A real-time signaling flow intelligent arrangement system based on queue optimization

Abstract

The application discloses a kind of real-time signaling stream intelligent arrangement systems based on queue optimization, and the application relates to communication network technical field, comprising: multi-dimensional feature perception and fusion module, for real-time acquisition and output the multiple dynamic attribute parameters of signaling;Adaptive scheduling decision module is connected multi-dimensional feature perception and fusion module, for receiving the dynamic attribute parameter and generating scheduling instruction.The real-time signaling stream intelligent arrangement systems based on queue optimization, by introducing the double-loop intelligent architecture of prediction and decision verification, effectively improves the foresight and reliability of signaling stream scheduling.System can make decision by comprehensively multi-dimensional dynamic factor, and after the double inspection of rule base and micro simulation, thereby still maintain the rationality of scheduling strategy and system stability when facing complex burst traffic, guarantee the quality of service of end to end.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication network, in particular to a real-time signaling flow intelligent arrangement system based on queue optimization. BACKGROUND

[0002] The existing scheduling standards generally present a reactive feature, that is, mainly according to the signaling state of the current arrived queue to make decisions, and cannot make a prediction on the traffic mode change that the system may face in the short term. When complex, sudden and internally related signaling flows appear in the network, this passive coping mechanism appears rigid and slow. The system is difficult to adaptively adjust the weight balance between different scheduling factors according to the real-time load change, the logical relationship between the signaling and the predicted traffic trend, resulting in insufficient flexibility and intelligent level of the overall arrangement strategy, which ultimately affects the stable guarantee of end-to-end service performance. Therefore, the problem to be solved by the present system is how to realize an intelligent arrangement mechanism that can integrate multi-dimensional dynamic factors and make forward-looking scheduling. SUMMARY

[0003] The present application aims to provide a real-time signaling flow intelligent arrangement system based on queue optimization to solve the problems raised in the background technology. To solve the above technical problems, the present application provides the following technical scheme: a real-time signaling flow intelligent arrangement system based on queue optimization, comprising:

[0004] A multi-dimensional feature perception and fusion module is used for real-time collection and output of multiple dynamic attribute parameters of signaling;

[0005] An adaptive scheduling decision module is connected to the multi-dimensional feature perception and fusion module, used for receiving the dynamic attribute parameters and generating a scheduling instruction;

[0006] A queue execution module is connected to the adaptive scheduling decision module, used for executing the scheduling instruction;

[0007] The adaptive scheduling decision module internally includes a two-stage decision unit and an internal verification unit;

[0008] The two-stage decision unit is used for generating a preliminary scheduling scheme based on the currently received dynamic attribute parameters;

[0009] The internal verification unit includes a rule library comparison subunit and a micro-simulation deduction subunit;

[0010] The rule library comparison subunit is used for comparing the preliminary scheduling scheme with a reference scheme in a preset rule library, and outputting an optimized scheduling scheme to the micro-simulation deduction subunit according to the comparison result;

[0011] The micro-simulation deduction subunit is used for forward-looking deduction of the optimized scheduling scheme based on a current state snapshot of the system, and feeds back performance index data obtained through deduction to the adaptive scheduling decision module to adjust decision parameters thereof, while outputting a final determined scheduling instruction to the queue execution module.

[0012] It needs to be further explained that after the system is started, the multi-dimensional feature perception and fusion module continuously runs, and real-time collection of a plurality of dynamic attribute parameters of each signaling unit in the input signaling stream is performed. These parameters can include but are not limited to a service type to which the signaling belongs, an emergency level identifier carried by the signaling itself, an identity level of a signaling source device, and a current depth of each processing queue when the signaling arrives. These parameters are collected and integrated into a set of dynamic data sets representing the current system state and signaling features in real time and in parallel, and are output to the adaptive scheduling decision module.

[0013] After the adaptive scheduling decision module receives the above dynamic data set, a two-stage decision unit inside the adaptive scheduling decision module immediately starts working. The unit first analyzes and calculates the input data based on a set of preset initial strategy models, quickly generates a preliminary scheduling scheme for the current queue, and the scheme clearly defines the priority order of the to-be-processed signaling or resource allocation suggestions. Subsequently, the internal inspection unit starts to operate. The rule base comparison subunit first intervenes, which imports the preliminary scheduling scheme into a lightweight simulation environment, which internally builds a plurality of typical business scenario rules and stability constraint conditions refined from historical operation and maintenance experience. The comparison subunit performs a quick trial run of the preliminary scheme in this simulation environment, monitors and evaluates the risks that can be caused if the preliminary scheme is actually executed, such as whether it will cause the processing delay of high-priority signaling to exceed an acceptable range, or whether it will cause a sharp fluctuation in the queue length. If the evaluation result indicates that the risk level is below a preset safety threshold, the preliminary scheme can directly enter the next stage; if the risk level exceeds the threshold, the rule base comparison subunit will trigger the adjustment mechanism of the decision model, and modify the preliminary scheme according to the optimization direction provided by the rule base, thereby generating an optimized scheduling scheme.

