Method, device, equipment and medium for dynamic optimization of aircraft network service quality

Abstract

The present invention relates to the field of communication technology and provides a method, apparatus, device and medium for dynamically optimizing aircraft network service quality. The method, apparatus, equipment and medium can construct a network service quality quantification model based on indicator fusion according to the weight coefficient of the transport layer network indicator. Since the transport layer network indicator analyzes each data packet, the analysis granularity is finer, the real-time performance is stronger, and the impact of the application is smaller, so that a relatively comprehensive network status can be reflected. A dual-critic network is constructed based on the MATD3 algorithm and the network service quality quantification model, and the target network service quality quantification value is determined in combination with the transport layer network indicator value and the motion parameter to adjust the network resource scheduling strategy of the network to which the target aircraft belongs. The dynamic optimization of the network service quality is achieved through real-time monitoring of the transport layer indicator and the aircraft motion status and intelligent resource scheduling.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device, equipment and medium for dynamically optimizing aircraft network service quality. Background Art

[0002] In the low-altitude economy, drones and other aircraft usually use 5G (5th Generation Mobile Communication Technology) and 5G-A (5G-Advanced) communication technologies to transmit data with ground stations. The data that needs to be transmitted includes control signaling, audio and video data, etc.

[0003] However, due to various factors such as weather, 5G or 5G-A coverage, and 5G or 5G-A signal strength, the quality of the communication channel between the drone and the ground station is unstable. It is necessary to evaluate the QoS (Quality of Service) of 5G or 5G-A communication in real time and dynamically adjust the bandwidth allocated to different business data to ensure the transmission of key data such as control signaling.

[0004] In response to the above problems, existing technologies for QoS assurance have the following main drawbacks:

[0005] 1. Traditional QoS solutions are based solely on application-layer metrics (such as the number of video freezes) and cannot reflect real-time changes in transport-layer link quality.

[0006] 2. Using a fixed threshold to determine network status fails to consider the impact of the drone's dynamic flight characteristics on channel quality.

[0007] 3. The bandwidth adjustment method does not differentiate service priorities, which may cause the transmission of critical control instructions to be blocked;

[0008] 4. Traditional solutions calculate information such as latency, jitter, and packet loss rate at the application layer, but they also have the following drawbacks:

[0009] 1) The application layer is mostly built on some reliable transport protocol, so it cannot directly see underlying network issues such as packet loss and retransmission. Even if the network is unstable, the reliable protocol will automatically retransmit and recover, and the application layer can only see the recovered data stream;

[0010] 2) When calculating latency statistics at the application layer, timestamps are typically inserted when a request or reply is generated. This calculated latency includes not only the transmission time on the network link, but also the time the application spends generating, processing, and sending the request. This makes it difficult to clearly determine whether performance issues arise at the network layer (such as routing and link latency) or the application layer (such as request processing time), hindering the efficiency and accuracy of troubleshooting.

[0011] Therefore, how to reasonably optimize the network service quality of aircraft has become an urgent problem to be solved. Summary of the Invention

[0012] In view of the above, it is necessary to provide a method, device, equipment and medium for dynamically optimizing the quality of aircraft network service, aiming to solve the problem of being unable to ensure the quality of aircraft network service.

[0013] A method for dynamically optimizing aircraft network service quality, the method comprising:

[0014] In response to a dynamic optimization instruction for the network service quality of the target aircraft, a network service quality quantification model based on indicator fusion is constructed according to weight coefficients of transport layer network indicators;

[0015] A dual critic network is constructed based on the MATD3 algorithm and the network service quality quantification model; wherein the dual critic network includes a real-time critic network and a delayed critic network;

[0016] Using a probe deployed on the target aircraft side to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time;

[0017] Inputting the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network;

[0018] In the real-time critic network, the adjusted weight coefficient and the transport layer network indicator value are input into the network service quality quantification model to obtain a real-time network service quality quantification value;

[0019] After a preset delay, the real-time network service quality quantization value is synchronized to the delay critic network to obtain the delayed network service quality quantization value;

[0020] At any time during the real-time execution of the network service quality dynamic optimization instruction, obtaining the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network;

[0021] Obtaining a smaller value between the current real-time network service quality quantization value and the current delayed network service quality quantization value as a target network service quality quantization value;

[0022] The network resource scheduling strategy of the network to which the target aircraft belongs is adjusted according to the target network service quality quantization value.

[0023] According to a preferred embodiment of the present invention, constructing a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators includes:

[0024] Obtaining the delay, jitter, and packet loss rate of the transport layer network indicators;

[0025] Based on the delay, the jitter, and the packet loss rate, the network service quality quantification model is constructed using the following formula:

[0026] Q_score=α·Delay + β·Jitter + γ·Loss;

[0027] Among them, Q_score represents the quantitative value of network service quality, Delay represents the value of the delay, Jitter represents the value of the jitter, Loss represents the value of the packet loss rate, α represents the first weight coefficient corresponding to the delay, Jitter represents the second weight coefficient corresponding to the jitter, and γ represents the third weight coefficient corresponding to the packet loss rate.

