Resource allocation system and method in satellite-ground convergence network

Abstract

The invention relates to the technical field of communication networks, in particular to a resource allocation system and method in a satellite-ground fusion network, and the system comprises a satellite-ground topology and channel evolution predictor which is used for obtaining satellite ephemeris, user GNSS positioning and moving vectors, ground base station topology and a real-time CQI / RSRP measurement report; generating future link state information; the business QoE impact and switching cost modeling device is used for calculating transient interruption time of a switching action; generating switching cost information; the continuity risk quantification engine is used for generating continuity risk information containing the link maintaining risk probability, the instantaneous impact collapse probability and the link switching risk probability; the risk evasion type resource decision-making device is used for calculating maintenance link comprehensive cost and switching link comprehensive cost; calculating a dynamic switching damping threshold value; generating risk avoidance decision information; according to the invention, the high-frequency ping-pong switching near the edge state point is effectively inhibited, and the signaling overhead caused by invalid switching is reduced.

Description

Technical Field

[0001] This invention relates to the field of communication network technology, specifically to a resource allocation system and method in a space-ground integrated network. Background Technology

[0002] With the rapid development of satellite-terrestrial converged networks, providing seamless coverage and high-quality service experience for highly dynamic mobile users has become a key technical challenge. Ensuring service continuity is one of its core objectives. In converged networks, user terminals need to switch between dynamically changing satellite links and terrestrial base station links.

[0003] However, existing resource allocation and handover technologies have significant limitations. Traditional decision-making mainly relies on instantaneous network appearance indicators such as signal-to-noise ratio or throughput, lacking forward-looking prediction of the future evolution of the link, which is a short-sighted passive response mechanism. Existing technologies generally ignore the transient transfer overhead of the handover action itself, that is, the physical interruption time caused by the handover process and its instantaneous impact cost on the QoE of a specific service. This short-sighted decision-making mechanism based on instantaneous thresholds is very likely to lead to frequent ping-pong handovers in the edge areas of link quality. Such ineffective handovers not only increase the network signaling burden, but also seriously damage the fundamental value of service continuity for users, causing service lag or interruption, resulting in a serious disconnect between network appearance indicators and actual user experience. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a resource allocation system and method in a space-ground integrated network. Specifically, the technical solution of this invention is as follows:

[0005] A resource allocation system in a space-ground integrated network, the system comprising:

[0006] The satellite-to-ground topology and channel evolution predictor is used to acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; it integrates a preset orbital dynamics model and a preset wireless channel prediction model to predict the future state of all available links for the user, so as to generate future link state information.

[0007] A service QoE impact and switching cost modeler is used to obtain user service flow types and QoE requirements; calculate the transient interruption time of switching actions; quantify the instantaneous QoE drop value of a specific service based on the transient interruption time; and generate switching cost information based on the instantaneous QoE drop value.

[0008] The continuous risk quantification engine is used to calculate the risk probability of maintaining the current link based on the future link status information, the switching cost information, and a preset QoE acceptable threshold; calculate the instantaneous impact collapse probability; calculate the risk probability of switching to the target link; and generate continuous risk information containing the risk probability of maintaining the link, the instantaneous impact collapse probability, and the risk probability of switching the link.

[0009] A risk-averse resource decision-maker is used to calculate the overall cost of maintaining the link and the overall cost of switching the link based on the continuous risk information, preset business priority weights, and preset normalized resource costs; to calculate the dynamic switching damping threshold based on the instantaneous impact collapse probability; and to execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk-averse decision information.

[0010] Furthermore, the future link state information includes: predicted signal-to-noise ratio, predicted latency, and predicted packet loss rate; the handover cost information includes: transient interruption time and instantaneous QoE drop value; the continuity risk information includes: the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of handover link risk; the risk avoidance decision information includes: the overall cost of maintaining the link, the overall cost of handover link, the dynamic handover damping threshold, and the optimal decision instruction.

[0011] Furthermore, the satellite-to-ground topology and channel evolution predictor includes:

[0012] The data aggregation submodule is used to acquire satellite ephemeris data, terminal GNSS positioning and movement vectors, ground base station topology information, and real-time CQI / RSRP measurement reports;

[0013] The channel evolution prediction submodule is used to predict the time series of signal-to-noise ratio, latency, and packet loss rate of all available links within a preset time period based on the report, the ephemeris data, the positioning and movement vectors, and the topology information, by fusing a preset orbital dynamics model and a preset wireless channel prediction model.

[0014] The status information generation submodule is used to generate the future link status information based on the time series.

[0015] Furthermore, the business QoE impact and switching cost modeler includes:

[0016] The interruption time calculation submodule is used to obtain the service flow type and calculate the transient interruption time based on the preset signaling interaction time, the preset physical layer synchronization time, and the preset data buffer reconstruction time.

[0017] The QoE impact modeling submodule is used to call a preset QoE mapping function specific to the service flow type; and calculate the instantaneous QoE drop value based on the transient interruption time and the estimated packet loss rate during the handover process.

[0018] The switching cost generation submodule is used to generate the switching cost information based on the transient interruption time and the instantaneous QoE drop value.

[0019] Furthermore, the continuous risk quantification engine includes:

[0020] The steady-state QoE prediction submodule is used to obtain the future link state information; and call a preset steady-state QoE prediction function to convert it into a future steady-state QoE prediction value.

[0021] The risk probability calculation submodule is used to calculate, based on the predicted future steady-state QoE value, the probability that maintaining the current link will cause the QoE to fall below a preset acceptable QoE threshold, thus obtaining the link maintenance risk probability; based on the current QoE, the instantaneous QoE drop value, and the acceptable QoE threshold, the probability that an instantaneous impact will cause QoE collapse, thus obtaining the instantaneous impact collapse probability; and based on the predicted future steady-state QoE value, the probability that the future QoE of the link after the switch will fall below the acceptable QoE threshold, thus obtaining the future collapse probability after the switch.