[0014] Thereafter, the micro-simulation deduction subunit starts working. It first captures the accurate state snapshot of the system at the current time, including the detailed content of all active queues, the instantaneous load rate of the central processor, the memory occupation, etc. Then, it loads the scheduling scheme optimized through the rule base comparison onto the state snapshot, and performs a short-time range, multi-cycle discrete event simulation deduction. The deduction process aims to prospectively observe the influence of the scheduling scheme on the overall behavior of the system in the next few consecutive working cycles, and record key performance indicator data, such as the average waiting time of signaling during the deduction, the change trend of the overall throughput of the system, etc. These performance indicator data obtained through the deduction are immediately fed back to the core decision logic of the adaptive scheduling decision module. The decision module takes these data as an immediate effect evaluation signal to fine-tune the parameter weights of its internal strategy model, so as to realize online learning and optimization of the decision-making ability. At the same time, the final scheduling instruction confirmed through the deduction is formally sent to the queue execution module.

[0015] The queue execution module reorders the signaling queues in the physical cache or allocates computing resources for specific signaling according to the final scheduling instruction received, thereby completing the scheduling arrangement this time. The whole process from data collection, preliminary decision, internal rule inspection to micro-simulation deduction and feedback optimization forms a continuous, closed-loop automated decision chain.

[0016] Through the inspection and optimization steps containing at least two different mechanisms: rule base comparison and micro-simulation deduction, the system ensures that the scheduling decision is not only based on the current state, but also fully considers the long-term consequences and potential risks of the decision, thereby realizing high reliability, adaptive intelligent arrangement of real-time signaling flow, and effectively overcoming the defects of traditional scheduling methods lacking of foresight and adaptive ability.

[0017] Further, the multi-dimensional feature perception and fusion module comprises a short-term traffic prediction sub-module;

[0018] The short-term traffic prediction sub-module is used to analyze historical signaling flow data, predict the arrival trend and correlation of signaling flow within a set time window in the future, and output the prediction result as a set of dynamic weight factors to the adaptive scheduling decision module.

[0019] Further, the prediction model adopted by the short-term traffic prediction sub-module is an online learning time series analysis model.

[0020] The performance indicator data obtained through the deduction of the micro-simulation deduction subunit are synchronously fed back to the short-term traffic prediction sub-module for correcting the prediction bias.

[0021] Further, the logic compared by the rule base comparison subunit comprises:

[0022] running the preliminary scheduling scheme in a simulation environment, evaluating the high-priority signaling latency and queue state fluctuation risk that it may cause;

[0023] When the evaluation risk exceeds a preset threshold, triggering the strategy adjustment mechanism of the adaptive scheduling decision module to generate the optimized scheduling scheme.

[0024] Further, the process of forward-looking deduction of the micro-simulation deduction subunit includes:

[0025] Constructing a state snapshot based on the current queue state and resource occupation of the system;

[0026] Placing the optimized scheduling scheme under the state snapshot, simulating the subsequent continuous multiple scheduling periods;

[0027] Recording the signaling average processing latency and system throughput efficiency data generated during the simulation process as the performance indicator data.

[0028] Further, after receiving the performance indicator data, the adaptive scheduling decision module uses it as an immediate reward signal to update the strategy model parameters in its internal strategy model, realizing online adaptive optimization of the decision model.

[0029] Further, the dynamic attribute parameters collected by the multi-dimensional feature perception and fusion module at least include the service type identifier of the signaling, the emergency level identifier of the signaling, the identity identifier of the signaling source, and the real-time queue depth.

[0030] Further, the core decision model of the adaptive scheduling decision module adopts a strategy model constructed based on a reinforcement learning framework, and its state space is composed of the dynamic attribute parameters output by the multi-dimensional feature perception and fusion module, and its action space is a set of selectable scheduling strategies.

[0031] Further, the queue execution module reorders or allocates resources to the signaling queue according to the final scheduling instruction.

[0032] Further, the multi-dimensional feature perception and fusion module, the adaptive scheduling decision module, and the queue execution module work cooperatively to form a closed-loop "prediction-decision-verification" process to realize forward-looking intelligent arrangement of real-time signaling flow.

[0033] The application provides a real-time signaling flow intelligent arrangement system based on queue optimization.

[0034] The real-time signaling flow intelligent arrangement system based on queue optimization effectively improves the foresight and reliability of signaling flow scheduling by introducing a double-loop intelligent architecture of prediction and decision verification. The system can make decisions by comprehensively considering multiple dynamic factors and is subjected to double inspection of rule library and micro simulation, thereby maintaining the rationality of scheduling strategy and system stability when facing complex burst traffic, and guaranteeing the end-to-end service quality.

[0035] The real-time signaling flow intelligent arrangement system based on queue optimization has online learning and adaptive optimization capabilities and can continuously adjust the scheduling strategy according to historical decision effects. This self-evolution mechanism reduces the dependence on artificial preset rules and improves the adaptability of the system under different network conditions, thereby providing effective support for the intelligentization and automation of communication network operation. BRIEF DESCRIPTION OF DRAWINGS

[0036] Fig. 1 Fig. 1 is a module interaction schematic diagram of the real-time signaling flow intelligent arrangement system based on queue optimization of the present application;

[0037] Fig. 2 Fig. 4 is a scheduling logic diagram based on service type and urgency of the present application;

[0038] Fig. 3 Fig. 5 is a technical flowchart of micro simulation deduction of the present application;

[0039] Fig. 4 Fig. 6 is a decision flowchart of the adaptive scheduling decision module of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0041] Please refer to Figs. 1 to 4 The present application provides a technical solution: a real-time signaling flow intelligent arrangement system based on queue optimization, comprising:

[0042] A multi-dimensional feature perception and fusion module is configured to collect and output multiple dynamic attribute parameters of signaling in real time.