[0028] According to a preferred embodiment of the present invention, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network includes:

[0029] Obtaining the real-time speed of the target aircraft from the motion parameters;

[0030] When the real-time speed is greater than the speed threshold, the adjusted first weight coefficient is calculated using the following formula:

[0031] ;

[0032] in, represents the adjusted first weight coefficient, the initial value of the first weight coefficient, represents the speed coefficient, represents the real-time speed, Indicates the maximum speed.

[0033] According to a preferred embodiment of the present invention, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes:

[0034] Obtaining the real-time longitudinal acceleration of the target aircraft from the motion parameters;

[0035] When the real-time longitudinal acceleration is greater than the longitudinal acceleration threshold, calculating a compensation value of the second weight coefficient;

[0036] adding the compensation value to the second weight coefficient;

[0037] The compensation value of the second weight coefficient is calculated using the following formula:

[0038] ;

[0039] in, represents the compensation value of the second weight coefficient, represents the real-time longitudinal acceleration, represents the longitudinal acceleration safety threshold, represents the initial value of the second weight coefficient, represents the real-time pitch angle of the target aircraft, Indicates the maximum pitch angle.

[0040] According to a preferred embodiment of the present invention, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes:

[0041] Obtaining the target altitude and real-time altitude of the target aircraft;

[0042] Calculating the difference between the target altitude and the real-time altitude to obtain the altitude difference of the target aircraft;

[0043] Obtaining a height tolerance of the target aircraft, and obtaining a real-time roll angle of the target aircraft from the motion parameters;

[0044] According to the height tolerance and the real-time roll angle, the adjusted third weight coefficient is calculated using the following formula:

[0045] ;

[0046] in, ;

[0047] in, represents the adjusted third weight coefficient, represents the initial value of the third weight coefficient, represents the real-time roll angle, represents the height difference, Indicates the height tolerance.

[0048] According to a preferred embodiment of the present invention, adjusting the network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantified value includes:

[0049] When the target network service quality quantization value is greater than or equal to a first threshold and less than a second threshold, obtaining a non-critical video stream corresponding to the network to which the target aircraft belongs, limiting the bandwidth of the non-critical video stream to a preset proportion of the original bandwidth, and initiating an I-frame priority transmission mechanism;

[0050] When the target network service quality quantization value is greater than or equal to the second threshold and less than a third threshold, initiating a coding upgrade mechanism for converting the first digital video compression format to the second digital video compression format in the network to which the target aircraft belongs, downgrading the video bit rate transmitted in the network to which the target aircraft belongs to to a configured bit rate, and disabling video stream metadata backhaul in the network to which the target aircraft belongs;

[0051] When the target network service quality quantization value is greater than or equal to the third threshold, the resolution of the image data transmitted in the network to which the target aircraft belongs is downgraded, a data packet truncation mechanism is enabled in the network to which the target aircraft belongs, and the transmission of all non-real-time data is suspended.

[0052] According to a preferred embodiment of the present invention, after adjusting the network resource scheduling policy of the network to which the target aircraft belongs according to the target network service quality quantified value, the method further includes:

[0053] Re-obtaining the network service quality quantization value output by the dual critic network as the network service quality update value;

[0054] Comparing the network service quality update value with the target network service quality quantized value;

[0055] When the network service quality update value is less than the target network service quality quantization value, determining that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs has an optimization effect; or

[0056] When the network service quality update value is greater than or equal to the target network service quality quantization value, it is determined that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs does not have an optimization effect, and an optimization prompt message is sent to the designated terminal device.

[0057] An aircraft network service quality dynamic optimization device, the aircraft network service quality dynamic optimization device comprising:

[0058] A construction unit, configured to construct a network service quality quantification model based on indicator fusion according to weight coefficients of transport layer network indicators in response to a dynamic optimization instruction for the network service quality of the target aircraft;

[0059] The construction unit is further configured to construct a dual critic network based on the MATD3 algorithm and the network service quality quantification model; wherein the dual critic network includes a real-time critic network and a delayed critic network;

[0060] A collection unit, configured to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time using a probe deployed on the target aircraft side;

[0061] an adjustment unit, configured to input the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjust the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network;

[0062] An input unit is configured to input the adjusted weight coefficient and the transport layer network indicator value into the network service quality quantification model in the real-time critic network to obtain a real-time network service quality quantification value;

[0063] A synchronization unit, configured to synchronize the real-time network service quality quantization value to the delay critic network after a preset delay, to obtain the delayed network service quality quantization value;

[0064] An acquisition unit, configured to acquire, at any time during the real-time execution of the network service quality dynamic optimization instruction, the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network;

[0065] The acquisition unit is further configured to acquire the smaller value of the current real-time network service quality quantization value and the current delayed network service quality quantization value as the target network service quality quantization value;

[0066] The adjustment unit is further configured to adjust a network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantization value.

[0067] A computer device, comprising:

[0068] a memory storing at least one instruction; and

[0069] The processor executes the instructions stored in the memory to implement the method for dynamically optimizing the aircraft network service quality.

[0070] A computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the method for dynamically optimizing aircraft network service quality.

