Task Simulation Method, Device and Computer Equipment for Virtual Simulation Platform

Abstract

The present application relates to a task simulation method, device and computer equipment for a virtual simulation platform. The method includes: a data synchronization management module performs data synchronization of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency. Further, online evaluation and offline evaluation are also required to optimize the autoregressive moving average model and the reinforcement learning model for the simulation of the next moment. Using this method can improve the efficiency of data synchronization between heterogeneous simulation platforms.

Description

Technical Field

[0001] The present application relates to the field of simulation technology, and in particular to a task simulation method, device and computer equipment for a virtual simulation platform. Background Art

[0002] With the advancement of technology, virtual simulation technology has been widely used in various fields, including industry, healthcare, and transportation. Traditional single-architecture simulation platforms are unable to meet these demands, leading to the emergence of heterogeneous virtual simulation platforms, consisting of multiple sub-platforms with different hardware, operating systems, and software. Data synchronization is a key challenge in their operation. Due to the diverse tasks of each sub-platform, system load fluctuates significantly. Network latency is unstable due to various factors, packet loss is often caused by interference, and clocks are subject to deviation.

[0003] Traditional task simulation methods rely on fixed synchronization frequencies and simple transmission mechanisms, making them unable to adapt to real-time system changes. Resources are wasted under light loads, while synchronization becomes difficult under heavy loads or poor network conditions, leading to skewed results. These methods fail to meet the high-precision and real-time requirements of modern simulations. Therefore, new solutions are urgently needed to address data synchronization issues and improve task simulation performance. Summary of the Invention

[0004] Based on this, it is necessary to provide a task simulation method, device and computer equipment for a virtual simulation platform to address the above technical problems.

[0005] A task simulation method for a virtual simulation platform is applied to the virtual simulation platform, wherein the virtual simulation platform includes a plurality of heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module. The method includes:

[0006] The data synchronization management module synchronizes the data of each heterogeneous virtual simulation sub-platform according to the pre-controlled data synchronization frequency;

[0007] The supervision module records the real-time simulation status information in each data synchronization, as well as the historical data of data synchronization at multiple historical simulation moments, and constructs a static verification data set based on the historical data;

[0008] Performing online evaluation and offline evaluation on the data synchronization frequency according to the real-time simulation state information and the static verification data set;

[0009] The control strategy of the data synchronization frequency is optimized according to the results of the online evaluation and the offline evaluation, and the task simulation at the next moment is performed according to the optimized control strategy.

[0010] In one embodiment, the control strategy for the data synchronization frequency is generated based on an autoregressive moving average model and a deep deterministic policy gradient algorithm;

[0011] Among them, the autoregressive moving average model generates predicted simulation state information for the next moment based on the simulation state information at the current moment; the deep deterministic policy gradient algorithm determines the optimal data synchronization frequency based on the predicted simulation state information and the simulation state information at the current moment.

[0012] The simulation state information is:

[0013] ; <*

[0014] is the system load index, is the network latency, is the packet loss rate, is the clock deviation, is the current synchronization frequency.

[0015] In one embodiment, it further includes: inputting the simulation state information into a pre-trained autoregressive moving average model, and the output predicted simulation state information for the next moment is:

[0016] ;

[0017] Among them, represents the predicted simulation state information, represents the simulation state information at the current moment.

[0018] In one embodiment, the simulation state information and the predicted simulation state information are used as inputs; the action space is defined as increasing the synchronization frequency, decreasing the synchronization frequency, and maintaining the synchronization frequency; a reward function is defined according to the simulation state information; the deep deterministic policy gradient algorithm is used to select the best action at each time step to adjust the synchronization frequency.

[0019] In one embodiment, it further includes: constructing a shared data flow channel, performing offline evaluation on the autoregressive moving average model and the reinforcement learning model of the deep deterministic policy gradient algorithm according to the static verification data set to obtain offline evaluation information; sending the offline evaluation information to the shared data flow channel; parsing the offline evaluation information in the shared data flow channel, and performing online evaluation on the autoregressive moving average model and the reinforcement learning model according to the parsing result of the offline evaluation information and the real-time simulation state information.

[0020] In one embodiment, it further includes: parsing the offline evaluation information in the shared data stream channel to obtain load error metrics, network latency error metrics, packet loss rate error metrics, and clock deviation; and online evaluating the autoregressive moving average model and the reinforcement learning model according to the load error metrics, network latency error metrics, packet loss rate error metrics, clock deviation, and real-time simulation status information.

