Flow generation deployment method, system and device based on simulation network and medium

Abstract

The invention discloses a flow generation deployment method, system and device based on a simulation network, and a medium. The method comprises the following steps: generating a corresponding flow generation and receiving service on the simulation network based on configuration; extracting a traffic time characteristic of the traffic data set based on model fitting, wherein the traffic generation service generates traffic according to the traffic time characteristic and sends the traffic to a traffic receiving service; accessing a flow generation service or a flow receiving service on different edge simulation network devices according to user configuration to realize a multi-region flow service; and integrating the traffic services and optimizing the deployment of the two traffic services on the cluster according to the accessed and sent objects. According to the invention, the deployment of the traffic service on the cluster can be optimized to improve the network transmission performance, the common traffic service is integrated, the resource occupation is reduced, the task execution efficiency is improved, and a feasible and efficient traffic generation deployment scheme is provided for multiple users to generate large-scale traffic in a simulation network scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network intelligence, in particular to a self-organizing network scene sensing method based on a neighbor node table, a device and a medium. BACKGROUND

[0002] With the continuous growth of network scale and the continuous deepening of computer network research, it is increasingly important to study the transmission characteristics of network traffic, which is of research significance for network planning and design, network performance optimization, network security, and application behavior analysis. Traditional traffic generation includes constructing transport layer packets, injecting simulated links, and generating traffic using traditional traffic distribution models, or simulating session scenarios using client-server interaction. In network research, it is more common to use a traffic generator based on scripts, records, or configuration patterns to create network packets, which can simulate the data packets generated in a real production environment, but the generated traffic packets do not come from actual application dialogues. In order to simulate real network traffic, servers are deployed in multiple locations to implement spatial distribution of traffic, which also brings problems such as high cost, difficult maintenance, and network opacity.

[0003] With the development of network intelligence technology, it is increasingly popular to use computer technology to simulate real network environments and behaviors, and simulation networks that can reflect real network characteristics have been proposed. They can create virtual network environments and simulate various network devices, protocols, and applications, and use virtualization technology to avoid the influence of physical factors, allowing the topology of the network to be changed to explore the potential characteristics of the network. The deployment and management of resources in a simulation network are different from those in a real scenario. In a real network environment, each role of the network corresponds to an actual physical device, while in a simulation network, virtual network devices are used to simulate the network, which makes it possible to perform system-level resource management and scheduling to reduce the cost of the simulation network, improve the efficiency of simulation, and improve the utilization rate of physical resources. However, this also presents new challenges. The simulation network scenario is different from the real network environment, and it is particularly important to reflect the characteristics of real network traffic in a simulation network. Currently, the generation of traffic in a simulation network is still in the exploratory stage, and there is no solution that is efficient, realistic, and scalable. Although existing research has made some progress in network traffic generation, there are still the following technical problems: 1. Low traffic generation efficiency: Existing methods mostly use software simulation to generate network traffic, which is difficult to meet the requirements of large-scale network simulation for traffic generation efficiency.

[0004] 2. Insufficient traffic realism: The network traffic generated by existing methods differs greatly from real network traffic, and it is difficult to accurately reflect the traffic characteristics in a real network environment.

[0005] 3. Poor scalability: Existing methods are designed for specific scenarios, lack of generality and scalability, and are difficult to adapt to different network simulation needs. SUMMARY

[0006] The purpose of the present application is to solve the problems of low efficiency, lack of authenticity, difficulty in accurately reflecting the traffic characteristics in real network environment, lack of generality and scalability, and difficulty in adapting to different network simulation needs in the prior art, and to provide a traffic generation deployment method, system, device and medium based on simulation network.

[0007] To achieve the above-mentioned purpose of the application, the first aspect of the present application provides a traffic generation deployment method based on simulation network, comprising: Generating corresponding traffic generation service and traffic receiving service on the simulation network based on the configuration file generated based on the simulation network topology and traffic demand provided by the user; Based on model fitting, the traffic time characteristics of the preset or user-provided traffic data set are extracted, and the traffic generation service generates traffic according to the traffic time characteristics and sends it to the traffic receiving service; According to the user configuration, access the corresponding traffic generation service or traffic receiving service on different edge simulation network devices to realize multi-region traffic service; According to the access and sending object, the traffic generation service and the traffic receiving service are integrated and optimized respectively, and the deployment of the two traffic services on the cluster is optimized.

