-dimensional influence tensor ,in, For real numbers, For the set of subcarrier spacings, For TTI length set, For MCS level set, For the set of transmit power; Based on the obtained four-dimensional influence tensor, tensor decomposition and optimal action selection are performed. Tucker decomposition is used to reduce computational complexity, decomposing T into a core tensor and a factor matrix. ,in, To decompose the rank, To decompose the rank index, For subcarrier factor vectors, For slot factor vectors, For MCS factor vectors, This represents the power factor vector; the optimal parameter combination is selected through modulus product calculation, using the formula: The optimal parameter combination at time t is calculated. ,in, For action vectors, For TTI length set, For frequency dimension modular product operation, It is a frequency vector. For time-dimension modular product operations, In terms of time dimension, For the modular product operation of the level dimension, As a hierarchical dimension, For power dimension modular product operation, For the power dimension.

8. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for designing cross-layer indices related to entangled states is as follows: Collect feedback data and define entangled states. Collect feedback data after actual transmission, and design a quantum entangled state correlation cross-layer index based on the feedback data, using the formula: Analysis yielded entangled state correlation cross-layer indices ,in, For the physical layer's bit error rate quantum state, For tensor product, For application layer latency jitter quantum states, For throughput quantum state, It is a round-trip time delay quantum state.

9. The adaptive wireless communication method based on data transmission state according to claim 1, characterized in that, The method for adjusting the quantum gate is as follows: By combining entangled state design with quantum gate adjustment, error compensation can be achieved through the formula: The compensation quantum gate was calculated. ,in, For matrix exponential mapping, The imaginary unit, For multi-objective state scoring, Multi-objective state scoring The rate of change over time For Pauli y-matrix, For tensor product, The Pauli x matrix; Through the formula: The final parameter compensation amount is calculated. ,in, For trace operation, Here is the density matrix. The square of the 2-norm of the multi-objective state rating gradient. For multi-objective state scoring gradients.

10. A wireless communication adaptive system based on data transmission state, the system being used to execute the adaptive method according to any one of claims 1-9, characterized in that, include: Multi-source data sensing module: acquires multi-source data, preprocesses the multi-source data to obtain the CSI compression matrix, predicts the channel coherence time, dynamically adjusts the CSI sampling interval, and defines the load-channel coupling factor. Multi-objective evaluation module: It acquires cross-layer data based on the CSI compression matrix, obtains the fusion matrix by fusion through rotation matrix, and extracts physical layer fusion features and application layer fusion features to calculate multi-objective state scores; Interference Co-processing Module: Based on cross-layer data, a 5G power compensation mechanism is established, a four-dimensional influence tensor is calculated, tensor decomposition and optimal action selection are performed, and T is decomposed into a core tensor and a factor matrix; the optimal parameter combination is selected through modular product calculation. Adaptive update module: Based on cross-layer data, a quantum entanglement feedback mechanism is introduced. By feeding back data and designing entangled states to associate cross-layer indices, the quantum gate is adjusted through entangled state design, and the model is updated in real time by combining incremental learning.

Images