[0021] In one embodiment, it is further used to monitor the clock deviation in real time, and when the clock deviation is greater than the threshold, regenerate the data synchronization frequency.

[0022] A task simulation device for a virtual simulation platform, which is applied to a virtual simulation platform. The virtual simulation platform includes multiple heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module. The device includes:

[0023] A synchronization frequency adjustment module for synchronizing data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency;

[0024] A verification module for the supervision module to record real-time simulation status information in each data synchronization, as well as historical data of data synchronization at multiple historical simulation moments, and construct a static verification data set according to the historical data; and online evaluating and offline evaluating the data synchronization frequency according to the real-time simulation status information and the static verification data set;

[0025] A simulation module for optimizing the control strategy of the data synchronization frequency according to the results of the online evaluation and offline evaluation, and thus performing task simulation at the next moment according to the optimized control strategy.

[0026] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] The data synchronization management module synchronizes data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency;

[0028] The supervision module records real-time simulation status information in each data synchronization, as well as historical data of data synchronization at multiple historical simulation moments, and constructs a static verification data set according to the historical data;

[0029] Online evaluating and offline evaluating the data synchronization frequency according to the real-time simulation status information and the static verification data set;

[0030] Optimizing the control strategy of the data synchronization frequency according to the results of the online evaluation and offline evaluation, and thus performing task simulation at the next moment according to the optimized control strategy.

[0031] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0032] The data synchronization management module synchronizes the data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency;

[0033] The supervision module records the real-time simulation status information in each data synchronization, as well as the historical data of data synchronization at multiple historical simulation moments, and constructs a static verification data set according to the historical data;

[0034] Online evaluation and offline evaluation are performed on the data synchronization frequency according to the real-time simulation status information and the static verification data set;

[0035] Optimize the control strategy of the data synchronization frequency according to the results of the online evaluation and offline evaluation, and perform the task simulation at the next moment according to the optimized control strategy.

[0036] The task simulation method, device, computer device and storage medium of the above virtual simulation platform dynamically adjust the data synchronization frequency through real-time status, so as to achieve adaptive optimization of the synchronization strategy. However, the adjustment of the synchronization frequency of multiple heterogeneous virtual simulation sub-platforms is prone to performance instability after multiple time steps. Further, the performance benchmark of the control strategy of the data synchronization frequency is verified offline, and then the effectiveness of the control strategy of the data synchronization frequency is determined during online verification, thus forming a closed loop as a whole. Ensure to provide efficient and reliable data synchronization services in a complex simulation environment, and thus perform the tasks of the virtual simulation platform. Description of the Drawings

[0037] Figure 1 It is a schematic flowchart of the task simulation method of the virtual simulation platform in an embodiment;

[0038] Figure 2 It is a structural block diagram of the task simulation device of the virtual simulation platform in an embodiment;

[0039] Figure 3 It is an internal structure diagram of a computer device in an embodiment. Detailed Embodiments

[0040] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] In one embodiment, as Figure 1As shown, a task simulation method for a virtual simulation platform is provided. The method is applied to the virtual simulation platform, which includes multiple heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module, including the following steps:

[0042] In step 102 , the data synchronization management module receives simulation data of each heterogeneous virtual simulation sub-platform, and collects simulation status information of each heterogeneous virtual simulation sub-platform in real time through the feedback and supervision module.

[0043] The data synchronization management module consists of a central coordination unit, local control units, and a data transmission module. The central coordination unit serves as the global controller, responsible for dynamically adjusting the synchronization frequency based on the status of each simulation system (load, latency, clock deviation, etc.). Local control units: Each simulation system (such as HIL simulation systems, VR simulation systems, and computer virtual simulation systems) has its own local control unit that communicates with the central coordination unit. The local units collect real-time data such as system load and network status and send it to the central unit. The data transmission module: This module is responsible for transmitting data between systems, with the transmission rate and frequency adjusted according to instructions from the central coordination unit.

[0044] The feedback and supervision modules include a delay monitoring module, a system load monitoring module, and a clock synchronization module. The delay monitoring module monitors the delay of each data transmission and provides feedback to the central coordination unit. The system load monitoring module monitors the CPU, memory, network bandwidth, and other loads of each simulation system. The clock synchronization module regularly reports clock deviations between simulation systems to assist in adjusting synchronization strategies.