[0008] Preferably, the configuration file generated based on the simulation network topology and traffic demand provided by the user generates corresponding traffic generation service and traffic receiving service on the simulation network, comprising: Creating a traffic generator and a receiving service corresponding to the traffic generation service and the traffic receiving service; Configure the open port and the network card to create a network connection between the traffic generator, the receiving service and the simulation network.

[0009] Preferably, the traffic time characteristics of the preset or user-provided traffic data set are extracted based on model fitting, and the traffic generation service generates traffic according to the traffic time characteristics and sends it to the traffic receiving service, comprising: After the format check and preprocessing of the traffic data set, input it into the autoregressive model, and the autoregressive model is as follows: Consider a long connection with n data packets in the current time slot, and each data packet is sent with a certain time interval; Indicates the size of the i-th data packet; denotes the time interval between the (i-1)th packet transmission and the ith packet transmission, , the correlation coefficient of the time interval, the number of previous transmitted packet lengths considered when fitting the packet model, the number of previous transmitted time intervals considered when fitting the time interval model, , are the constant terms of the two models respectively, then the autoregressive models of the packet and the time interval are expressed as follows:

[0010]

[0011] wherein, , , ; The correlation coefficient and the constant term of the model are calculated according to the input traffic data set, and the order is gradually tried and determined according to the order determination criterion , , so as to obtain the final traffic fitting model; The fitted model parameters are sent to the traffic generator, and the traffic generation program of the traffic generator obtains the subsequent time interval and packet size according to the given initial input or initial state of the data set and generates and sends the traffic to the receiving service end.

[0012] Preferably, according to the access and transmission object, the traffic generation service and the traffic receiving service are integrated and optimized respectively, and the deployment of the two traffic services on the cluster is optimized, including: The traffic receiving service to be deployed is analyzed, and if there are multiple traffic receiving services accessing the same simulation network device, they are integrated into a larger traffic receiving service, and distributed deployment is performed in the case of insufficient load; After the traffic receiving service is integrated, the traffic generation service is analyzed, and if there are multiple traffic generation services accessing the same simulation network device and concurrently sending to the same integrated traffic receiving service, they are integrated into a larger traffic generation service, and distributed deployment is performed in the case of insufficient load; The physical machine where the simulation network device needs to be accessed is obtained, the load condition of the physical machine is judged, and in the case that the resources of the physical machine allow, the scheduling strategy of selecting a suitable physical machine based on resource use and load distribution of the cluster is skipped, and the service is deployed on the physical machine.

[0013] Preferably, the integrating and optimizing the traffic generation service and the traffic receiving service according to the access and the sending respectively and optimizing the deployment of the two traffic services on the cluster further comprises: The service pre-starting is used to complete the deployment of the traffic service before the user submits the traffic request, and then the traffic request is received to generate the traffic, comprising: When the simulation network is initially constructed, all the simulation network devices at the edge of the simulation network are analyzed and acquired; For the simulation network devices at the edge of the simulation network, the traffic generation service connected therewith is deployed and started, and the network connection is opened by means of the network plug-in provided by the simulation network platform; The traffic request is received to generate the traffic.

[0014] Preferably, after the service pre-starting is used to complete the deployment of the service before the user submits the task, and then the traffic request is received to generate the traffic, the method further comprises: The data monitoring platform is started, and the corresponding collection interface and the collection data type are registered in the data monitoring platform; The data collection program is added in the traffic generator, and the traffic transmission condition is acquired regularly and sent to the data monitoring platform.

[0015] To achieve the object of the application, a second aspect provides an efficient network traffic generation deployment system based on a simulation network, which applies the efficient network traffic generation deployment method based on a simulation network. The controller module is used to control and manage the execution flow of other modules and the interaction between the modules, and ensure the correct execution of the modules; The traffic generation module comprises a traffic generator, which is used for the deployment of the traffic generation and receiving service and the start of the traffic generator; The model fitting module is used to fit the traffic data set by using the autoregressive model and obtain the corresponding traffic characteristic parameters, and send the traffic characteristic parameters to the traffic generator; The data collection module comprises a data monitoring platform, the data monitoring platform is registered with the corresponding collection interface and collection data type, and a part of the data collection module runs in the traffic generation service to acquire the transmission data of the network card, and another part runs in the cluster to collect, summarize and display the data condition; The deployment optimization module is used to acquire the simulation network structure and the pre-deployment condition of the traffic service, so as to pre-start the service and integrate the service.