[0022] The risk information generation submodule is used to calculate the switching link risk probability by combining the instantaneous impact collapse probability and the future collapse probability after the switch; and to generate the continuity risk information including the holding link risk probability, the instantaneous impact collapse probability and the switching link risk probability.

[0023] Furthermore, the risk-averse resource decision-maker includes:

[0024] The comprehensive cost calculation submodule is used to obtain the probability of maintaining the link risk and the probability of switching the link risk; and to calculate the comprehensive cost of maintaining the link and the comprehensive cost of switching the link by combining the preset service priority weight and the preset normalized resource cost.

[0025] The damping threshold calculation submodule is used to obtain the instantaneous impact collapse probability; and calculate the dynamic switching damping threshold by combining the preset system sensitivity coefficient and the service priority weight.

[0026] The decision generation submodule is used to determine whether the overall cost of the switching link is less than the overall cost of the holding link minus the dynamic switching damping threshold; if the determination is yes, the optimal decision instruction is determined to be switching; if the determination is no, the optimal decision instruction is determined to be holding; and based on the optimal decision instruction, the risk avoidance decision information is generated.

[0027] Furthermore, the wireless channel prediction model is a long short-term memory network model or a Markov model.

[0028] Furthermore, the system is deployed on the core network side of the terrestrial network, MEC nodes, or satellite network ground gateway stations.

[0029] A resource allocation method in a space-ground integrated network includes the following steps:

[0030] Acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; fuse preset orbital dynamics models and preset wireless channel prediction models to predict the future state of all available user links, thereby generating future link state information;

[0031] Obtain the user's service flow type and QoE requirements; calculate the transient interruption time of the handover action; based on the transient interruption time, quantify the instantaneous QoE drop value of a specific service; and generate handover cost information based on the instantaneous QoE drop value.

[0032] Based on the future link status information, the switching cost information, and the preset QoE acceptable threshold, calculate the risk probability of maintaining the current link; calculate the instantaneous impact collapse probability; calculate the risk probability of switching to the target link; and generate continuous risk information containing the risk probability of maintaining the link, the instantaneous impact collapse probability, and the risk probability of switching the link.

[0033] Based on the continuous risk information, preset business priority weights, and preset normalized resource costs, calculate the overall cost of maintaining the link and the overall cost of switching the link; based on the instantaneous impact failure probability, calculate the dynamic switching damping threshold; and execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk avoidance decision information.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. This invention realizes the transformation from passive response to active avoidance. By using satellite-to-ground topology and channel evolution predictor, the basis for resource decision-making is changed from the current instantaneous measurement value to the evolution curve of the future link state. This forward-looking prediction enables the system to actively perform handover before anticipating that the user is about to enter the obstruction area or the channel deteriorates, thus avoiding the foreseeable QoE collapse risk in the future, rather than waiting for the signal to be lost before responding passively.

[0036] 2. This invention avoids instantaneous impact crashes and ensures QoE continuity. Through a service QoE impact and handover cost modeler, it quantifies the transient interruption time caused by handover actions and the instantaneous QoE drop value for specific services. The continuity risk quantification engine calculates the probability of instantaneous impact crashes and decomposes the total handover risk into instantaneous impact and future channel risk, thereby avoiding handover to a link with a good future channel but where the handover action itself will cause service crashes, ensuring a smooth user experience.

[0037] 3. This invention effectively suppresses ping-pong handover, enhances decision robustness, and constructs a risk-averse resource decision-making closed loop to avoid QoE collapse risk. It calculates a dynamic handover damping threshold based on the instantaneous impact collapse probability. When the instantaneous impact risk is high, the dynamic threshold will increase significantly, requiring the net benefit brought by the handover to be large enough to trigger it, thereby effectively suppressing high-frequency ping-pong handover near the edge state point and reducing the signaling overhead caused by invalid handover.

[0038] 4. This invention intelligently balances QoE risk and resource cost. Through a comprehensive cost calculation submodule, the risk probability of maintaining and switching links is uniformly weighted with resource cost to calculate a dimensionless comprehensive cost. Based on this, the decision-maker performs a weighted trade-off between the risk cost of ensuring user QoE continuity and the cost of network resource consumption, enabling the system to reject links that are momentarily optimal but unstable, thus achieving optimal resource decision-making with risk avoidance as the goal. Attached Figure Description

[0039] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0040] Figure 1 This is a flowchart of the method of the present invention;

[0041] Figure 2 This is a structural diagram of the system of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0043] Example 1:

[0044] Please see Figure 1 A resource allocation system in a space-ground integrated network, the system comprising:

[0045] The satellite-to-ground topology and channel evolution predictor is used to acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; it integrates a preset orbital dynamics model and a preset wireless channel prediction model to predict the future state of all available links for the user, so as to generate future link state information.

[0046] A service QoE impact and switching cost modeler is used to obtain user service flow types and QoE requirements; calculate the transient interruption time of switching actions; quantify the instantaneous QoE drop value of a specific service based on the transient interruption time; and generate switching cost information based on the instantaneous QoE drop value.

[0047] The continuity risk quantification engine is used to calculate the probability of maintaining the current link based on the future link status information, the switching cost information, and a preset QoE acceptable threshold, which is determined according to the service level agreement of service k or relevant industry standards, such as the minimum acceptable threshold of MOS score defined by ITU-T for VoIP; calculate the probability of instantaneous impact failure; calculate the probability of switching to the target link; and generate continuity risk information containing the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of switching the link risk.

[0048] A risk-averse resource decision-maker is used to calculate the overall cost of maintaining the link and the overall cost of switching the link based on the continuous risk information, preset business priority weights, and preset normalized resource costs; to calculate the dynamic switching damping threshold based on the instantaneous impact collapse probability; and to execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk-averse decision information.