[0045] Step 104: The data synchronization management module synchronizes the data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency.

[0046] In this step, the system load must be considered. If the synchronization frequency is too high, it may increase the system burden when the system is heavily loaded, causing data processing delays or even system freezes, affecting overall simulation efficiency. For example, when multiple sub-platforms are performing complex calculations simultaneously and the amount of data is large, too frequent data synchronization requests may cause an imbalance in system resource allocation. Network conditions are also a key factor. If the network delay is large or the packet loss rate is high, an excessively high synchronization frequency may cause data transmission to fail or be incomplete, affecting the accuracy and reliability of the data.

[0047] Therefore, the data synchronization management module exchanges data orderly among various heterogeneous sub-platforms according to the pre-controlled data synchronization frequency. At a specified time interval or under specific triggering conditions (determined by the synchronization frequency), the data transmission process is initiated to accurately send the new data generated by each sub-platform to other sub-platforms that need it, thus ensuring the coordinated operation of the entire virtual simulation platform and enabling each sub-platform to perform subsequent simulation operations and processing based on the latest and consistent data, ultimately achieving efficient and accurate virtual simulation tasks.

[0048] Step 106: The supervision module records the real-time simulation status information in each data synchronization, as well as the historical data of data synchronization at multiple historical simulation moments, and constructs a static verification data set based on the historical data.

[0049] Step 108: Online and offline evaluations of the data synchronization frequency are performed based on the real-time simulation status information and the static verification data set.

[0050] The performance benchmark of the control strategy for the offline verification of the data synchronization frequency is verified, and then the effectiveness of the control strategy for the data synchronization frequency is determined during online verification, thus forming a closed loop as a whole.

[0051] Step 110: The control strategy for the data synchronization frequency is optimized according to the results of the online and offline evaluations, and the task simulation for the next moment is performed according to the optimized control strategy.

[0052] In the task simulation method of the above virtual simulation platform, the data synchronization frequency is dynamically adjusted according to the real-time state, so as to realize the adaptive optimization of the synchronization strategy. However, the adjustment of the synchronization frequencies of multiple heterogeneous virtual simulation sub-platforms is prone to performance instability after multiple time steps. Further, the performance benchmark of the control strategy for the data synchronization frequency is verified offline, and then the effectiveness of the control strategy for the data synchronization frequency is determined during online verification, thus forming a closed loop as a whole. Ensure to provide efficient and reliable data synchronization services in a complex simulation environment, so as to perform the tasks of the virtual simulation platform.

[0053] In one embodiment, the control strategy for the data synchronization frequency is generated according to the autoregressive moving average model and the deep deterministic policy gradient algorithm; wherein, the autoregressive moving average model generates the predicted simulation status information for the next moment through the simulation status information at the current moment; the deep deterministic policy gradient algorithm determines the optimal data synchronization frequency through the predicted simulation status information and the simulation status information at the current moment; the simulation status information is:

[0054] ;

[0055] is the system load index, is the network latency, is the packet loss rate, is the clock deviation, is the current synchronization frequency.

[0056] Specifically, the autoregressive moving average model plays an important role in predicting the simulation state information at the next moment in the entire control strategy. It analyzes and fits the dynamic changes of the system by obtaining the simulation state information at the current moment. Specifically, the autoregressive moving average model comprehensively considers the interrelationships and changing trends of various factors in the system at the current moment, thereby generating a prediction of the simulation state information at the next moment. For example, the autoregressive moving average model analyzes the value and changing trend of the system load index (Lt) at the current moment and its association with other factors (such as network delay Dt, packet loss rate Pt, clock deviation Ct, and current synchronization frequency Ft), and based on this, predicts the possible value and changing situation of the system load index at the next moment. Similarly, for other simulation state information such as network delay, packet loss rate, and clock deviation, predictions will be made in a similar manner, and finally a complete set of predicted simulation state information at the next moment is obtained.

[0057] The core function of the deep deterministic policy gradient algorithm is to determine the optimal data synchronization frequency. This algorithm takes the predicted simulation state information generated by the autoregressive moving average model and the actual simulation state information at the current moment as inputs. It extracts features and learns from the above information through a deep neural network, and constructs a policy model that can reflect the relationship between the system state and the optimal synchronization frequency. In this model, the algorithm continuously explores and evaluates the performance of the system under different synchronization frequencies. According to a certain reward mechanism, for example, when the system load is low, the network delay is small, the packet loss rate is low, and the clock deviation is within an acceptable range, a higher reward is given, otherwise a lower reward is given, and the policy is gradually optimized until the optimal data synchronization frequency that can make the system performance reach the best is determined.