[0043] An adaptive scheduling decision module is connected to the multi-dimensional feature perception and fusion module and configured to receive the dynamic attribute parameters and generate scheduling instructions.

[0044] A queue execution module is connected to the adaptive scheduling decision module and configured to execute the scheduling instructions.

[0045] wherein the adaptive scheduling decision module internally comprises a two-stage decision unit and an internal verification unit;

[0046] The two-stage decision unit is configured to generate a preliminary scheduling scheme based on the current received dynamic attribute parameters;

[0047] The internal verification unit comprises a rule library comparison subunit and a micro-simulation deduction subunit;

[0048] The rule library comparison subunit is configured to compare the preliminary scheduling scheme with a reference scheme in a preset rule library, and output an optimized scheduling scheme to the micro-simulation deduction subunit according to the comparison result;

[0049] The micro-simulation deduction subunit is configured to perform forward-looking deduction on the optimized scheduling scheme based on a current state snapshot of the system, and feed back performance index data obtained by the deduction to the adaptive scheduling decision module to adjust decision parameters thereof, and output a final determined scheduling instruction to the queue execution module.

[0050] The multi-dimensional feature perception and fusion module comprises a short-term traffic prediction sub-module;

[0051] The short-term traffic prediction sub-module is configured to analyze historical signaling flow data, predict the arrival trend and correlation of signaling flow within a set time window in the future, and output the prediction result as a set of dynamic weight factors to the adaptive scheduling decision module. It needs to be further explained that in the specific implementation process, the short-term traffic prediction sub-module is implemented as follows: the sub-module continuously receives and caches system historical signaling flow data, which are organized in time sequence and attached with signaling type labels. When the prediction process starts, the sub-module first pre-processes the historical data to identify periodic patterns and trend changes therein, such as the traffic law of a specific service within a fixed time interval or the traffic climbing trend caused by a sudden event.

[0052] Subsequently, an online learning time series analysis model is activated. Based on the processed historical data, the model predicts the signaling flow within a set length of time window in the future. The prediction target not only includes the expected arrival amount of different types of signaling, but also analyzes the correlation that may exist between different signaling flows, such as the centralized arrival of some control signaling which often triggers batch requests of subsequent data signaling. The result of the prediction calculation is not a simple traffic value, but is converted into a set of dynamic weight factors. This set of factors quantitatively describes the trend of the relative importance of various scheduling consideration dimensions in a short time in the future, wherein the scheduling consideration dimensions include service priority and delay sensitivity. For example, when it is predicted that high-priority signaling flow will soon surge, the weight factor of the corresponding service type will be correspondingly enhanced.

[0053] This set of dynamic weighting factors is then output to the adaptive scheduling decision module as one of its key inputs for initial decision-making, expanding the decision-making basis from static parameters reflecting the current state to include dynamic and predictive information. Furthermore, performance index data from the micro-simulation deduction subunit is also fed back to the short-term traffic prediction submodule. This feedback data includes information on the difference between actual and predicted traffic in the previous decision cycle. The prediction submodule uses this difference information, through its built-in online learning mechanism, to adjust the model's internal parameters, thereby correcting the accuracy of subsequent predictions and forming a continuously improving prediction loop. This implementation ensures that the scheduling system can orchestrate based on traffic predictions that continuously approach reality, improving the foresight and adaptability of the decision-making process.

[0054] The short-term traffic prediction submodule uses an online learning time series analysis model for prediction.

[0055] The performance index data obtained from the micro-simulation deduction subunit are synchronously fed back to the short-term flow prediction submodule to correct its prediction deviation.

[0056] It should be further explained that, in the specific implementation process, an adaptive correction mechanism for the prediction model is involved. The core of the online learning time series analysis model used in this short-term traffic prediction submodule lies in its ability to continuously adjust its prediction logic based on actual system operation feedback. After completing the traffic prediction for a time window, the model does not terminate its task but enters a state of pending verification. When the corresponding scheduling decisions are simulated and applied to the system, the system records the actual arrival of signaling flows within that time window. The difference between these actual data and the previously predicted data is quantified as a prediction deviation signal.

[0057] The prediction deviation signal is fed back to the prediction submodule in real time. The online learning mechanism is then activated, and its processing includes case classification: if the deviation signal indicates that the predicted value is consistently higher or lower than the actual value, the learning mechanism will adjust the model's basic trend judgment parameters; if the deviation exhibits irregular fluctuations, the learning mechanism may focus on adjusting the model's sensitivity to random disturbances. This adjustment process is based on an incremental learning algorithm, where model parameters are updated in small iterations rather than being completely retrained, thus ensuring that the model can adapt to gradual changes in traffic patterns while avoiding over-adjustment due to a single sudden event.

[0058] Through this closed loop path that uses the actual effect data after the micro-simulation deduction as the calibration signal and continuously acts on the prediction model, the system makes the traffic prediction ability no longer static and offline, but dynamic and online self-optimization process. This implementation detail ensures that the prediction result can gradually approach the real network traffic behavior, providing more and more reliable forward-looking basis for subsequent scheduling decisions, which constitutes the key foundation of the intelligence of the whole system.