[0049] This invention provides a resource allocation system in a space-ground converged network. Its core objective is to solve the technical problem in the prior art where the pursuit of instantaneous apparent indicators such as SINR or throughput leads to ping-pong switching, which in turn seriously damages the fundamental value of user service continuity. This system replaces the traditional short-sighted trigger based on instantaneous thresholds by constructing a forward-looking decision-making closed loop aimed at avoiding the risk of QoE collapse.

[0050] In this embodiment, the system comprises four core modules deployed on MEC nodes of the terrestrial network to achieve low-latency decision-making:

[0051] Satellite-Ground Topology and Channel Evolution Predictor: The purpose of this predictor is to change the basis of resource decision-making from current measurements to future evolution curves, thereby realizing the transformation from passive response to active avoidance.

[0052] In this embodiment, the satellite-to-ground topology and channel evolution predictor acquires satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports in real time through a data aggregation interface.

[0053] After obtaining the above data, the predictor fuses two preset models:

[0054] The pre-defined orbital dynamics model refers to a deterministic model based on Keplerian mechanics and satellite orbital parameters; its function is to accurately predict a pre-defined prediction window in the future using satellite ephemeris and user GNSS positioning. Within, the geometry of all visible satellite links, including elevation angle, Doppler shift, and entry and exit times of the keyhole effect region;

[0055] The preset wireless channel prediction model refers to a probabilistic model trained based on historical data, such as an LSTM trained based on historical channel data and corresponding movement vectors. Its function is to use the time series of real-time CQI / RSRP measurement reports and user movement vectors to predict the evolution of the wireless environment of the terrestrial link, especially obstruction events such as entering urban canyons or tunnels.

[0056] Based on this fusion model, the predictor forecasts the future state of all available links for the user to generate structured future link state information; this information is packaged into a set of future-oriented state curves. ,in And output it to the continuous risk quantification engine;

[0057] Business QoE Impact and Switching Cost Modeler: The purpose of this modeler is to accurately quantify the transient transfer overhead that exists in the switching action itself and is ignored in the existing technology, that is, the hidden physical cost of the switching action to the user experience.

[0058] In this embodiment, the service QoE impact and switching cost modeler acquires the user service flow type during operation. and the QoE requirements of this business ;

[0059] This module performs calculations on the transient interruption time of the switching action. Transient interruption time This refers to the source link Release to target link During the availability period, the physical time of a complete interruption of the business flow is calculated using the following model:

[0060]

[0061] in, Total interruption time; unit: seconds; calculation result of this formula;

[0062] : Signaling interaction time required for switching; unit: seconds; according to The type is obtained from the network configuration parameters;

[0063] Time required for the terminal to complete physical layer synchronization on the new link; unit: seconds; determined according to terminal hardware specifications and 3GPP specifications;

[0064] Time required for emptying, rebuilding, and reordering data packets on the terminal side; unit: seconds; determined according to protocol stack standards;

[0065] In obtaining Then, based on the transient interruption time, this module quantifies the instantaneous QoE drop value of a specific service. QoE instantaneous drop value It refers to the The resulting instantaneous degradation in user-perceptible experience quality, which is achieved through a business-specific... Quantify using the QoE impact model:

[0066]

[0067] in, Business type, obtained from PCF;

[0068] Business-specific The QoE mapping function, such as the E-Model for VoIP, or the proxy model for video services trained on offline datasets; predefined or pre-trained by the system;

[0069] : The transient interruption time calculated in the previous step;

[0070] Switch The expected additional packet loss rate during the period; estimated based on protocol status and initial synchronization quality of the target link;

[0071] The innovation of this formula lies in its mapping of physical layer interruption time to user-perceived experience loss; this module generates a formula based on QoE instantaneous drop values, containing... and The switching cost information is then output to subsequent modules;

[0072] Continuous Risk Quantification Engine: The purpose of this engine is to provide a quantitative probabilistic basis for whether to switch or maintain the core issue of this invention; it no longer compares instantaneous SINR, but compares the total risk probability of future QoE collapse;

[0073] In this embodiment, the continuity risk quantification engine is based on future link status information and switching cost information. and the preset acceptable QoE threshold Perform calculations;

[0074] To achieve the above quantization, the engine calculates the risk probability of maintaining the current link. ; Risk probability of maintaining the current link This refers to the situation where the system decides to remain on the current link. In the future Within a certain period, the QoE of this link fell below The probability of is calculated using the following model:

[0075]

[0076] in, It is a preset steady-state QoE prediction function. predictor Converted to future QoE score; Based on The integral probability calculated from the predicted confidence interval; specifically, assuming that at any time t, the predicted QoE value is... If the predicted value follows a normal distribution with a mean of the predicted value and a standard deviation of the prediction confidence interval width (e.g., based on the variance estimate of the prediction model), then the probability can be calculated by taking the normal distribution at intervals less than 10 ... The cumulative distribution function value over the interval is obtained. The final... The maximum value of the probability calculated at all times within the time window can be taken to represent the worst-case risk within the time window;

[0077] The engine calculates the probability of instantaneous impact collapse. Probability of instantaneous impact collapse This refers to the effect caused by the switching action itself. Will a sudden drop immediately cause QoE to drop from its current value? Break Its calculation model is as follows:

[0078]

[0079] in, To predict QoE based on real-time measurements of the current link using a steady-state QoE prediction function. The calculated current QoE score, From the modeler;

[0080] The engine calculates the probability of risk when switching to the target link. Risk probability of switching to the target link This refers to the situation where the system decides to switch to the alternative link. The total probability that this leads to a QoE collapse; this definition is one of the key innovations of this invention, as it encompasses two failure paths: transient impact failure. Or the switch will fail in the future. Its calculation model is as follows:

[0081]

[0082] in, This formula is based on probability theory. Here, to simplify the model calculation, the instantaneous impact failure and the failure of the future link state after the handover are treated as approximately independent events. This approximation is reasonable in most scenarios because the instantaneous impact failure is mainly determined by short-term fixed overhead such as signaling interaction and hardware synchronization, while the future link failure is mainly determined by long-term factors such as user movement and environmental occlusion. The correlation between the two is weak, and the total failure risk is that neither fails. The engine generates content including , and The continuous risk information is output to the decision-maker;

[0083] Risk-averse resource decision-maker: The purpose of this decision-maker is to act as the central decision-making module of the system, making the final decision based on risk aversion rather than best efforts; it weighs the QoE risk and resource costs.