[0016] Preferably, the controller module will request the cluster to clear the currently deployed service to release the currently occupied physical resources when the traffic generation requirement ends.

[0017] To achieve the object of the present application, the third aspect provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for deploying traffic generation based on a simulation network according to the first aspect or run the system for deploying traffic generation based on a simulation network according to the second aspect.

[0018] To achieve the object of the present application, the fourth aspect provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method for deploying traffic generation based on a simulation network according to the first aspect or run the system for deploying traffic generation based on a simulation network according to the second aspect.

[0019] Compared with the prior art, the present application has the following beneficial effects: The present application deploys corresponding traffic generation and reception services on the simulation network according to the configuration, extracts traffic time characteristics in model fitting according to the traffic data set to generate traffic, accesses the corresponding traffic services on different edge simulation network devices to reflect the spatial distribution, optimizes the deployment of traffic services on the cluster to improve the network transmission performance, integrates the common traffic services to reduce resource occupation and improve the execution efficiency of the task, and provides a feasible and efficient traffic generation deployment scheme for large-scale traffic generation of multiple users in the simulation network scenario. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A flowchart of the steps of a method for deploying traffic generation based on a simulation network according to an embodiment; Figure 2 A system architecture diagram of a system for deploying traffic generation based on a simulation network according to an embodiment; Figure 3 An execution flowchart of a deployment optimization module of a system for deploying traffic generation based on a simulation network according to an embodiment; Figure 4 A workflow diagram of a data acquisition module in a system for deploying traffic generation based on a simulation network according to an embodiment. DETAILED DESCRIPTION

[0021] In order to make the object, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0022] Embodiment 1 As Figure 1As shown, the steps of the traffic generation deployment method based on the simulation network of embodiment 1 include: S1: generating corresponding traffic generation services and traffic receiving services on the simulation network based on the configuration file generated based on the simulation network topology and traffic demand provided by the user; S2: extracting the traffic time characteristics of the preset or user-provided traffic data set based on model fitting, and the traffic generation service generates traffic according to the traffic time characteristics and sends it to the traffic receiving service; S3: accessing the corresponding traffic generation service or traffic receiving service on different edge simulation network devices according to user configuration to realize multi-region traffic service; S4: integrating and optimizing the deployment of the two traffic services on the cluster according to the access and sending objects, respectively; Further, the above steps S1-S4 specifically include the following steps: According to the user demand, generate various resources required for traffic generation, including creating traffic generators and receiving service ends corresponding to traffic generation services and traffic receiving services; Configure open ports and network cards to create network connections between traffic generators, receiving service ends, and simulation networks.

[0023] After the format check and preprocessing of the traffic data set, input it into the autoregressive model, which is specifically as follows: Consider that a long connection has n data packets in the current time slot, and each data packet is sent with a certain time interval; denotes the size of the i-th data packet; denotes the time interval between the sending of the i-1th data packet to the i-th data packet, , the correlation coefficient of the i-th time interval, the number of previous sent data packet lengths considered when fitting the data packet model, the number of previous sent data packet time intervals considered when fitting the time interval model, , respectively, the constant term when fitting the two models, then the autoregressive models of the data packet and the time interval are as follows:

[0024]

[0025] wherein, , , ; According to the input flow data set, the correlation coefficient and constant term of the model are calculated, and the order is gradually tried and determined according to the order determination criterion , , and the final flow fitting model is obtained; The fitted model parameters are sent to the flow generator, and the flow generation program of the flow generator obtains the time interval and packet size after the initial input or initial state of the data set according to the given initial input, and generates and sends the flow to the receiving server according to the given initial input or initial state of the data set.

[0026] According to the user configuration, access the corresponding traffic generation service or traffic receiving service on different edge simulation network devices to realize the traffic service of multiple regions and reflect the spatial distribution characteristics of traffic.