[0071] It can be seen from the above technical solutions that the present invention can construct a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators. Since the transport layer network indicators analyze each data packet, the analysis granularity is finer, the real-time performance is stronger, and the impact of the application is smaller, which can reflect a more comprehensive network status. A dual-critic network is constructed based on the MATD3 algorithm and the network service quality quantification model, and the target network service quality quantification value is determined in combination with the transport layer network indicator value and the motion parameters to adjust the network resource scheduling strategy of the network to which the target aircraft belongs. Through real-time monitoring of the transport layer indicators and the aircraft motion status and intelligent resource scheduling, dynamic optimization of the network service quality is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a flow chart of a preferred embodiment of the method for dynamically optimizing aircraft network service quality of the present invention;

[0073] Figure 2 This is a functional module diagram of a preferred embodiment of the aircraft network service quality dynamic optimization device of the present invention;

[0074] Figure 3 It is a structural diagram of a computer device of a preferred embodiment of the present invention for implementing a method for dynamically optimizing aircraft network service quality. DETAILED DESCRIPTION

[0075] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0076] like Figure 1 FIG. 1 is a flow chart of a preferred embodiment of the method for dynamically optimizing the aircraft network service quality of the present invention. The order of the steps in the flow chart can be changed according to different requirements, and some steps can be omitted.

[0077] The dynamic optimization method for aircraft network service quality is applied to one or more computer devices, which are devices that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Their hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0078] The computer device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0079] The computer device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0080] The server can be an independent server or 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, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0081] Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0082] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0083] The network where the computer device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0084] S10 , in response to a dynamic optimization instruction for the network service quality of the target aircraft, constructing a network service quality quantification model based on indicator fusion according to weight coefficients of transport layer network indicators.

[0085] In this embodiment, the target aircraft may be an aircraft in a low-altitude economic scenario, such as a drone.

[0086] In this embodiment, the network service quality dynamic optimization instruction can be automatically triggered when it is detected that the target aircraft is started, so as to achieve full monitoring of the flight process of the target aircraft.

[0087] In this embodiment, constructing a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators includes:

[0088] Obtaining the delay, jitter, and packet loss rate of the transport layer network indicators;

[0089] Based on the delay, the jitter, and the packet loss rate, the network service quality quantification model is constructed using the following formula:

[0090] Q_score=α·Delay + β·Jitter + γ·Loss;

[0091] Among them, Q_score represents the quantitative value of network service quality, Delay represents the value of the delay, Jitter represents the value of the jitter, Loss represents the value of the packet loss rate, α represents the first weight coefficient corresponding to the delay, Jitter represents the second weight coefficient corresponding to the jitter, and γ represents the third weight coefficient corresponding to the packet loss rate.

[0092] Among them, Delay, Jitter, and Loss can be normalized, and the value range of Q_score can be [0,1].

[0093] In the above embodiment, a mathematical model for comprehensively scoring network quality is generated by combining latency, jitter, and packet loss rate through a weighted algorithm. Because transport layer metrics analyze each underlying packet, they can capture and analyze network latency, retransmissions, packet loss, congestion, jitter, and other conditions. This allows for a more granular and real-time analysis, reflecting a more comprehensive picture of network conditions. Furthermore, latency statistics at the transport layer are less affected by applications and result in more accurate statistics. Using transport layer metrics not only enables accurate assessment of network quality but also provides an effective basis for subsequent adjustments to network resource scheduling strategies.

[0094] S11, constructing a dual critic network based on the MATD3 (Multi-Agent Twin Delayed DDPG) algorithm and the network service quality quantification model; wherein the dual critic network includes a real-time critic network and a delayed critic network.

[0095] In this embodiment, by integrating the network service quality quantification model with the reinforcement learning model, the stability and efficiency of learning can be improved, and the evaluation capability of different strategies can be enhanced.

[0096] When building and training the dual critic network, the following strategies can be used to process training samples:

[0097] 1) Prioritized experience replay: samples whose Q_score drops by more than 20% are given a sampling weight of 3 times;

[0098] 2) State cluster storage: High-speed movement state (flight speed ≥ 20m / s) samples are stored separately to improve the generalization ability of the policy network in extreme or critical scenarios.

[0099] In drone training datasets, the proportion of samples in high-speed states (such as flight speed ≥ 20m / s) is usually less than 10%, resulting in insufficient decision-making capabilities of the policy network for high-speed scenarios. In addition, when moving at high speeds, problems such as sudden changes in channel quality and control command delays are significantly amplified, requiring targeted and intensive training.

[0100] Therefore, by processing samples with a Q_score drop of more than 20% and samples in high-speed movement state, more sufficient samples can be collected, thereby improving the performance of the constructed dual-critic network.

[0101] S12, using a probe deployed on the target aircraft side to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time.

[0102] In this embodiment, the transport layer network indicator value may include values ​​of delay, jitter, and packet loss rate.

[0103] In this embodiment, the motion parameters may include, but are not limited to: speed, acceleration, pitch angle, roll angle, etc.

[0104] S13: Input the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjust the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network.

[0105] In this embodiment, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network includes:

[0106] Obtaining the real-time speed of the target aircraft from the motion parameters;

[0107] When the real-time speed is greater than the speed threshold, the adjusted first weight coefficient is calculated using the following formula:

[0108] ;

[0109] in, represents the adjusted first weight coefficient, the initial value of the first weight coefficient, represents the speed coefficient, represents the real-time speed, Indicates the maximum speed.