[0084] In this embodiment, the risk-averse resource decision-maker is based on continuous risk information. Preset business priority weights and the preset normalized resource cost The normalized resource cost It is a comprehensive measure of the various resources consumed by using link l, such as bandwidth, power, or spectrum costs, for example, through Normalization is performed in the following manner, where It is the original cost function. and The decision is based on the maximum and minimum possible original costs of all links in the system.

[0085] To execute the decision, the decision maker calculates the overall cost of maintaining the link. Overall cost of switching links Comprehensive cost It is a uniform, dimensionless decision score used to compare the total cost of different actions:

[0086]

[0087]

[0088] in, It is a preset hyperparameter used to balance risk and cost;

[0089] To prevent ping-pong switching, the decision-maker is based on the probability of instantaneous shock collapse. Calculate the dynamic switching damping threshold Dynamically switch damping threshold Also known as switching hysteresis, it requires that the net benefit of the switch be large enough to trigger it; the innovation of this invention lies in the fact that this threshold is dynamic:

[0090]

[0091] in, It is the preset system sensitivity coefficient;

[0092] The decision-maker performs decisions based on the sustain link cost, the handover link cost, and a dynamic handover damping threshold: only when... Only when the switch is in effect will a switch be performed; otherwise, the current link will be maintained. The decision result is encapsulated as risk avoidance decision information and sent to the network execution layer.

[0093] The system in this invention, by constructing a complete technical closed loop encompassing prediction, cost modeling, risk quantification, and avoidance decision-making, changes the paradigm of resource allocation. It no longer passively responds to instantaneous measurements but proactively avoids the total QoE collapse risk, including transient transfer overhead. It achieves a shift from passive response to proactive avoidance, for example, proactively switching 5 seconds before entering a tunnel, rather than switching after signal loss. It solves the problem of decoupling QoE from network metrics; the system intentionally rejects instantaneously optimal but unstable links to ensure a smooth user experience. Through a system based on… Intelligent switching damping This effectively suppressed ping-pong handover and significantly reduced the signaling overhead caused by invalid handover;

[0094] It should be noted that this embodiment mainly focuses on service continuity optimization for a single user. In multi-user scenarios, the decision results of this system can be used as input to the upper-layer network resource manager. The RRM combines the decision requests of multiple users and the global resource status to perform the final resource allocation and admission control in order to achieve global optimization.

[0095] Example 2:

[0096] The future link status information includes: predicted signal-to-noise ratio, predicted latency, and predicted packet loss rate; the handover cost information includes: transient interruption time and instantaneous QoE drop value; the continuity risk information includes: the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of handover link risk; the risk avoidance decision information includes: the overall cost of maintaining the link, the overall cost of handover link, the dynamic handover damping threshold, and the optimal decision instruction.

[0097] Based on Example 1, this example specifies the content of the information artifacts transmitted between the four major modules of the system to ensure the completeness and unambiguity of data handover.

[0098] Future link state information: Its purpose is to provide the full-dimensional input required to calculate steady-state QoE; in this embodiment, it specifically includes the signal-to-noise ratio of the predictions generated by the predictor. Predicted latency And the predicted packet loss rate Time series; this set of vectors Compared to SINR alone, it can more accurately map to the QoE score of a specific service;

[0099] Switching cost information: Its purpose is to encapsulate the physical and perceived costs of the switching action; in this embodiment, it specifically includes the transient interruption time calculated by the modeler. and QoE instantaneous drop value ;

[0100] Continuity risk information: Its purpose is to provide the decision-maker with all the risk components needed for decision-making; in this embodiment, it specifically includes the keep-alive risk probability calculated by the risk quantification engine. Probability of instantaneous impact collapse and the probability of switching links The transmission of this triple is crucial because the decision-maker not only needs... and To calculate Cost, also needs To independently calculate dynamic damping ;

[0101] Risk avoidance decision information: Its purpose is to provide a traceable and complete package of decision results; in this embodiment, it includes not only the final optimal decision instruction, but also the intermediate evidence leading to that decision, namely, the overall cost of maintaining the link. Overall cost of switching links and dynamically switching damping threshold ;

[0102] This embodiment ensures the standardization and completeness of data transfer between modules by structurally defining the four major information artifacts within the system; in particular, it addresses the probability of instantaneous impact crashes. As an independent data item, it is explicitly transmitted in continuous risk information, providing an indispensable and decoupled input for risk-averse resource decision-makers to achieve risk-based dynamic damping, thereby enhancing the modularity and scalability of the system.

[0103] Example 3:

[0104] Satellite-to-ground topology and channel evolution predictor includes:

[0105] The data aggregation submodule is used to acquire satellite ephemeris data, terminal GNSS positioning and movement vectors, ground base station topology information, and real-time CQI / RSRP measurement reports;

[0106] The channel evolution prediction submodule is used to predict the time series of signal-to-noise ratio, latency, and packet loss rate of all available links within a preset time period based on the report, the ephemeris data, the positioning and movement vectors, and the topology information, by fusing a preset orbital dynamics model and a preset wireless channel prediction model.

[0107] The status information generation submodule is used to generate the future link status information based on the time series.