[0058] In another embodiment, the simulation state information is input into a pre-trained autoregressive moving average model, and the predicted simulation state information at the next moment is output as:

[0059] ;

[0060] where, represents the predicted simulation state information, represents the simulation state information at the current moment.

[0061] Specifically, the autoregressive moving average model predicts the future system state based on the historical data collected in real time:

[0062] 1. Predict network delay: Predict the possible future peak network delay to adjust the synchronization frequency in advance

[0063] 2. Predict system load: Predict the changing trend of system load to ensure reducing the synchronization frequency when the load increases and avoid system overload.

[0064] 3. Predict clock deviation: Detect the change of clock deviation and pre-adjust the clock synchronization strategy.

[0065] Based on the result of time series prediction, the system can pre-adjust the synchronization frequency. For example:

[0066] 1. If it is predicted that the future network latency will increase, the synchronization frequency can be reduced in advance to reduce the data transmission pressure.

[0067] 2. If it is predicted that the future system load will decrease, the synchronization frequency can be increased to improve the accuracy and real-time performance of synchronization.

[0068] In one embodiment, the simulation state information and the predicted simulation state information are used as inputs; the action space is defined as increasing the synchronization frequency, decreasing the synchronization frequency, and maintaining the synchronization frequency; a reward function is defined according to the simulation state information; the deep deterministic policy gradient algorithm is adopted to select the best action at each time step to adjust the synchronization frequency.

[0069] Each action corresponds to a specific synchronization frequency adjustment strategy. For example:

[0070] 1. When increasing the synchronization frequency, the data synchronization is adjusted from 10 times per second to 20 times per second.

[0071] 2. When decreasing the synchronization frequency, the synchronization frequency is adjusted from 20 times per second to 10 times per second.

[0072] In one embodiment, a shared data stream channel is constructed, and the autoregressive moving average model and the reinforcement learning model are evaluated offline according to the static verification data set to obtain the offline evaluation information; the offline evaluation information is sent to the shared data stream channel; the offline evaluation information in the shared data stream channel is parsed, and the autoregressive moving average model and the reinforcement learning model are evaluated online according to the parsing result of the offline evaluation information and the real-time simulation state information.

[0073] In an embodiment, a shared data stream channel is constructed to ensure real-time sharing and updating of data during offline and online verification processes. After obtaining the offline evaluation information, a message queue (such as Kafka, RabbitMQ) or a stream processing framework (such as Apache Flink) is used to implement real-time data transmission, ensuring low latency and high throughput. It should be noted that since data exchange is relatively frequent during the task simulation process, when setting historical data, the historical data is not updated in real time, but updated at a preset interval. For example, the update time is set to 1 hour, etc. At this time, the network environment of multiple heterogeneous virtual simulation sub-platforms will not change significantly. Therefore, the performance criteria obtained from offline training can meet the heterogeneous simulations of multiple heterogeneous virtual simulation sub-platforms.

[0074] In one of the embodiments, the offline evaluation information includes: load error metrics, network latency error metrics, packet loss rate error metrics, and clock deviation. The above error metrics can adopt RMSE and MAE metrics to analyze the offline evaluation information in the shared data stream channel to obtain load error metrics, network latency error metrics, packet loss rate error metrics, and clock deviation error metrics. Based on the load error metrics, network latency error metrics, packet loss rate error metrics, clock deviation error metrics, and real-time simulation status information, online evaluation of the autoregressive moving average model and the reinforcement learning model is performed.

[0075] In this embodiment, the load error metrics, network latency error metrics, packet loss rate error metrics, and clock deviation error metrics are the performance criteria for the autoregressive moving average model and the reinforcement learning model implemented in this historical segment. During the online evaluation stage, this performance criteria can be used for online evaluation. When the online evaluation result reaches the performance criteria, it indicates that the performance of the autoregressive moving average model and the reinforcement learning model can meet the task simulation. Or by setting weights or other means, the performance criteria for online evaluation are made higher than those for offline evaluation, so as to further optimize the autoregressive moving average model and the reinforcement learning model during the online evaluation process. Or if the online evaluation shows that the performance of the autoregressive moving average model and the reinforcement learning model is lower than the performance criteria, the autoregressive moving average model and the reinforcement learning model also need to be further optimized. It should be noted that through offline and online evaluations, the entire simulation process forms a closed loop, greatly enhancing the reliability of task simulation on the virtual simulation platform.