[0110] The speed threshold can be configured according to experiments, such as 15 m / s.

[0111] In this embodiment, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes:

[0112] Obtaining the real-time longitudinal acceleration of the target aircraft from the motion parameters;

[0113] When the real-time longitudinal acceleration is greater than the longitudinal acceleration threshold, calculating a compensation value of the second weight coefficient;

[0114] adding the compensation value to the second weight coefficient;

[0115] The compensation value of the second weight coefficient is calculated using the following formula:

[0116] ;

[0117] in, represents the compensation value of the second weight coefficient, represents the real-time longitudinal acceleration, represents the longitudinal acceleration safety threshold, represents the initial value of the second weight coefficient, represents the real-time pitch angle of the target aircraft, Indicates the maximum pitch angle.

[0118] The longitudinal acceleration threshold may also be configured according to experiments, such as 4 m / s².

[0119] The configuration of the longitudinal acceleration safety threshold can prevent data packets from being out of order due to violent maneuvers. For example, the longitudinal acceleration safety threshold can be configured to 8 m / s².

[0120] In this embodiment, dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes:

[0121] Obtaining the target altitude and real-time altitude of the target aircraft;

[0122] Calculating the difference between the target altitude and the real-time altitude to obtain the altitude difference of the target aircraft;

[0123] Obtaining a height tolerance of the target aircraft, and obtaining a real-time roll angle of the target aircraft from the motion parameters;

[0124] According to the height tolerance and the real-time roll angle, the adjusted third weight coefficient is calculated using the following formula:

[0125] ;

[0126] in, ;

[0127] in, represents the adjusted third weight coefficient, represents the initial value of the third weight coefficient, represents the real-time roll angle, represents the height difference, Indicates the height tolerance.

[0128] The height tolerance may be configured as 2m.

[0129] The target height may be an ideal height for hovering.

[0130] By adjusting the third weight coefficient, the priority of packet loss weight can be reduced during tilted flight.

[0131] The sum of the first weight coefficient, the second weight coefficient and the third weight coefficient is 1.

[0132] The adjustment ranges of the first weight coefficient, the second weight coefficient, and the third weight coefficient are all limited to certain limits, thereby effectively avoiding sudden changes and drastic fluctuations in the weight coefficients. For example, the adjustment range of the first weight coefficient can be limited to [-0.12, +0.12].

[0133] In this case, a motion smoothing filter may be used to smooth each weight coefficient during the entire flight process of the target aircraft, so as to further avoid sudden changes in the weight coefficient.

[0134] In the above embodiment, it is possible to respond quickly based on parameters such as flight speed, acceleration, and attitude angle, prioritize low latency during high-speed maneuvers (such as increasing the first weight coefficient), optimize packet loss rate during stable cruising (such as increasing the third weight coefficient), and suppress network jitter during violent maneuvers (such as dynamically compensating for the second weight coefficient).

[0135] Through the above embodiments, the weight coefficients of various transmission layer indicators can be adjusted in real time according to the motion parameters of the aircraft. The spatiotemporal correlation analysis method between the transmission layer indicators and the UAV motion state has established a dynamic mapping relationship between the UAV kinematic parameters and the transmission layer indicators for the first time.

[0136] S14, in the real-time Critic network, inputting the adjusted weight coefficient and the transport layer network indicator value into the network service quality quantification model to obtain a real-time network service quality quantification value.

[0137] Through the above embodiment, a real-time quantified value of the network service quality can be calculated according to the real-time transport layer index and the weight coefficient adjusted according to the aircraft motion parameter.

[0138] S15, after a preset delay, synchronizing the real-time network service quality quantization value to the delay critic network to obtain the delayed network service quality quantization value.

[0139] The preset delay can be configured according to the actual application scenario.

[0140] For example, at the current time t, if the delay is T, the network service quality quantization value output by the real-time critic network at time (tT) can be synchronized to the delay critic network and used as the network service quality quantization value output by the delay critic network at the current time t.

[0141] S16, at any time during the real-time execution of the network service quality dynamic optimization instruction, obtaining the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network.

[0142] For example, when the arbitrary moment is t, the current real-time network service quality quantization value Q output by the real-time critic network is obtained, and the current delayed network service quality quantization value Q' output by the delayed critic network is obtained (Q' is the network service quality quantization value output by the real-time critic network at the moment (tT)).

[0143] S17: Acquire the smaller value of the current real-time network service quality quantization value and the current delayed network service quality quantization value as the target network service quality quantization value.

[0144] For example, when Q is less than Q', Q is determined as the target network service quality quantization value.

[0145] Through the above embodiments, the overestimation problem can be effectively suppressed.

[0146] S18: Adjust the network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantization value.