[0108] Based on Example 1, this example specifically defines the internal implementation of the satellite-to-ground topology and the channel evolution predictor, decoupling its functions into three sub-modules:

[0109] Predictors include:

[0110] Data aggregation submodule: Its purpose is to act as the data entry point of the system and collect the information required for decision-making from heterogeneous data sources. In this embodiment, this submodule is used through dedicated interfaces to obtain satellite ephemeris data from the satellite operation center, GNSS positioning and movement vectors reported by terminals, ground base station topology information from the network operation and maintenance database, and real-time CQI / RSRP measurement reports reported by the physical layer.

[0111] Channel evolution prediction submodule: Its purpose is to execute the core prediction algorithm; in this embodiment, this submodule is used to predict the time series of signal-to-noise ratio, latency and packet loss rate of all available links within a preset time period based on all reports, data, vectors and information obtained by the data aggregation submodule, and by fusing the preset orbit dynamics model and the preset wireless channel prediction model.

[0112] State information generation submodule: Its purpose is to encapsulate the original prediction results into a standardized output; in this embodiment, this submodule is used to package and format the time series generated by the channel evolution prediction submodule to generate the future link state information of Embodiment 2 for use by the continuity risk quantification engine.

[0113] This embodiment achieves clear architectural decoupling by decomposing the predictor function into three sub-modules: convergence, prediction, and encapsulation. By forcibly fusing two models, orbital dynamics and wireless channel, in the channel evolution prediction sub-module, it significantly improves the comprehensive prediction accuracy of heterogeneous links in the space-ground converged network, providing a high-confidence input for subsequent risk quantification.

[0114] Example 4:

[0115] The business QoE impact and switching cost modeler includes:

[0116] The interruption time calculation submodule is used to obtain the service flow type and calculate the transient interruption time based on the preset signaling interaction time, the preset physical layer synchronization time, and the preset data buffer reconstruction time.

[0117] The QoE impact modeling submodule is used to call a preset QoE mapping function specific to the service flow type; and calculate the instantaneous QoE drop value based on the transient interruption time and the estimated packet loss rate during the handover process.

[0118] The switching cost generation submodule is used to generate the switching cost information based on the transient interruption time and the instantaneous QoE drop value.

[0119] Based on Example 1, this example specifically defines the internal implementation of the business QoE impact and switching cost modeler, decoupling its functionality into three sub-modules:

[0120] The modeler includes:

[0121] Interruption time calculation submodule: Its purpose is to quantify the physical interruption duration of the handover; in this embodiment, this submodule is used to obtain the service flow type and, based on the preset signaling interaction time retrieved from the network configuration library. Preset physical layer synchronization time and preset data buffer rebuild time ,pass The transient interruption time was calculated. ;

[0122] The QoE impact modeling submodule aims to map physical interruption duration into perceived experience loss. In this embodiment, this submodule is used to call a function related to the service flow type. Pre-defined QoE mapping functions This submodule calculates the transient interrupt time passed in by the interrupt time calculation submodule. A predicted packet loss rate during the handover process ,pass The instantaneous drop value of QoE was calculated. For example, for a video service, this The function can be modeled as a nonlinear model that better reflects the perceived saturation effect, for example... Where A is the maximum QoE drop value, This is a characteristic time constant perceived by the business. This model can more accurately characterize the dose-effect relationship of a sharp deterioration in user experience after the interruption time exceeds a certain threshold; in another embodiment, it can also be simplified to a linear model, such as... ,in and The impact coefficient is obtained through regression analysis;

[0123] The switching cost generation submodule aims to encapsulate the calculation results; in this embodiment, this submodule is used to calculate the transient interruption time based on the first two submodules. and QoE instantaneous drop value They are packaged to generate the switching cost information for Example 2;

[0124] This embodiment decomposes the quantification of switching costs into two steps: physical interruption time calculation and QoE impact modeling. This decomposition enables the present invention to evaluate switching overhead in a refined and service-aware manner. For example, a 230ms interruption may be catastrophic for VoIP services, but may have little impact on background file download services. This refined quantification is key to avoiding overprotection of non-critical services and insufficient protection of critical services.

[0125] Example 5:

[0126] The continuous risk quantification engine includes:

[0127] The steady-state QoE prediction submodule is used to obtain the future link state information; and call a preset steady-state QoE prediction function to convert it into a future steady-state QoE prediction value.

[0128] The risk probability calculation submodule is used to calculate, based on the predicted future steady-state QoE value, the probability that maintaining the current link will cause the QoE to fall below a preset acceptable QoE threshold, thus obtaining the link maintenance risk probability; based on the current QoE, the instantaneous QoE drop value, and the acceptable QoE threshold, the probability that an instantaneous impact will cause QoE collapse, thus obtaining the instantaneous impact collapse probability; and based on the predicted future steady-state QoE value, the probability that the future QoE of the link after the switch will fall below the acceptable QoE threshold, thus obtaining the future collapse probability after the switch.

[0129] The risk information generation submodule is used to calculate the switching link risk probability by combining the instantaneous impact collapse probability and the future collapse probability after the switch; and to generate the continuity risk information including the holding link risk probability, the instantaneous impact collapse probability and the switching link risk probability.

[0130] Based on Example 1, this example specifically defines the internal implementation of the continuous risk quantification engine, decoupling its functionality into three sub-modules:

[0131] The engine includes a steady-state QoE prediction submodule, whose purpose is to convert physical layer prediction into application layer experience prediction. In this embodiment, this submodule is used to obtain future link state information from the predictor and call a preset steady-state QoE prediction function. ,Will Convert into a time series of future steady-state QoE predictions The preset steady-state QoE prediction function For example, it could be a weighted model based on a specific business type k, such as... ,in It is a preset weight. It is a non-linear function that maps each physical indicator to a standard scoring range; or, the function can also be a deep neural network model trained with a large number of physical indicators and corresponding human scores.