[0027] According to the access and sending object, the traffic generation service and the traffic receiving service are integrated and optimized, and the deployment of the two traffic services on the cluster is optimized, including: The traffic receiving service to be deployed is analyzed, and if there are multiple traffic receiving services accessing the same simulation network device, they are integrated into a larger traffic receiving service, and distributed deployment is performed under the condition of insufficient load; After the traffic receiving service is integrated, the traffic generation service is analyzed, and if there are multiple traffic generation services accessing the same simulation network device and concurrently sending to the same integrated traffic receiving service, they are integrated into a larger traffic generation service, and distributed deployment is performed under the condition of insufficient load; Get the physical machine where the simulation network device is located, judge the load condition of the physical machine, and in the case that the resources of the physical machine allow, skip the cluster based on resource usage and load distribution selection scheduling strategy to select the appropriate physical machine, and deploy the service on the physical machine.

[0028] The service pre-starting method is used to complete the traffic service deployment before the user submits the traffic request, and then the traffic generation is performed, including: When the simulation network is initially constructed, analyze and obtain all the simulation network devices at the edge of the simulation network; For the simulation network devices at the edge of the simulation network, deploy and start the traffic generation service connected thereto, and use the network plug-in provided by the simulation network platform to connect the network; it should be noted that the network plug-in can be a virtual network card; Receive traffic requests to generate traffic.

[0029] After the service pre-starting method is used to complete the service deployment before the user submits the task, and after receiving the traffic request to generate the traffic, start the data monitoring platform, register the corresponding collection interface and collection data type in the data monitoring platform; In the flow generator, a data acquisition program is added to periodically obtain the flow transmission and send it to the data monitoring platform.

[0030] Embodiment 2 This embodiment 2 is based on embodiment 1, and provides an efficient network flow generation deployment system based on a simulation network. The system applies the efficient network flow generation deployment method based on a simulation network in embodiment 1, and includes: A controller module is configured to control and manage the execution flow of other modules and the interaction between the modules, and ensure correct execution of the modules. A flow generation module includes a flow generator, and is configured to deploy the flow generation and receiving service and start the flow generator. A model fitting module is configured to fit the flow data set by using an autoregressive model and obtain corresponding flow characteristic parameters, and send the flow characteristic parameters to the flow generator. A data acquisition module includes a data monitoring platform, the data monitoring platform is registered with corresponding acquisition interfaces and acquisition data types, and the data acquisition module is partially operated in the flow generation service to obtain the transmission data of the network card, and partially operated in the cluster to collect, summarize and display the data. A deployment optimization module is configured to obtain the simulation network structure and the pre-deployment of the flow service, and perform service pre-start and service integration.

[0031] Preferably, the controller module requests the cluster to clear the currently deployed service to release the currently occupied physical resources when the flow generation requirement ends.

[0032] FIG. 2 shows the flow and structure of the entire flow generation deployment system, and specifically as follows: First, the controller module sends the obtained user requirement to the flow generation module, and sends the obtained flow data set to the model fitting module, so as to obtain the deployment view of the flow service and the flow characteristics of the corresponding flow service. Then, the controller module sends the above result to the deployment optimization module, the module calls the api of the kubernetes cluster to deploy and start the required flow service on the simulation network. At the same time, when the flow service starts, the acquisition program carried by the flow service also runs, and periodically sends the flow transmission data of the service to the monitoring platform. Finally, when the flow generation requirement ends, the controller module requests the cluster to clear the currently deployed service to release the currently occupied physical resources.

[0033] FIG. 3 shows the specific execution flow of the deployment optimization module, and specifically as follows: The service pre-starting mode is used to complete the traffic service deployment before the user submits a traffic request, and then the traffic request is received to generate traffic, including: When the simulation network is initially constructed, all edge network device data on the simulation network is analyzed and acquired; The traffic receiving service of each edge network device is deployed and started on the same physical machine of each edge network device, and the network card of each edge network device is deployed and started to perform network connection between the traffic generation service, the traffic receiving service, and the simulation network; The traffic generation service of each edge network device is deployed and started on the same physical machine of each edge network device, and the network card of each edge network device is deployed and started to perform network connection between the traffic generation service, the traffic receiving service, and the simulation network; The traffic request is received to generate traffic.

[0034] Fig. 4 is a workflow of a data acquisition module in a traffic generation deployment system based on a simulation network. First, the data type to be acquired, the corresponding resource label, and the acquisition port are registered on the data monitoring platform. The platform will periodically send an http request to acquire the acquisition data; Next, the prepared acquisition program needs to be started on the traffic generation service side to periodically acquire the traffic transmission of the virtual network card on the pod. Since the network card has a special name, for the case of connecting multiple simulation network devices by the service, all network cards with special names on the pod are acquired to prevent the loss of traffic data. Then, the data is exposed on the port page in a format defined in advance, so as to be acquired by the data monitoring platform; The data monitoring platform saves the data in a database. The platform running program presents all acquisition data on the page in the form of a chart, etc., for the user to query the current traffic task execution state and the traffic publishing and transmission situation.