[0147] In this embodiment, adjusting the network resource scheduling policy of the network to which the target aircraft belongs according to the target network service quality quantified value includes:

[0148] When the target network service quality quantization value is greater than or equal to a first threshold and less than a second threshold, obtaining a non-critical video stream corresponding to the network to which the target aircraft belongs, limiting the bandwidth of the non-critical video stream to a preset proportion of the original bandwidth, and initiating an I-frame priority transmission mechanism;

[0149] When the target network service quality quantization value is greater than or equal to the second threshold and less than a third threshold, initiating a coding upgrade mechanism for converting the first digital video compression format to the second digital video compression format in the network to which the target aircraft belongs, downgrading the video bit rate transmitted in the network to which the target aircraft belongs to to a configured bit rate, and disabling video stream metadata backhaul in the network to which the target aircraft belongs;

[0150] When the target network service quality quantization value is greater than or equal to the third threshold, the resolution of the image data transmitted in the network to which the target aircraft belongs is downgraded, a data packet truncation mechanism is enabled in the network to which the target aircraft belongs, and the transmission of all non-real-time data is suspended.

[0151] The non-critical video frames may be configured according to business agreements.

[0152] The first threshold, the second threshold, and the third threshold can be configured based on a large number of experiments in actual scenarios.

[0153] The preset ratio and the configured bit rate may also be configured based on a large number of experiments in actual scenarios.

[0154] For example, when the target network quality of service quantization value is greater than or equal to the first threshold and less than the second threshold, the first-level resource scheduling strategy is adopted. For example, the bandwidth of non-critical video streams is limited to 70% of the original value, and the I-frame priority transmission mechanism is enabled. This strategy only affects the enhanced data of the media stream.

[0155] For another example, when the target network quality of service quantization value is greater than or equal to the second threshold and less than the third threshold, H.264 to H.265 transcoding is initiated (H.265 has higher compression efficiency than H.264, saving more bandwidth for video stream transmission of equivalent image quality. However, the H.265 codec complexity is 2-3 times that of H.264, consuming more computing resources. Therefore, this adjustment is a dynamic process. When bandwidth resources are sufficient, H.264 is used to encode the video stream to save computing resources. However, when bandwidth resources are limited, the encoding algorithm is adjusted to H.265, trading computing resources for lower bandwidth consumption). The video bitrate is downgraded to 64 kbps, and video stream metadata feedback is disabled. This policy affects the basic quality of the media stream.

[0156] For another example, when the target network quality of service quantization value is greater than or equal to the third threshold, the resolution is adaptively downgraded (e.g., from 1080p to 720p, or from 720p to 480p), packet truncation is enabled (e.g., retaining the first 80% of video macroblocks), and all non-real-time data transmission is suspended. This policy affects all non-control services.

[0157] Through the above embodiments, the network resources of the network to which the aircraft belongs can be hierarchically scheduled according to the output network service quality quantization value, and dynamic optimization of service quality is achieved under the premise of ensuring priority transmission of flight control instructions. This solves the QoS (Quality of Service) fluctuation problem caused by the dynamic environment in the communication between network base stations such as 5G base stations and aircraft such as drones in low-altitude economic scenarios, effectively reduces the communication interruption rate, reduces the standard deviation of control instruction transmission delay, and can also ensure basic image quality.

[0158] In this embodiment, after adjusting the network resource scheduling policy of the network to which the target aircraft belongs according to the target network service quality quantified value, the method further includes:

[0159] Re-obtaining the network service quality quantization value output by the dual critic network as the network service quality update value;

[0160] Comparing the network service quality update value with the target network service quality quantized value;

[0161] When the network service quality update value is less than the target network service quality quantization value, determining that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs has an optimization effect; or

[0162] When the network service quality update value is greater than or equal to the target network service quality quantization value, it is determined that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs does not have an optimization effect, and an optimization prompt message is sent to the designated terminal device.

[0163] In the above embodiment, after the network resource scheduling strategy is adjusted according to the output network service quality quantization value, the available bandwidth, resolution, etc. of the audio and video streams in the network may also change accordingly, thereby also changing the index values ​​of transmission layer indicators such as delay, jitter, and packet loss rate. In other words, if the network service quality quantization value decreases accordingly, then this adjustment will have an optimization effect. Otherwise, it can prompt relevant personnel to promptly adjust the dynamic optimization plan of the aircraft network service quality to achieve better optimization effects.

[0164] This embodiment uses a dynamic weight coefficient adjustment mechanism based on reinforcement learning to improve the communication service quality in high-speed drone movement scenarios. Its core lies in dynamically adjusting the weight of transmission layer indicators (such as latency, jitter, and packet loss rate) in the network service quality quantification model through real-time perception of the drone's motion state and environmental parameters, and then obtaining QoS evaluation results. This is used as the basis for dynamically adjusting the transmission parameters of services such as audio and video that occupy large bandwidth resources, thereby ensuring the priority transmission of key instructions such as control signaling.

[0165] It can be seen from the above technical solutions that the present invention can construct a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators. Since the transport layer network indicators analyze each data packet, the analysis granularity is finer, the real-time performance is stronger, and the impact of the application is smaller, which can reflect a more comprehensive network status. A dual-critic network is constructed based on the MATD3 algorithm and the network service quality quantification model, and the target network service quality quantification value is determined in combination with the transport layer network indicator value and the motion parameters to adjust the network resource scheduling strategy of the network to which the target aircraft belongs. Through real-time monitoring of the transport layer indicators and the aircraft motion status and intelligent resource scheduling, dynamic optimization of the network service quality is achieved.