[0059] The logic of the rule base comparison sub-unit includes:

[0060] The preliminary scheduling scheme is run in a simulation environment to evaluate the high-priority signaling latency and queue state fluctuation risk that it may cause;

[0061] When the evaluation risk exceeds the preset threshold, the strategy adjustment mechanism of the adaptive scheduling decision module is triggered to generate an optimized scheduling scheme.

[0062] It needs to be further explained that in the specific implementation process, the internal logic judgment and execution process of the rule base comparison sub-unit is implemented as follows: The preset rule base in the sub-unit is not a simple static list, but a collection containing multiple constraint conditions and optimization targets. These rules are derived from the refinement of typical scenarios in historical operation data, such as latency constraints for ensuring key business link, queue length fluctuation constraints for maintaining system overall stability, etc.

[0063] When the preliminary scheduling scheme is generated, the rule base comparison sub-unit loads it into a simplified simulation environment for deduction analysis. The deduction process simulates the behavior of the system in a short period after the execution of the scheme. The evaluation logic first focuses on high-priority signaling, calculates the time interval from entering the queue to starting to be processed in the simulation environment, and compares this simulated latency with the maximum allowed latency threshold set for this type of signaling in the rule base. At the same time, the evaluation logic monitors the change of the queue depth during the simulation process, calculates the fluctuation amplitude, and compares it with the stability threshold defined in the rule base. Based on the comparison results, the system makes a logical judgment: if the simulated latency is not over the limit and the queue fluctuation is within an acceptable range, it is determined that the risk is controllable, and the preliminary scheduling scheme can be directly passed to the next stage. If any evaluation indicator, such as the simulated latency of high-priority signaling, exceeds the corresponding threshold, it is determined that there is a risk, and the strategy adjustment mechanism is immediately triggered.

[0064] The adjustment mechanism is not a simple replacement, but a targeted correction according to the preset optimization strategy in the rule base, for example, dynamically increasing the scheduling weight of the business type to which the out-of-limit signaling belongs or inserting a specific scheduling gap to smooth the queue fluctuation, thereby generating an optimized scheduling scheme that meets the basic safety requirements of the rule base. This implementation detail provides a preliminary optimized and lower risk input scheme for subsequent more complex micro-simulation deduction by introducing a rule-based inner loop for quick inspection and correction, improving the efficiency and reliability of the entire decision-making process.

[0065] The process of forward-looking deduction by the micro-simulation deduction subunit includes:

[0066] A state snapshot is constructed based on the current queue state and resource occupation of the system;

[0067] The optimized scheduling scheme is placed in the state snapshot, and the subsequent continuous scheduling periods are simulated;

[0068] The average processing delay and system throughput efficiency data generated during the simulation are recorded as performance indicator data.

[0069] It needs to be further explained that in the specific implementation process, the implementation process of forward-looking deduction by the micro-simulation deduction subunit is as follows: after receiving the optimized scheduling scheme from the rule base comparison link, the subunit will first trigger a system state snapshot capture mechanism. This mechanism will instantaneously record the key real-time state of the system at the current time, including but not limited to the specific number and attributes of the signaling waiting for processing in each physical queue, the current load rate of each core of the central processor, the buffer size being occupied in the memory, and the instantaneous throughput of the network interface. This state snapshot strives to reflect the true and complete internal situation of the system at the decision moment.

[0070] Next, the micro-simulation deduction engine is activated. The engine loads the optimized scheduling scheme as an input instruction set on the captured system state snapshot, constructing a highly realistic but completely controllable simulation scenario. The deduction is not only one step, but also simulates the execution of subsequent continuous complete scheduling periods. In each simulation period, the engine will strictly process the signaling in the queue according to the logic of the scheduling scheme, while simulating the random arrival of new signaling, the operation time consumption of the processor, and the off-queue process after the completion of signaling processing. The entire simulation process is based on the principle of discrete event simulation.

[0071] During the deduction process, the engine continuously tracks and records a series of key performance indicators. For example, it counts the average waiting time of all processed signaling in the queue from the beginning to the end of the simulation, as well as the total number of successfully processed signaling by the system during the entire simulation period and the throughput efficiency reflected by the time ratio. These data are collected and temporarily stored in real time. When the preset number of simulation cycles is completed, the deduction process terminates. At this time, the recorded performance indicators such as average latency and throughput efficiency are summarized to form a predictive evaluation report on the possible effects of the scheduling scheme in the system in the near future. This evaluation report, which is the performance indicator data, will be fed back to the adaptive scheduling decision module to provide crucial data support for its final decision and self-learning based on forward-looking simulation.

[0072] This implementation detail enhances the ability to predict the long-term impact of scheduling decisions by introducing multi-cycle, system state-based fine deduction, upgrading the verification of scheduling decisions from static, single-point evaluation to dynamic, system-level simulation.

[0073] After receiving the performance indicator data, the adaptive scheduling decision module uses it as an immediate reward signal to update its internal strategy model parameters, achieving online adaptive optimization of the decision model. It is further noted that in the specific implementation process, the adaptive scheduling decision module uses the feedback data for online optimization: when the performance indicator data generated by the micro-simulation deduction sub-unit is fed back to the decision module, the processing logic inside the module is immediately started. These performance indicators, such as average latency and throughput efficiency, are converted into a quantitative immediate reward signal by the evaluation function preset in the decision module. The value of this reward signal reflects the overall performance of the evaluated scheduling scheme in the simulation environment.