[0076] In one of the embodiments, the clock deviation is monitored in real time. When the clock deviation is greater than the threshold, clock synchronization is performed by reducing the synchronization frequency until the clock deviation is less than the threshold.

[0077] It should be understood that although Figure 1The steps in the flowchart are shown in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least a part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0078] In one embodiment, as Figure 2 shown, a task simulation device for a virtual simulation platform is provided, which is applied to a virtual simulation platform. The virtual simulation platform includes multiple heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module, and includes: a synchronization frequency adjustment module 202, a verification module 204, and a simulation module 206, where:

[0079] The synchronization frequency adjustment module 202 is used to synchronize the data of each heterogeneous virtual simulation sub-platform according to the pre-controlled data synchronization frequency;

[0080] The verification module 204 is used to supervise the module to record real-time simulation status information in each data synchronization, as well as historical data of multiple historical simulation time data synchronizations, and construct a static verification data set according to the historical data; perform online evaluation and offline evaluation on the data synchronization frequency according to the real-time simulation status information and the static verification data set;

[0081] The simulation module 206 is used to optimize the control strategy of the data synchronization frequency according to the results of the online evaluation and offline evaluation, and thus perform task simulation at the next moment according to the optimized control strategy.

[0082] In one of the embodiments, the control strategy of the data synchronization frequency is generated based on an autoregressive moving average model and a deep deterministic policy gradient algorithm; wherein, the autoregressive moving average model generates predicted simulation status information at the next moment through the simulation status information at the current moment; the deep deterministic policy gradient algorithm determines the optimal data synchronization frequency through the predicted simulation status information and the simulation status information at the current moment; the simulation status information is:

[0083] ;

[0084] is the system load index, is the network delay, is the packet loss rate, is the clock deviation, is the current synchronization frequency.

[0085] In one embodiment, the synchronization frequency adjustment module 202 is further configured to input the simulation status information into a pre-trained autoregressive moving average model, and output the predicted simulation status information for the next moment as:

[0086] ;

[0087] Where, represents the predicted simulation status information, represents the simulation status information at the current moment.

[0088] In one embodiment, the synchronization frequency adjustment module 202 is further configured to use the simulation status information and the predicted simulation status information as the input of the reinforcement learning model; define the action space as increasing the synchronization frequency, decreasing the synchronization frequency, and maintaining the synchronization frequency; define the reward function according to the simulation status information; and use the deep deterministic policy gradient algorithm to select the best action at each time step to adjust the synchronization frequency.

[0089] In one embodiment, the verification module 204 is further configured to construct a shared data stream channel, perform offline evaluation on the autoregressive moving average model and the reinforcement learning model of the deep deterministic policy gradient algorithm according to the static verification data set, and obtain offline evaluation information; send the offline evaluation information to the shared data stream channel; parse the offline evaluation information in the shared data stream channel, and perform online evaluation on the autoregressive moving average model and the reinforcement learning model according to the parsing result of the offline evaluation information and the real-time simulation status information.

[0090] In one embodiment, the offline evaluation information includes: load error index, network delay error index, packet loss rate error index, and clock deviation error index; the verification module 204 is further configured to parse the offline evaluation information in the shared data stream channel to obtain the load error index, network delay error index, packet loss rate error index, and clock deviation; and perform online evaluation on the autoregressive moving average model and the reinforcement learning model according to the load error index, network delay error index, packet loss rate error index, clock deviation, and real-time simulation status information.

[0091] In one embodiment, the synchronization frequency adjustment module 202 is further configured to monitor the clock deviation in real time, and when the clock deviation is greater than the threshold, regenerate the data synchronization frequency.

[0092] For the specific limitations of the task simulation device of the virtual simulation platform, reference can be made to the limitations of the task simulation method of the virtual simulation platform in the foregoing text, which will not be elaborated herein. Each module in the task simulation device of the virtual simulation platform described above can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0093] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 3 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a task simulation method of a virtual simulation platform. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0094] Those skilled in the art can understand that Figure 3 the structure shown in

[0095] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0096] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method in the above embodiment.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0098] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0099] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application shall be subject to the appended claims.