[0166] like Figure 2 The figure shows a functional block diagram of a preferred embodiment of the aircraft network service quality dynamic optimization device of the present invention. The aircraft network service quality dynamic optimization device 11 includes a construction unit 110, a collection unit 111, an adjustment unit 112, an input unit 113, a synchronization unit 114, and an acquisition unit 115. As used herein, a module / unit refers to a series of computer program segments that can be executed by a processor and perform fixed functions, and are stored in a memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0167] The construction unit 110 is configured to construct a network service quality quantification model based on indicator fusion according to weight coefficients of transport layer network indicators in response to a dynamic optimization instruction for the network service quality of the target aircraft;

[0168] The construction unit 110 is further configured to construct a dual-critic network based on the MATD3 algorithm and the network service quality quantification model; wherein the dual-critic network includes a real-time critic network and a delayed critic network;

[0169] The collecting unit 111 is used to collect transport layer network index values ​​and motion parameters of the target aircraft in real time using a probe deployed on the target aircraft side;

[0170] The adjustment unit 112 is configured to input the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjust the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network;

[0171] The input unit 113 is configured to input the adjusted weight coefficient and the transport layer network indicator value into the network service quality quantification model in the real-time critic network to obtain a real-time network service quality quantification value;

[0172] The synchronization unit 114 is configured to synchronize the real-time network service quality quantization value to the delay critic network after a preset delay to obtain the delayed network service quality quantization value;

[0173] The acquisition unit 115 is configured to acquire, at any time during the real-time execution of the network service quality dynamic optimization instruction, the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network;

[0174] The acquisition unit 115 is further configured to acquire the smaller value of the current real-time network service quality quantization value and the current delayed network service quality quantization value as the target network service quality quantization value;

[0175] The adjusting unit 112 is further configured to adjust a network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantization value.

[0176] It can be seen from the above technical solutions that the present invention can construct a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators. Since the transport layer network indicators analyze each data packet, the analysis granularity is finer, the real-time performance is stronger, and the impact of the application is smaller, which can reflect a more comprehensive network status. A dual-critic network is constructed based on the MATD3 algorithm and the network service quality quantification model, and the target network service quality quantification value is determined in combination with the transport layer network indicator value and the motion parameters to adjust the network resource scheduling strategy of the network to which the target aircraft belongs. Through real-time monitoring of the transport layer indicators and the aircraft motion status and intelligent resource scheduling, dynamic optimization of the network service quality is achieved.

[0177] like Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device according to a preferred embodiment of the present invention for implementing a method for dynamically optimizing aircraft network service quality.

[0178] The computer device 1 may include a memory 12, a processor 13 and a bus (the arrow in the figure represents the bus), and may also include a computer program stored in the memory 12 and executable on the processor 13, such as an aircraft network service quality dynamic optimization program.

[0179] Those skilled in the art will understand that the schematic diagram is merely an example of the computer device 1 and does not constitute a limitation on the computer device 1. The computer device 1 may have either a bus structure or a star structure. The computer device 1 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components. For example, the computer device 1 may also include input and output devices, network access devices, etc.

[0180] It should be noted that the computer device 1 is only an example. Other existing or future electronic products that are suitable for the present invention should also be included in the scope of protection of the present invention and included here by reference.

[0181] The memory 12 includes at least one type of readable storage medium, including flash memory, a removable hard drive, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic storage device, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 12 may be an internal storage unit of the computer device 1, such as a removable hard drive of the computer device 1. In other embodiments, the memory 12 may be an external storage device of the computer device 1, such as a plug-in removable hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, and the like. Furthermore, the memory 12 may include both an internal storage unit and an external storage device of the computer device 1. The memory 12 can be used not only to store application software installed in the computer device 1 and various data, such as the code for the aircraft network quality of service dynamic optimization program, but also to temporarily store data that has been output or is about to be output.

[0182] In some embodiments, processor 13 may be comprised of an integrated circuit, such as a single packaged integrated circuit or multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. Processor 13 is the control core (control unit) of computer device 1, connecting the various components of computer device 1 via various interfaces and circuits. It executes programs or modules stored in memory 12 (e.g., a program for dynamically optimizing aircraft network quality of service) and accesses data stored in memory 12 to perform various functions and process data.

[0183] The processor 13 executes the operating system of the computer device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned embodiments of the method for dynamically optimizing the quality of service of an aircraft network, for example Figure 1 Steps shown.

[0184] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, which describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a construction unit 110, a collection unit 111, an adjustment unit 112, an input unit 113, a synchronization unit 114, and an acquisition unit 115.

[0185] The integrated unit implemented as a software functional module can be stored in a computer-readable storage medium. The software functional module stored in the storage medium includes instructions for causing a computer device (which can be a personal computer, computer equipment, or network device, etc.) or a processor to execute portions of the method for dynamically optimizing aircraft network quality of service (QoS) as described in various embodiments of the present invention.

[0186] If the modules / units integrated in the computer device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-mentioned method embodiments by instructing relevant hardware devices through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments.