[0074] The decision module is a strategy model based on the reinforcement learning framework, which uses the received immediate reward signal as the key evaluation basis for the effectiveness of this decision cycle. The updating process of the model parameters follows the following logic: if the reward signal is positive, indicating that the optimized scheduling scheme performs well in the deduction, such as reduced latency and stable throughput, the model will tend to strengthen the decision logic used to generate the scheme, i.e., fine-tune the connection weights inside its neural network, so that in the future when similar system states and signaling characteristics are encountered, the probability of producing similar scheduling decisions increases. Conversely, if the reward signal is negative, indicating that the scheme has deficiencies, the model will weaken the decision path that led to this result.

[0075] This parameter update is a continuous and incremental process rather than a periodic batch adjustment. Each cycle from decision generation to micro-simulation verification to feedback update constitutes a complete learning cycle. Through a large number of such cycles, the model gradually accumulates experience of which scheduling strategy is more effective under different system states and signaling loads. This implementation makes the scheduling strategy not fixed and not simply a rule stack, but can evolve with the evolution of the actual running environment of the system, thereby dynamically improving its adaptability and effectiveness under different working conditions, realizing a fundamental change from static configuration to dynamic self-learning, and constituting a continuous guarantee for the intelligent arrangement capability of the system.

[0076] The dynamic attribute parameters collected by the multi-dimensional feature perception and fusion module at least include a signaling service type identifier, a signaling emergency level identifier, a signaling source identifier, and a real-time queue depth. It needs to be further explained that in the specific implementation process, the multi-dimensional feature perception and fusion module collects dynamic attribute parameters in the following implementation manner: the module continuously monitors signaling streams through multiple detection points arranged inside the system, and whenever a new signaling arrives, the module synchronously analyzes the signaling header and load content to extract key attributes.

[0077] The signaling service type identifier is obtained by analyzing the preset protocol type field or service category code, and the identifier is used to distinguish the business category to which the signaling belongs, such as session control, mobility management, or emergency alarm. The signaling emergency level identifier is determined by reading the specific priority flag bit or service quality level label carried in the signaling, and the identifier directly reflects the urgency requirement for processing the signaling. The signaling source identifier is confirmed by verifying the source address digital signature or access network device certificate of the signaling, to judge the credibility and importance level of the signaling source.

[0078] The real-time queue depth is directly obtained from the module by querying the cache counter of each processing queue at regular intervals, representing the current instantaneous load pressure of the system. After these parameters are collected in parallel, the fusion logic performs standardization and normalization processing to form a unified and structured dynamic data set, providing a comprehensive and real-time state perception basis for subsequent intelligent decision-making.

[0079] The core decision model of the adaptive scheduling decision module adopts a strategy model based on a reinforcement learning framework, and the state space of the strategy model is composed of dynamic attribute parameters output by the multi-dimensional feature perception and fusion module, and the action space is a set of selectable scheduling strategies. It needs to be further explained that the internal decision mechanism of the strategy model based on the reinforcement learning framework is implemented in the following manner: the model constructs a comprehensive state vector after normalization processing of the dynamic attribute parameter set output by the multi-dimensional feature perception and fusion module in real time, which fully characterizes the current signaling load condition, resource pressure, and internal characteristics of the signaling stream of the system.

[0080] The decision-making process of the model begins with the analysis of the current state vector. The policy model, which is a pre-trained neural network with online learning capability, receives the state vector as input. The internal calculation layers perform nonlinear transformation and feature extraction on the input information, and finally generate a probability distribution corresponding to all available scheduling strategies in the output layer. The action space is composed of these specific scheduling strategies, such as "prioritize processing signaling of type A", "allocate additional resources for signaling source level B", or "use weighted round robin to balance queue load", and other basic scheduling actions and their combinations. The model determines the scheduling scheme to be used in the current period by sampling or selecting the action with the highest probability based on the output probability distribution.

[0081] The entire decision-making process is a learning cycle that continuously interacts with the system environment. After the model executes the selected action, i.e., generates the preliminary scheduling scheme, the scheme undergoes rule library comparison and micro-simulation deduction for inspection and evaluation. The performance indicators generated by the deduction are converted into reward signals, such as positive rewards for lower latency and negative rewards for queue overflow. This reward signal, together with the new system state, constitutes a complete experience data. The model uses these experience data to adjust its neural network weights through optimization algorithms such as gradient descent, aiming to increase the probability of selecting actions that can achieve higher cumulative rewards in a specific state. Through massive interactive learning, the model gradually masters how to balance multi-dimensional factors under different complex working conditions, thereby autonomously generating efficient and robust scheduling strategies, realizing a fundamental change from relying on fixed rules to having adaptive optimization capabilities.

[0082] The queue execution module reorders or allocates resources to the signaling queue based on the final scheduling instructions. It is worth noting that in the specific implementation process, the queue execution module operates as follows based on the final scheduling instructions: the module continuously monitors the output instruction channel of the adaptive scheduling decision module, and when it receives the final scheduling instructions that have undergone double verification and optimization, it immediately starts the execution process. The execution process first analyzes the instructions to identify the specific operation intent implied in the instructions, such as the need to adjust the order of specific signaling in the queue or the need to reserve processing resources for a certain type of signaling.