[0132] Risk probability calculation submodule: Its purpose is to perform independent calculations of the three core risks; in this embodiment, this submodule:

[0133] based on Future steady-state QoE forecast Calculate its acceptable QoE threshold in the future. The probability of maintaining the link risk is obtained. ;

[0134] Based on the current QoE The instantaneous drop in QoE value transmitted from the modeler With QoE acceptable threshold ,pass Calculate the probability that a transient shock will cause QoE collapse, and obtain the transient shock collapse probability. ;

[0135] based on Future steady-state QoE forecast Calculate its future drop below The probability of future collapse after switching is obtained from the probability of switching. ;

[0136] Risk information generation submodule: Its purpose is to combine and encapsulate risks; in this embodiment, this submodule is used to combine the risk probability calculation submodule to generate the instantaneous shock collapse probability. and the probability of future crashes after switching ,pass The total handover link risk probability is calculated. ; Generate includes , and Continuous risk information;

[0137] This embodiment clearly defines sub-modules. , and The calculation path for the three risks; it involves switching the total risk. Explicit decomposition into instantaneous impact risk and future channel risks By combining these factors, this invention can accurately identify and avoid a typical mistake that traditional decision-making makes: switching to a link with a good future channel, but the switching action itself will cause the service to crash; this multi-dimensional quantification of risk is the mathematical basis for achieving robust decision-making.

[0138] Example 6:

[0139] The risk-avoidance resource decision-maker includes: a comprehensive cost calculation submodule, used to obtain the probability of maintaining the link risk and the probability of switching the link risk; and to calculate the comprehensive cost of maintaining the link and the comprehensive cost of switching the link by combining the preset business priority weight and the preset normalized resource cost.

[0140] The damping threshold calculation submodule is used to obtain the instantaneous impact collapse probability; and calculate the dynamic switching damping threshold by combining the preset system sensitivity coefficient and the service priority weight.

[0141] The decision generation submodule is used to determine whether the overall cost of the switching link is less than the overall cost of the holding link minus the dynamic switching damping threshold; if the determination is yes, the optimal decision instruction is determined to be switching; if the determination is no, the optimal decision instruction is determined to be holding; and based on the optimal decision instruction, the risk avoidance decision information is generated.

[0142] Based on Example 1, this example specifically defines the internal implementation of the risk-averse resource decision-maker, decoupling its functionality into three sub-modules:

[0143] The decision-maker includes a comprehensive cost calculation submodule, whose purpose is to unify risk and cost under the same dimension for comparison; in this embodiment, this submodule is used to obtain the keep-alive risk probability transmitted by the risk engine. and the probability of switching links Combined with preset business priority weights and the preset normalized resource cost Calculate the overall cost of maintaining the link respectively. Overall cost of switching links ;

[0144] The damping threshold calculation submodule aims to generate dynamically switching brakes to suppress the ping-pong effect. In this embodiment, this submodule is used to obtain the instantaneous impact collapse probability transmitted from the risk engine. Combined with preset system sensitivity coefficients and business priority weight ,pass The dynamic switching damping threshold is calculated. ;

[0145] The decision generation submodule aims to perform the final comparison and decision; in this embodiment, this submodule is used to determine the overall cost of the switching link. Is it less than the total cost of maintaining the link? Subtract the dynamic switching damping threshold ,Right now ;

[0146] If the judgment is yes, it indicates the net benefit of the switch. Sufficient to overcome the instantaneous impact cost of switching The optimal decision instruction is determined to be switching;

[0147] If the judgment is negative, then the optimal decision instruction is to maintain.

[0148] This submodule generates risk avoidance decision information for Example 2 based on the optimal decision instruction;

[0149] This embodiment constructs the decision-maker as a clear three-step closed loop; through the damping threshold calculation submodule, it utilizes... Dynamically adjust switching sensitivity; when and Similar and At higher levels, It will increase significantly, leading to The conditions are difficult to meet, thus suppressing the high-frequency ping-pong switching near such high-risk, low-return edge state points, which greatly enhances the robustness of system decision-making.

[0150] The decision-making mechanism of this invention has good robustness; even under high prediction uncertainty, the predictor output... The confidence interval will widen, leading to a change in the calculated risk probability. and When levels generally increase, the system tends to make conservative decisions. Extremely high When it is huge, decision-making conditions It becomes extremely difficult to satisfy, which effectively prevents the system from performing any switch that could cause a momentary business crash. Even if the current link quality is poor, it forces the maintenance of basic availability, avoiding the occurrence of worse results, and embodies the core idea of ​​risk avoidance.

[0151] Example 7:

[0152] The wireless channel prediction model is either a long short-term memory network model or a Markov model.

[0153] Based on Example 3, this example specifies the particular model to be selected for wireless channel prediction; the preferred model is either a Long Short-Term Memory (LSTM) network model or a Markov model.

[0154] In this embodiment, the LSTM model is preferably used. The technical consideration is that LSTM is a special type of recurrent neural network with a natural advantage in processing and predicting time series data. It can capture long-term dependencies and nonlinear characteristics in channel quality changes. For example, LSTM can learn from a calibration dataset containing user movement vectors and historical CQI sequences to fit channel change patterns, thereby predicting deterministic occlusion events caused by users entering urban canyons or tunnels, which is difficult for traditional Markov models to predict accurately.

[0155] In another embodiment with limited computing resources, a Markov model can be used. The technical consideration is that the Markov model can simplify the channel state into a finite number of discrete states and statistically obtain the state transition probability based on a calibration dataset containing historical measurement data and corresponding channel states. This model has low computational overhead and is suitable for predicting channel fading with strong randomness but no obvious long-term patterns.