[0187] The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0188] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0189] Blockchain, as used in this article, refers to a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks linked together using cryptographic methods. Each block contains information about a batch of online transactions, used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product and service layer, and the application service layer.

[0190] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The figure shows that only one straight line is used, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 12 and at least one processor 13.

[0191] Although not shown, the computer device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 13 via a power management device, thereby enabling functions such as charge management, discharge management, and power consumption management through the power management device. The power supply may also include one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components. The computer device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be further described here.

[0192] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the computer device 1 and other computer devices.

[0193] Optionally, the computer device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or display unit, and is used to display information processed by the computer device 1 and to display a visual user interface.

[0194] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0195] It will be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0196] Combine Figure 1 The memory 12 in the computer device 1 stores a plurality of instructions to implement a method for dynamically optimizing aircraft network service quality, and the processor 13 can execute the plurality of instructions to implement:

[0197] In response to a dynamic optimization instruction for the network service quality of the target aircraft, a network service quality quantification model based on indicator fusion is constructed according to weight coefficients of transport layer network indicators;

[0198] A dual critic network is constructed based on the MATD3 algorithm and the network service quality quantification model; wherein the dual critic network includes a real-time critic network and a delayed critic network;

[0199] Using a probe deployed on the target aircraft side to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time;

[0200] Inputting the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network;

[0201] In the real-time critic network, the adjusted weight coefficient and the transport layer network indicator value are input into the network service quality quantification model to obtain a real-time network service quality quantification value;

[0202] After a preset delay, the real-time network service quality quantization value is synchronized to the delay critic network to obtain the delayed network service quality quantization value;

[0203] At any time during the real-time execution of the network service quality dynamic optimization instruction, obtaining the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network;

[0204] Obtaining a smaller value between the current real-time network service quality quantization value and the current delayed network service quality quantization value as a target network service quality quantization value;

[0205] The network resource scheduling strategy of the network to which the target aircraft belongs is adjusted according to the target network service quality quantization value.

[0206] Specifically, the specific implementation method of the processor 13 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0207] It should be noted that the data involved in this case were all obtained legally. The software tools or components not produced by our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0208] In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementation may employ other division methods.

[0209] The present invention can be used in a wide variety of 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, and the like. The present invention 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 invention can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0210] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0211] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0212] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0213] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0214] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the present invention may also be implemented by a single unit or device through software or hardware. Terms such as first and second are used to indicate names and do not imply any particular order.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for dynamically optimizing aircraft network service quality, characterized in that: The method for dynamically optimizing aircraft network service quality includes: In response to a dynamic optimization instruction for the network service quality of the target aircraft, a network service quality quantification model based on indicator fusion is constructed according to weight coefficients of transport layer network indicators; A dual critic network is constructed based on the MATD3 algorithm and the network service quality quantification model; wherein the dual critic network includes a real-time critic network and a delayed critic network; wherein, when constructing the dual critic network, a priority experience replay strategy and a state clustering storage strategy are adopted to process training samples; the priority experience replay strategy is used to assign a sampling weight of 3 times to training samples whose network service quality quantification value decreases by more than 20%, and the state clustering storage strategy is used to separately store training samples whose flight speed is greater than or equal to 20m / s; Using a probe deployed on the target aircraft side to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time; Inputting the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network; In the real-time critic network, the adjusted weight coefficient and the transport layer network indicator value are input into the network service quality quantification model to obtain a real-time network service quality quantification value; After a preset delay, the real-time network service quality quantization value is synchronized to the delay critic network to obtain the delayed network service quality quantization value; At any time during the real-time execution of the network service quality dynamic optimization instruction, obtaining the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network; Obtaining a smaller value between the current real-time network service quality quantization value and the current delayed network service quality quantization value as a target network service quality quantization value; The network resource scheduling strategy of the network to which the target aircraft belongs is adjusted according to the target network service quality quantization value.

2. The method for dynamically optimizing aircraft network service quality according to claim 1, wherein: The method of constructing a network service quality quantification model based on indicator fusion according to the weight coefficients of the transport layer network indicators includes: Obtaining the delay, jitter, and packet loss rate of the transport layer network indicators; Based on the delay, the jitter, and the packet loss rate, the network service quality quantification model is constructed using the following formula: Q_score=α·Delay + β·Jitter + γ·Loss; Among them, Q_score represents the quantitative value of network service quality, Delay represents the value of the delay, Jitter represents the value of the jitter, Loss represents the value of the packet loss rate, α represents the first weight coefficient corresponding to the delay, Jitter represents the second weight coefficient corresponding to the jitter, and γ represents the third weight coefficient corresponding to the packet loss rate.

3. The method for dynamically optimizing aircraft network service quality according to claim 2, wherein: The dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network includes: Obtaining the real-time speed of the target aircraft from the motion parameters; When the real-time speed is greater than the speed threshold, the adjusted first weight coefficient is calculated using the following formula: ； in, represents the adjusted first weight coefficient, the initial value of the first weight coefficient, represents the speed coefficient, represents the real-time speed, Indicates the maximum speed.