[0083] For queue reordering operations, the execution module directly manipulates the data pointers in the physical queues or logical queues according to the priority adjustment rules specified in the instructions, changing the processing sequence of the signaling units. For resource allocation operations, the execution module interacts with the system's resource manager to adjust the allocation proportion of resources such as computing cores, memory buffers, or network bandwidth among different signaling processing threads according to the instructions. All operations are completed in an atomic transaction manner to ensure the instantaneous integrity and consistency of the queue state switching, avoiding signaling loss or state confusion during the adjustment process. After the execution is completed, the module will feedback the operation result state to the system, thus completing the closed loop from intelligent decision to physical execution, ensuring that the arrangement strategy can be accurately implemented.

[0084] The multi-dimensional feature perception and fusion module, the adaptive scheduling decision module, and the queue execution module work together to form a closed-loop "prediction-decision-verification" process to realize the forward-looking intelligent arrangement of real-time signaling flow. It needs to be further explained that in the specific implementation process, the closed-loop process formed by the cooperation of the whole system is reflected in the continuous data flow and feedback interaction between modules. The multi-dimensional feature perception and fusion module, as the starting point of the process, uninterruptedly collects and outputs dynamic data reflecting the real-time state of the system. These data are received by the adaptive scheduling decision module to start its internal double-check decision-making process including preliminary generation, rule comparison, and micro-simulation deduction.

[0085] In this process, the preliminary decision first undergoes rapid risk screening and correction based on the rule library, and then the optimized scheme undergoes multi-cycle forward-looking deduction evaluation based on the system state snapshot. The performance data generated by the deduction is not only used for the final scheduling instruction, but more importantly, this part of data is immediately fed back to the core strategy model of the adaptive scheduling decision module for online fine-tuning of its parameters, and also fed back to the short-term traffic prediction submodule for correction of its prediction algorithm. Finally, the confirmed scheduling instruction is implemented by the queue execution module, thereby affecting the actual running state of the system.

[0086] This process from perception to decision, from verification to execution, and from execution effect feedback to perception and decision starting point runs repeatedly. It makes the system no longer a static pipeline that passively responds to the signaling flow, but an organic whole that can learn from history and real-time interaction, can foresee the short-term future state, and can dynamically optimize its scheduling strategy accordingly. This closed-loop, learning and forecasting-capable "prediction-decision-verification" process is the core mechanism to realize the forward-looking intelligent arrangement of real-time signaling flow, ensuring the adaptability and robustness of the system in the face of complex and variable network environment.

[0087] It needs to be further explained that in the implementation process of the real-time signaling flow intelligent arrangement system based on queue optimization described in the application, it is realized through a series of closely coordinated steps. The operation of the whole system starts from the continuous perception of the multi-dimensional characteristics of the signaling flow. The perception module built in the system will analyze each input signaling in real time, extract its inherent attribute information, which includes but is not limited to the business type represented by the signaling, the emergency degree marked by the signaling itself, the identity of the signaling source device and the current length of each processing queue in the system at the signaling arrival time. After all these parameters are synchronously collected and standardized, a comprehensive dynamic data set is formed, which fully describes the real-time load condition and the characteristics of the signaling flow faced by the system.

[0088] Next, the core decision mechanism of the system starts to work: an adaptive scheduling decision maker based on online learning algorithm receives the above dynamic data set. The decision maker first uses its internal strategy model to quickly generate a preliminary signaling processing sequence scheme based on the current data. However, this preliminary scheme is not directly adopted. The system designs a key double-checking process to improve the robustness and foresight of the decision. The first double-checking is to compare the preliminary scheme with a preset rule base. The rule base defines a series of basic criteria that need to be followed for the stable operation of the system, such as ensuring the upper limit of the time delay of high-priority signaling and preventing excessive fluctuation of queue length. The comparison process is carried out in a simplified simulation environment to evaluate whether the preliminary scheme may violate these core rules. If the evaluation finds potential risks, the system will automatically adjust the preliminary scheme according to the guidance of the rule base to generate an optimized alternative scheme.

[0089] The second double-checking launched subsequently is more detailed. The system will capture the accurate state snapshot of all key components at the current time, including queue content, processor load, memory occupation, etc., to build a highly simulated simulation environment. The scheduling scheme optimized by the first double-checking is placed in this environment to deduce its execution effect in the future continuous number of working periods. This micro-simulation process can predict the influence of the scheme on the overall performance of the system, such as the change trend of the average processing delay of the signaling and the system throughput efficiency. The performance prediction data generated after the deduction is immediately fed back to the adaptive scheduling decision maker. The decision maker uses these data as a kind of learning signal to fine-tune the parameters of its internal strategy model, so that its subsequent decisions can better tend to optimize the overall performance of the system. At the same time, the deduced scheduling instruction is determined to be feasible and is finally confirmed.

[0090] Finally, the confirmed scheduling instructions are sent to the queue execution unit. Based on the specific content of the instructions, this unit reorders the signaling in the physical queue or adjusts the resource allocation strategy, thereby translating intelligent decision-making into actual scheduling actions. The entire process, from feature perception, preliminary decision-making, rule verification, simulation deduction to learning optimization and instruction execution, forms a complete, closed-loop automated intelligent chain. Through this integration of multi-level verification and online learning mechanisms, the system achieves a transformation from passive response to proactive prediction and optimization of real-time signaling streams, effectively improving the intelligence level and reliability of signaling scheduling in complex network environments.