[0156] This embodiment employs models such as LSTM or Markov that can handle time-dependent factors, enabling the satellite-to-ground topology and channel evolution predictor to learn and predict complex time-related factors in the wireless channel. This significantly improves the accuracy of future link state information and is a key technical support for the present invention to achieve proactive planning rather than passive response.

[0157] Example 8:

[0158] The system is deployed on the core network side of the terrestrial network, MEC nodes, or ground gateway stations of the satellite network.

[0159] In any of the systems in Examples 1 to 7, this embodiment limits the physical deployment location of the system; the system can be flexibly deployed on the core network side of the terrestrial network, MEC node, or satellite network ground gateway station;

[0160] Deployed at MEC nodes: This is a preferred embodiment of the present invention; its technical consideration is that MEC nodes are close to the network edge and user terminals, and can obtain GNSS and CQI / RSRP measurement reports reported by the terminals with the lowest latency; at the same time, the decision results can be issued and executed as quickly as possible; this deployment method maximizes the system's response speed to channel and location changes, and is especially suitable for ultra-low latency and high reliability services such as vehicle-to-everything (V2X) autonomous driving control signaling.

[0161] Deployed on the core network side of the terrestrial network: The technical consideration is that the core network has a global network topology and resource view, and can centrally manage and coordinate the resource allocation strategies of multiple MEC nodes and a large number of users, which is conducive to achieving global resource optimization and policy coordination;

[0162] Deployed at ground gateway stations of the satellite network: The technical consideration is that gateway stations are the convergence points of satellite links. Deploying them here allows the system to better grasp the real-time status of satellite resources and focuses on unified scheduling between satellite and ground links.

[0163] This embodiment provides flexible deployment options to adapt to different network architectures and business needs; deployment on MEC nodes can minimize decision latency and ensure the ultra-low latency continuity of critical services such as vehicle networking; deployment on the core network or gateway station is more conducive to global resource optimization and unified coordination of network policies.

[0164] Example 9:

[0165] Please see Figure 2 A resource allocation method in a space-ground integrated network includes the following steps:

[0166] Acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; fuse preset orbital dynamics models and preset wireless channel prediction models to predict the future state of all available user links, thereby generating future link state information;

[0167] Obtain the user's service flow type and QoE requirements; calculate the transient interruption time of the handover action; based on the transient interruption time, quantify the instantaneous QoE drop value of a specific service; and generate handover cost information based on the instantaneous QoE drop value.

[0168] Based on the future link status information, the switching cost information, and the preset QoE acceptable threshold, calculate the risk probability of maintaining the current link; calculate the instantaneous impact collapse probability; calculate the risk probability of switching to the target link; and generate continuous risk information containing the risk probability of maintaining the link, the instantaneous impact collapse probability, and the risk probability of switching the link.

[0169] Based on the continuous risk information, preset business priority weights, and preset normalized resource costs, calculate the overall cost of maintaining the link and the overall cost of switching the link; based on the instantaneous impact failure probability, calculate the dynamic switching damping threshold; and execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk avoidance decision information.

[0170] The present invention also provides a resource allocation method in a space-ground integrated network, which can be executed by the system of Embodiment 1; the steps included in the method have been fully disclosed in the detailed description of the four major modules of the system in the implementation of Embodiment 1;

[0171] The execution flow of this method is illustrated below through a specific embodiment, which corresponds to the ping-pong switching suppression scenario mentioned in the background art:

[0172] Suppose a user is using VoIP services and is currently connected to a terrestrial link. Above, its signal quality is at an edge; meanwhile, a LEO satellite After this process, the signal quality is slightly better; traditional solutions would switch immediately; the execution steps of the method of this invention are as follows:

[0173] The satellite-to-ground topology and channel evolution predictor acquires all inputs; orbital dynamics model prediction. The channel is good for the next 60 seconds, but It will also remain stable; the system generates future link status information;

[0174] Business QoE Impact and Switching Cost Modeler Launched;

[0175] Get business type ,That ;

[0176] Calculate transient interruption time The system has confirmed this Earth-to-satellite handover. , , ; ;

[0177] Quantify the instantaneous drop value of QoE System call ,enter Calculations show that this switch will have a significant impact on VoIP services. point;

[0178] Generate switching cost information; start the continuity risk quantification engine; obtain input: , , ; Calculate the risk probability of maintaining the current link Based on the prediction in step one, its The probability of scoring below 2.5 points ;

[0179] Calculate the probability of instantaneous shock collapse :calculate ,Right now ;because If true, then a collapse is a deterministic event. ;

[0180] Calculate the risk probability of switching to the target link Based on the prediction in step one, ; ;

[0181] Generate continuous risk information ( , , );

[0182] Risk-averse resource decision-maker activated; Input obtained: Business priority , Resource costs , ;

[0183] Calculate the overall cost:

[0184]

[0185]

[0186] Calculate the dynamic switching damping threshold :set up , ;

[0187] Decision making: Judgment ?Right now The condition is no;

[0188] Generate risk avoidance decision information: The instruction is to prohibit handover and maintain the current ground link;

[0189] The embodiments of this method demonstrate that, by proactively quantifying the instantaneous impact cost of the handover action itself, the present invention determines that this is unacceptable for VoIP services, leading to a total risk cost associated with the handover. Far higher than the cost of maintaining the status quo Therefore, this method avoids the harmful switching that would occur in traditional solutions, thus ensuring the continuity of VoIP services; in another embodiment, this method can also calculate much smaller This enables proactive risk avoidance during switching; it demonstrates that the method can intelligently balance risk avoidance between mitigating future risks and avoiding instantaneous shocks, ultimately achieving the fundamental value of ensuring service continuity.