[0035] Embodiment 3 This embodiment 3 is based on embodiment 1, and provides a computer electronic device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. The program implements each process of the steps of the traffic generation deployment method based on a simulation network of embodiment 1 when executed by the processor, and can achieve the same technical effects, or implements the functions of each part of the traffic generation deployment system based on a simulation network of embodiment 2, and can achieve the same technical effects.

[0036] The processor can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor is configured to execute computer programs stored in the memory to implement the steps of the method according to the above-mentioned embodiment 1 or the modules and their functions of the system according to the above-mentioned embodiment 2.

[0037] The memory is configured to store programs. The memory can include volatile memory, such as random-access memory (RAM), e.g., static random-access memory (SRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), etc. The memory can also include non-volatile memory, such as flash memory. The memory is configured to store computer programs (e.g., application programs, functional modules, etc. for implementing the above-mentioned method), computer instructions, etc.

[0038] The computer programs, computer instructions, etc. can be stored in one or more memories in a partitioned manner. The computer programs, computer instructions, data, etc. mentioned above can be invoked by the processor.

[0039] The processor and the memory can be independent structures or integrated structures. When the processor and the memory are independent structures, the memory and the processor can be coupled by a bus.

[0040] In summary, the present application has the following advantages and effects over the prior art: The high-efficiency network traffic generation deployment method and system based on the simulation network provided by the above-mentioned embodiments of the present application generate various resources required for traffic generation based on user demand, create corresponding traffic generation objects required for services and receiving service objects, open ports and network cards, and network connections between traffic generation objects, receiving service objects and simulation network devices, and fit the traffic data set into an autoregressive model, fit the autoregressive model according to the following description, and obtain the final traffic fitting parameters in this way. These parameters are transmitted to the traffic generator to generate traffic, then the common traffic services in the above-mentioned created service objects are integrated, and then all optimized resource objects are deployed on the cluster, and the service pre-start processing is also provided to deploy the service in advance to optimize the execution time and efficiency of the entire traffic task, and the corresponding collection interface and collection data type are registered in the data monitoring platform started in advance, the data collection program is added in the traffic generator, the traffic transmission situation is obtained regularly and sent to the data monitoring platform, so as to obtain all data of the traffic transmission generated by each service in the entire traffic generation process. The entire method and system can satisfy the characteristics of the real network traffic under the simulation network and the resource management and scheduling realized in the kubernetes container orchestration platform to reduce the cost of the simulation network, improve the efficiency of simulation and the utilization rate of physical resources.

[0041] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM), and includes a plurality of instructions for making a terminal (which can be a computer, a server or a network device, etc.) execute the method or system of each embodiment of the present application.

[0042] The above-mentioned is the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A traffic generation and deployment method based on simulated networks, characterized in that, Includes the following steps: Based on the user-provided simulated network topology and traffic requirements, the configuration file generates corresponding traffic generation and traffic reception services on the simulated network. Based on model fitting, the traffic time characteristics of a preset or user-provided traffic dataset are extracted. The traffic generation service generates traffic according to the traffic time characteristics and sends it to the traffic receiving service. Based on user configuration, the corresponding traffic generation or traffic receiving service is connected to different edge simulation network devices to achieve multi-region traffic service; Based on the objects being accessed and sent, the traffic generation service and traffic reception service are integrated and their deployment on the cluster is optimized.

2. The traffic generation and deployment method based on a simulated network according to claim 1, characterized in that, The configuration file generated based on the simulated network topology and traffic requirements provided by the user generates corresponding traffic generation and traffic reception services on the simulated network, including: Create traffic generators and receiving servers corresponding to traffic generation and traffic receiving services; Configure open ports and network cards, and create network connections between the traffic generator, receiving server, and simulated network.