4. The method for dynamically optimizing aircraft network service quality according to claim 2, wherein: The dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes: Obtaining the real-time longitudinal acceleration of the target aircraft from the motion parameters; When the real-time longitudinal acceleration is greater than the longitudinal acceleration threshold, calculating a compensation value of the second weight coefficient; adding the compensation value to the second weight coefficient; The compensation value of the second weight coefficient is calculated using the following formula: ； in, represents the compensation value of the second weight coefficient, m represents the real-time longitudinal acceleration, represents the longitudinal acceleration safety threshold, represents the initial value of the second weight coefficient, represents the real-time pitch angle of the target aircraft, Indicates the maximum pitch angle.

5. The method for dynamically optimizing aircraft network service quality according to claim 2, wherein: The dynamically adjusting the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network further includes: Obtaining the target altitude and real-time altitude of the target aircraft; Calculating the difference between the target altitude and the real-time altitude to obtain the altitude difference of the target aircraft; Obtaining a height tolerance of the target aircraft, and obtaining a real-time roll angle of the target aircraft from the motion parameters; According to the height tolerance and the real-time roll angle, the adjusted third weight coefficient is calculated using the following formula: ； in, ; in, represents the adjusted third weight coefficient, represents the initial value of the third weight coefficient, represents the real-time roll angle, represents the height difference, Indicates the height tolerance.

6. The method for dynamically optimizing aircraft network service quality according to claim 1, wherein: The adjusting the network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantified value includes: When the target network service quality quantization value is greater than or equal to a first threshold and less than a second threshold, obtaining a non-critical video stream corresponding to the network to which the target aircraft belongs, limiting the bandwidth of the non-critical video stream to a preset proportion of the original bandwidth, and initiating an I-frame priority transmission mechanism; When the target network service quality quantization value is greater than or equal to the second threshold and less than a third threshold, initiating a coding upgrade mechanism for converting the first digital video compression format to the second digital video compression format in the network to which the target aircraft belongs, downgrading the video bit rate transmitted in the network to which the target aircraft belongs to to a configured bit rate, and disabling video stream metadata backhaul in the network to which the target aircraft belongs; When the target network service quality quantization value is greater than or equal to the third threshold, the resolution of the image data transmitted in the network to which the target aircraft belongs is downgraded, a data packet truncation mechanism is enabled in the network to which the target aircraft belongs, and the transmission of all non-real-time data is suspended.

7. The method for dynamically optimizing aircraft network service quality according to claim 1, wherein: After adjusting the network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantified value, the method further includes: Re-obtaining the network service quality quantization value output by the dual critic network as the network service quality update value; Comparing the network service quality update value with the target network service quality quantized value; When the network service quality update value is less than the target network service quality quantization value, determining that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs has an optimization effect; or When the network service quality update value is greater than or equal to the target network service quality quantization value, it is determined that adjusting the network resource scheduling strategy of the network to which the target aircraft belongs does not have an optimization effect, and an optimization prompt message is sent to the designated terminal device.

8. A device for dynamically optimizing aircraft network service quality, characterized in that: The aircraft network service quality dynamic optimization device includes: A construction unit, configured to construct a network service quality quantification model based on indicator fusion according to weight coefficients of transport layer network indicators in response to a dynamic optimization instruction for the network service quality of the target aircraft; The construction unit is further configured to construct a dual-critic network based on the MATD3 algorithm and the network service quality quantification model; wherein the dual-critic network includes a real-time critic network and a delayed critic network; wherein, when constructing the dual-critic network, a priority experience replay strategy and a state clustering storage strategy are adopted to process training samples; the priority experience replay strategy is configured to assign a sampling weight of 3 times to training samples whose network service quality quantification value decreases by more than 20%, and the state clustering storage strategy is configured to separately store training samples whose flight speed is greater than or equal to 20 m / s; A collection unit, configured to collect transport layer network indicator values ​​and motion parameters of the target aircraft in real time using a probe deployed on the target aircraft side; an adjustment unit, configured to input the transport layer network indicator value and the motion parameter into the real-time critic network, and dynamically adjust the weight coefficient of the transport layer network indicator according to the motion parameter in the real-time critic network; An input unit is configured to input the adjusted weight coefficient and the transport layer network indicator value into the network service quality quantification model in the real-time critic network to obtain a real-time network service quality quantification value; A synchronization unit, configured to synchronize the real-time network service quality quantization value to the delay critic network after a preset delay, to obtain the delayed network service quality quantization value; An acquisition unit, configured to acquire, at any time during the real-time execution of the network service quality dynamic optimization instruction, the current real-time network service quality quantization value output by the real-time critic network and the current delayed network service quality quantization value output by the delayed critic network; The acquisition unit is further configured to acquire the smaller value of the current real-time network service quality quantization value and the current delayed network service quality quantization value as the target network service quality quantization value; The adjustment unit is further configured to adjust a network resource scheduling strategy of the network to which the target aircraft belongs according to the target network service quality quantization value.

9. A computer device, characterized in that: The computer device comprises: a memory storing at least one instruction; and A processor executes instructions stored in the memory to implement the method for dynamically optimizing aircraft network service quality as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the method for dynamically optimizing aircraft network service quality according to any one of claims 1 to 7.

Images