Claims

1. A task simulation method for a virtual simulation platform, characterized in that: Applied to a virtual simulation platform, the virtual simulation platform includes multiple heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module, and the method includes: The data synchronization management module receives simulation data from each heterogeneous virtual simulation sub-platform, and collects simulation status information of each heterogeneous virtual simulation sub-platform in real time through the feedback and supervision module; The data synchronization management module synchronizes data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency; the control strategy of the data synchronization frequency is generated based on an autoregressive moving average model and a deep deterministic policy gradient algorithm; The feedback and supervision module records the real-time simulation status information in each data synchronization, as well as the historical data of multiple historical simulation moment data synchronizations, and constructs a static verification data set based on the historical data; Performing online evaluation and offline evaluation on the data synchronization frequency according to the real-time simulation state information and the static verification data set; Optimizing the control strategy of the data synchronization frequency according to the results of the online evaluation and the offline evaluation, thereby performing task simulation at the next moment according to the optimized control strategy; The deep deterministic policy gradient algorithm determines the optimal data synchronization frequency by predicting simulation state information and the current simulation state information, including: The simulation state information and the predicted simulation state information As input; The action space is defined as increasing synchronization frequency, decreasing synchronization frequency, and maintaining synchronization frequency; Define a reward function based on simulation state information; A deep deterministic policy gradient algorithm is used to select the best action at each time step to adjust the synchronization frequency; Performing online evaluation and offline evaluation on the data synchronization frequency according to the real-time simulation state information and the static verification data set includes: Constructing a shared data stream channel, and performing offline evaluation on the autoregressive moving average model and the reinforcement learning model corresponding to the deep deterministic policy gradient algorithm based on the static verification data set to obtain offline evaluation information; Sending the offline evaluation information to the shared data stream channel; Parsing the offline evaluation information in the shared data stream channel, and performing online evaluation on the autoregressive moving average model and the reinforcement learning model based on the offline evaluation information parsing result and the real-time simulation state information; The offline evaluation information includes: load error index, network delay error index, packet loss rate error index and clock deviation error index; Parsing the offline evaluation information in the shared data stream channel, and performing online evaluation on the autoregressive moving average model and the reinforcement learning model based on the offline evaluation information parsing result and the real-time simulation state information, including: Parsing the offline evaluation information in the shared data stream channel to obtain a load error indicator, a network delay error indicator, a packet loss rate error indicator, and a clock deviation; The autoregressive moving average model and the reinforcement learning model are evaluated online according to the load error index, the network delay error index, the packet loss rate error index, the clock deviation and the real-time simulation state information.

2. The method according to claim 1, characterized in that in, The autoregressive moving average model generates predicted simulation state information at the next moment through the simulation state information at the current moment; the deep deterministic policy gradient algorithm determines the optimal data synchronization frequency through the predicted simulation state information and the simulation state information at the current moment; The simulation status information is: is the system load indicator, It's network latency, is the packet loss rate, is the clock bias, is the current synchronization frequency.

3. The method according to claim 2, characterized in that The autoregressive moving average model generates predicted simulation state information at the next moment through simulation state information at the current moment, including: The simulation state information is input into the pre-trained autoregressive moving average model, and the predicted simulation state information at the next moment is output as: in, Represents the predicted simulation status information, Indicates the simulation status information at the current moment.

4. The method according to any one of claims 2 to 3, characterized in that The method further comprises: The clock deviation is monitored in real time, and when the clock deviation is greater than a threshold, the data synchronization frequency is regenerated.

5. A task simulation device for a virtual simulation platform, used to implement the task simulation method for a virtual simulation platform according to any one of claims 1 to 4, characterized in that: Applied to a virtual simulation platform comprising a plurality of heterogeneous virtual simulation sub-platforms, a data synchronization management module, and a feedback and supervision module, the device comprises: A synchronization frequency adjustment module is used for the data synchronization management module to receive simulation data from each heterogeneous virtual simulation sub-platform, and to collect simulation status information of each heterogeneous virtual simulation sub-platform in real time through the feedback and supervision module, and to synchronize data of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency; A verification module is configured to record the real-time simulation status information and the historical data of data synchronization at multiple historical simulation moments in each data synchronization by the feedback and supervision module, and to construct a static verification data set based on the historical data; and to perform online and offline evaluation of the data synchronization frequency based on the real-time simulation status information and the static verification data set; The simulation module is used to optimize the control strategy of the data synchronization frequency according to the results of the online evaluation and the offline evaluation, so as to perform task simulation at the next moment according to the optimized control strategy.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images