[0190] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A resource allocation system in a space-ground integrated network, characterized in that, The system includes: The satellite-to-ground topology and channel evolution predictor is used to acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; By integrating a pre-defined orbital dynamics model and a pre-defined wireless channel prediction model, the future state of all available links for the user is predicted to generate future link state information. A business QoE impact and switching cost modeler is used to obtain user business flow types and QoE requirements; and to calculate the transient interruption time of switching actions. Based on the transient interruption time, the instantaneous QoE drop value of a specific service is quantified; Based on the instantaneous drop value of QoE, switching cost information is generated; A continuous risk quantification engine is used to calculate the risk probability of maintaining the current link based on the future link status information, the switching cost information, and a preset QoE acceptable threshold. Calculate the probability of instantaneous impact collapse; Calculate the probability of risk when switching to the target link; And generate continuous risk information including the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of switching the link risk; A risk-averse resource decision-maker is used to calculate the overall cost of maintaining the link and the overall cost of switching the link based on the continuous risk information, preset business priority weights, and preset normalized resource costs; to calculate the dynamic switching damping threshold based on the instantaneous impact collapse probability; and to execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk-averse decision information.

2. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The future link state information includes: predicted signal-to-noise ratio, predicted latency, and predicted packet loss rate; the handover cost information includes: transient interruption time and instantaneous QoE drop value; the continuity risk information includes: the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of handover link risk; the risk avoidance decision information includes: the overall cost of maintaining the link, the overall cost of handover link, the dynamic handover damping threshold, and the optimal decision instruction.

3. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The satellite-to-ground topology and channel evolution predictor includes: The data aggregation submodule is used to acquire satellite ephemeris data, terminal GNSS positioning and movement vectors, ground base station topology information, and real-time CQI / RSRP measurement reports; The channel evolution prediction submodule is used to predict the time series of signal-to-noise ratio, latency, and packet loss rate of all available links within a preset time period based on the report, the ephemeris data, the positioning and movement vectors, and the topology information, by fusing a preset orbital dynamics model and a preset wireless channel prediction model. The status information generation submodule is used to generate the future link status information based on the time series.

4. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The business QoE impact and switching cost modeler includes: The interruption time calculation submodule is used to obtain the service flow type and calculate the transient interruption time based on the preset signaling interaction time, the preset physical layer synchronization time, and the preset data buffer reconstruction time. The QoE impact modeling submodule is used to call a preset QoE mapping function specific to the service flow type; and calculate the instantaneous QoE drop value based on the transient interruption time and the estimated packet loss rate during the handover process. The switching cost generation submodule is used to generate the switching cost information based on the transient interruption time and the instantaneous QoE drop value.

5. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The continuous risk quantification engine includes: The steady-state QoE prediction submodule is used to obtain the future link state information; and call a preset steady-state QoE prediction function to convert it into a future steady-state QoE prediction value. The risk probability calculation submodule is used to calculate, based on the predicted future steady-state QoE value, the probability that maintaining the current link will cause the QoE to fall below a preset acceptable QoE threshold, thus obtaining the link maintenance risk probability; based on the current QoE, the instantaneous QoE drop value, and the acceptable QoE threshold, the probability that an instantaneous impact will cause QoE collapse, thus obtaining the instantaneous impact collapse probability; and based on the predicted future steady-state QoE value, the probability that the future QoE of the link after the switch will fall below the acceptable QoE threshold, thus obtaining the future collapse probability after the switch. The risk information generation submodule is used to calculate the switching link risk probability by combining the instantaneous impact collapse probability and the future collapse probability after the switch; and to generate the continuity risk information including the holding link risk probability, the instantaneous impact collapse probability and the switching link risk probability.

6. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The risk-averse resource decision-maker includes: The comprehensive cost calculation submodule is used to obtain the probability of maintaining the link risk and the probability of switching the link risk; and to calculate the comprehensive cost of maintaining the link and the comprehensive cost of switching the link by combining the preset service priority weight and the preset normalized resource cost. The damping threshold calculation submodule is used to obtain the instantaneous impact collapse probability; and calculate the dynamic switching damping threshold by combining the preset system sensitivity coefficient and the service priority weight. The decision generation submodule is used to determine whether the overall cost of the switching link is less than the overall cost of the holding link minus the dynamic switching damping threshold; if the determination is yes, the optimal decision instruction is determined to be switching; if the determination is no, the optimal decision instruction is determined to be holding; and based on the optimal decision instruction, the risk avoidance decision information is generated.

7. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The wireless channel prediction model is a long short-term memory network model or a Markov model.

8. The resource allocation system in the space-ground integrated network according to claim 1, characterized in that, The system is deployed on the core network side of the terrestrial network, MEC nodes, or ground gateway stations of the satellite network.

9. A resource allocation method in a space-ground integrated network, characterized in that, Includes the following steps: Acquire satellite ephemeris, user GNSS positioning and movement vectors, ground base station topology, and real-time CQI / RSRP measurement reports; By integrating a pre-defined orbital dynamics model and a pre-defined wireless channel prediction model, the future state of all available links for the user is predicted to generate future link state information. Obtain the user's service flow type and QoE requirements; calculate the transient interruption time of the handover action; Based on the transient interruption time, the instantaneous QoE drop value of a specific service is quantified; and based on the instantaneous QoE drop value, switching cost information is generated. Based on the future link status information, the switching cost information, and the preset QoE acceptable threshold, calculate the risk probability of maintaining the current link; Calculate the probability of instantaneous impact collapse; Calculate the probability of risk when switching to the target link; And generate continuous risk information including the probability of maintaining the link risk, the probability of instantaneous impact failure, and the probability of switching the link risk; Based on the continuous risk information, preset business priority weights, and preset normalized resource costs, calculate the overall cost of maintaining the link and the overall cost of switching the link; based on the instantaneous impact failure probability, calculate the dynamic switching damping threshold; and execute decisions based on the overall cost of maintaining the link, the overall cost of switching the link, and the dynamic switching damping threshold to generate risk avoidance decision information.

Images