3. The traffic generation and deployment method based on a simulated network according to claim 2, characterized in that, The process of extracting traffic time characteristics from a preset or user-provided traffic dataset based on model fitting, and the traffic generation service generating traffic and sending it to the traffic receiving service based on these traffic time characteristics, includes: After format checking and preprocessing, the traffic dataset is input into the autoregressive model, which is as follows: Consider a long-lived connection with n data packets in the current time slot, and each data packet is sent at a certain time interval; This represents the size of the i-th data packet; This represents the time interval between sending the (i-1)th data packet to the i-th data packet. , The correlation coefficient of the i-th time interval The number of previously sent data packets of length considered when fitting the data packet model. The number of time intervals of previously sent data packets considered when fitting the time interval model. , Let be the constants used in fitting the two models, then the autoregressive model for data packets and time intervals is expressed as follows: in, , , ; The correlation coefficient and constant term of the model are calculated based on the input traffic dataset, and the order is determined step by step according to the order determination criteria. , This leads to the final flow fitting model; The fitted model parameters are sent to the traffic generator. The traffic generator's traffic generation program obtains the subsequent time intervals and packet sizes according to the given initial input or the initial state of the dataset, and generates and sends traffic to the receiving server accordingly.

4. The traffic generation and deployment method based on a simulated network according to claim 1, characterized in that, The process of integrating and optimizing the deployment of traffic generation and reception services on the cluster based on the access object and the sending object includes: Analyze the traffic receiving service to be deployed. If there are multiple traffic receiving services connected to the same simulated network device, integrate them into a larger traffic receiving service and deploy them in a distributed manner when the load is insufficient. After integrating the traffic receiving service, the traffic generation service is analyzed. If there are multiple traffic generation services connected to the same simulated network device and concurrently sending traffic to the same integrated traffic receiving service, they are integrated into a larger traffic generation service and distributed for deployment when the load is insufficient. Obtain the physical machine where the simulated network device to be connected is located, determine the load status of the physical machine, and if the resources of the physical machine allow, skip the cluster's scheduling strategy of selecting a suitable physical machine based on resource usage and load allocation, and deploy the service scheduling on the physical machine.

5. The traffic generation and deployment method based on a simulated network according to claim 4, characterized in that, The method of integrating and optimizing the deployment of traffic generation and traffic reception services on the cluster based on the access and transmission objects also includes: The traffic service is deployed before users submit traffic requests, and then traffic generation is performed upon receiving traffic requests, including: When initially building the simulation network, analyze and obtain all simulation network devices located at the edge of the simulation network; For simulated network devices at the edge of the simulated network, deploy and start the traffic generation service connected to them, and use the network plugins provided by the simulated network platform to establish network connectivity. It receives traffic requests to generate traffic.

6. The traffic generation and deployment method based on a simulated network according to claim 5, characterized in that, After the method of pre-starting the service to complete service deployment before the user submits the task and receiving traffic requests to generate traffic, the method further includes: Start the data monitoring platform and register the corresponding data collection interface and data type on the platform; Add a data acquisition program to the traffic generator to periodically obtain traffic transmission information and send it to the data monitoring platform.

7. A traffic generation and deployment system based on a simulated network, employing the traffic generation and deployment method based on a simulated network as described in any one of claims 1-6, characterized in that, The system includes: The controller module is used to control and manage the execution flow of other modules and the interaction between modules, ensuring that each module executes correctly; The traffic generation module includes a traffic generator, which is used for the deployment of traffic generation and receiving services and the startup of the traffic generator; The model fitting module is used to fit the traffic dataset using an autoregressive model and obtain the corresponding traffic feature parameters, and then send the traffic feature parameters to the traffic generator. The data acquisition module includes a data monitoring platform. The data monitoring platform is registered with corresponding acquisition interfaces and data types. Part of the data acquisition module runs in the traffic generation service to obtain the transmission data of the network card, and part of it runs in the cluster to collect, summarize and display the data. The deployment optimization module is used to obtain the pre-deployment status of the simulated network structure and traffic services, thereby enabling service pre-startup and service integration.

8. The traffic generation and deployment system based on a simulated network according to claim 7, characterized in that, When the traffic generation demand ends, the controller module requests the cluster to clear the currently deployed services in order to release the currently occupied physical resources.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the traffic generation and deployment method based on a simulated network as described in any one of claims 1 to 6, or runs the traffic generation and deployment system based on a simulated network as described in any one of claims 7 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the traffic generation and deployment method based on a simulated network as described in any one of claims 1 to 6, or runs the traffic generation and deployment system based on a simulated network as described in any one of claims 7 to 8.

Images