[0091] The core of this invention lies in the working mechanism of its adaptive scheduling decision module: the decision-making basis of this module is a comprehensive state vector, which is constructed from real-time data output by the multi-dimensional feature perception and fusion module. State vector S t It can be represented as:

[0092] S t =(T1, T2, ..., T m P1, P2, ..., P n ;Q depth Res util ); where S t The system's overall state vector at time t, where t represents the time node of the current scheduling decision, T1 to T2. m The number of arrivals of m different service types of signaling within a specific time window in the past; P1~P n Q: The number of signaling entries of n different priority levels in the current system queue; depth : The current depth of the system's critical business queue, Res util : Current utilization of the system's core processing resources, which include CPU and bandwidth, with values ​​ranging from [0, 1]; State vector S t The construction integrates dynamic traffic characteristics with static system states.

[0093] The decision-making module internally employs a parameterized policy function π(a|S) t ;θ), where π(·): parameterized scheduling policy function; a: optional scheduling action, belonging to action space A, such as "prioritize processing signaling of priority X" or "allocate resources Z to service Y"; S t θ: Current system state vector, i.e., input variable; θ: Set of parameters for the policy model, core parameters to be optimized, such as neural network weights, decision tree node thresholds, etc.; The policy function means: given the current state S tand model parameters θ. The action space A includes basic scheduling instructions such as "handle signaling with priority X first", "allocate extra resource Z for traffic type Y", and their combinations.

[0094] The decision flow introduces an online learning mechanism based on reward signals: when a scheduling action a t is executed, i.e. after subsequent verification and implementation, the system observes a new system state S t+1 at the next decision point t+1 and calculates an immediate reward R t . The design of this reward function R t takes into account the scheduling effect, and its formula is:

[0095] R t = w1 · (-ΔDelay high ) + w2 · (ΔThroughput) - w3 · (ΔQ variance );

[0096] where R t : the immediate reward value obtained after executing action a t at time t, the larger the value, the better the action effect; w1, w2, w3: preset weight coefficients, non-negative real numbers, used to balance the importance of different performance indicators, satisfying w1 + w2 + w3 = 1 or adjusted according to business needs; ΔDelay high : the average delay change of high-priority signaling from t to t+1, where Δ<0 indicates a decrease in delay, corresponding to a positive reward contribution; ΔThroughput: the change in system throughput from t to t+1, where Δ>0 indicates an increase in throughput, corresponding to a positive reward contribution; ΔQ variance : the change in queue length fluctuation from t to t+1, Δ<0 indicates that the queue is more stable, corresponding to a positive reward contribution; the quantitative value of reward R t directly reflects the good or bad of scheduling action a t in state S t .

[0097] The update of policy model parameters θ is the core of system implementation adaptation. The system uses the policy gradient method for optimization, and a basic form of its update rule is: θ ← θ + α · ∇ θ logπ(a t | S t ; θ) · G t ; where θ ← θ +...: parameter update symbol, indicating "assign the right side calculation result to the left side θ"; α: learning rate, positive real number, controls the step size of parameter update, value range [10 -5 , 10 -2, avoid oscillation caused by too large step size or slow convergence caused by too small step size; ∇ θ logπ(a t |S t ;θ):the log of the gradient of the policy function with respect to the parameters θ, indicating how to adjust θ to increase the probability of selecting action a t in state S t ; G t is the cumulative future discounted reward calculated from time t, representing the long-term value of the current decision; a t : the scheduling action actually executed at time t; by continuously updating the parameters θ according to the above rules, the policy model gradually learns what scheduling action should be taken in what system state to achieve long-term optimal performance.

[0098] In addition, the implementation details of the short-term traffic prediction sub-module can be further specified. This module can use time series prediction methods such as autoregressive integrated moving average models. The basic idea is to use historical data Y t , Y t-1 , Y t-2 ,... to predict future values Y t+h ; where Y t-k represents the signaling flow observation value at time t-k; prediction output: Y t+h : the predicted signaling flow value at time t+h based on historical data, h is the prediction step.

[0099] The model makes predictions by identifying trends and seasonal patterns in the data. The prediction results, such as the expected arrival intensity I forecast of a certain type of signaling in the future, are normalized to a dynamic weight factor W forecast between zero and one, and integrated into the construction of the state vector S t , or directly as an additional input to the policy function π, so that the decision has foresight;

[0100] where the dynamic weight conversion: W forecast = Norm(I forecast ), where: I forecast : the expected future arrival intensity of a certain type of signaling; Norm(·): normalization function, such as Min-Max normalization, so that W forecast ∈ [0, 1]; W forecast : the prediction weight factor finally integrated into the state vector S t or the policy function π.

[0101] The operation of the micro-simulation deduction sub-unit relies on the discrete event simulation technology. It maintains a list of future events, and accurately calculates the performance index output of the system under a specific scheduling scheme by simulating the progress of events such as signaling arrival, scheduler decision, signaling processing completion and departure on the virtual timeline. This event-based simulation can effectively capture the randomness and non-linear characteristics of queue behavior in the signaling flow.

[0102] By deeply integrating reinforcement learning, time series prediction and discrete event simulation, an intelligent orchestration system with self-optimization and forward-looking decision-making capability is constructed.

[0103] By introducing a double-loop intelligent architecture of prediction and decision verification, the forward-looking and reliability of signaling flow scheduling are effectively improved. The system can make decisions based on multiple dynamic factors and be verified by the rule base and micro-simulation, so that the rationality of the scheduling strategy and the stability of the system are maintained when facing complex burst traffic, and the end-to-end service quality is guaranteed.

[0104] In addition, the system has online learning and adaptive optimization capabilities, and can continuously adjust the scheduling strategy according to historical decision effects. This self-evolution mechanism reduces the dependence on artificial preset rules and improves the adaptability of the system under different network conditions, providing effective support for the intelligentization and automation of communication network operation.

[0105] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0106] Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A real-time signaling flow intelligent orchestration system based on queue optimization, characterized in that, The application relates to a multi-dimensional feature perception and fusion module for collecting and outputting multiple dynamic attribute parameters of signaling in real time. An adaptive scheduling decision module is connected to the multi-dimensional feature perception and fusion module and is used for receiving the dynamic attribute parameters and generating scheduling instructions. A queue execution module is connected to the adaptive scheduling decision module and is used for executing the scheduling instructions. The adaptive scheduling decision module comprises a two-stage decision unit and an internal inspection unit. The two-stage decision unit is used for generating a preliminary scheduling scheme based on the currently received dynamic attribute parameters. The internal inspection unit comprises a rule library comparison subunit and a micro-simulation deduction subunit. The rule library comparison subunit is used for comparing the preliminary scheduling scheme with a reference scheme in a preset rule library, and outputting an optimized scheduling scheme to the micro-simulation deduction subunit according to a comparison result. The micro-simulation deduction subunit is used for performing forward-looking deduction on the optimized scheduling scheme based on a current state snapshot of the system, feeding back performance index data obtained through the deduction to the adaptive scheduling decision module to adjust decision parameters of the adaptive scheduling decision module, and outputting a finally determined scheduling instruction to the queue execution module. The multi-dimensional feature perception and fusion module comprises a short-term traffic prediction sub-module.

2. The real-time signaling flow intelligent arrangement system based on queue optimization according to claim 1, characterized in that: The short-term traffic prediction sub-module is used for analyzing historical signaling flow data, predicting an arrival trend and a correlation of signaling flow in a future set time window, and outputting a prediction result as a set of dynamic weight factors to the adaptive scheduling decision module. The prediction model used by the short-term traffic prediction sub-module is an online learning time series analysis model.

3. The real-time signaling flow intelligent arrangement system based on queue optimization according to claim 2, characterized in that: The performance index data obtained through the deduction of the micro-simulation deduction subunit is synchronously fed back to the short-term traffic prediction sub-module to correct a prediction deviation. The logic of the rule library comparison subunit for comparison comprises the following steps:

4. The real-time signaling flow intelligent arrangement system based on queue optimization according to claim 1, characterized in that: The preliminary scheduling scheme is run in a simulation environment, and high-priority signaling time delay and queue state fluctuation risks possibly caused by the preliminary scheduling scheme are evaluated. When the evaluation risks exceed a preset threshold, a strategy adjustment mechanism of the adaptive scheduling decision module is triggered to generate the optimized scheduling scheme. The process of forward-looking deduction performed by the micro-simulation deduction subunit comprises the following steps:

5. The real-time signaling flow intelligent orchestration system based on queue optimization according to claim 1, characterized in that: A state snapshot is constructed based on a current queue state and resource occupation condition of the system. The optimized scheduling scheme is placed in the state snapshot, and a subsequent continuous multiple scheduling periods are simulated and run. Average signaling processing time delay and system throughput efficiency data generated in the simulation and running process are recorded as the performance index data. After receiving the performance index data, the adaptive scheduling decision module takes the performance index data as an instant reward signal to update strategy model parameters in the adaptive scheduling decision module, so that online adaptive optimization of a decision model is realized.

6. The real-time signaling flow intelligent orchestration system based on queue optimization according to claim 5, characterized in that: The dynamic attribute parameters collected by the multi-dimensional feature perception and fusion module at least comprise a service type identifier of signaling, an emergency degree identifier of signaling, an identity identifier of a signaling source and a real-time queue depth.

7. The real-time signaling flow intelligent orchestration system based on queue optimization according to claim 1, characterized in that: ​ 8. The real-time signaling flow intelligent arrangement system based on queue optimization according to claim 1, characterized in that: The core decision model of the adaptive scheduling decision module adopts a policy model constructed based on a reinforcement learning framework, a state space of the policy model is constituted by dynamic attribute parameters output by the multi-dimensional feature perception and fusion module, and an action space is a scheduling policy set.

9. The real-time signaling flow intelligent arrangement system based on queue optimization according to claim 1, characterized in that: The queue execution module performs reordering or resource allocation operations on the signaling queue according to the final scheduling instruction. 10.The queue optimization-based real-time signaling flow intelligent arrangement system according to any one of claims 1 to 9, characterized in that: The multi-dimensional feature perception and fusion module, the adaptive scheduling decision module and the queue execution module work cooperatively to form a closed-loop "prediction-decision-verification" process.

Images