Computer network simulation method and system based on discrete event and virtualization sandbox

Abstract

The invention provides a computer network simulation method and system based on discrete events and a virtualization sandbox, and the method comprises the steps: distributing a discrete event simulation scheme or a virtualization sandbox simulation scheme for nodes in computer network graph data according to the required bandwidth of each node of the computer network graph data; calling a discrete event simulation node creation tool installed in the physical machine, and creating nodes belonging to the discrete event simulation scheme as discrete event simulation nodes; calling a virtual sandbox simulation node creation tool installed in the physical machine, and creating nodes belonging to the virtual sandbox simulation scheme as virtual sandbox simulation nodes; a user mode protocol stack is used as a virtual network interface of the simulation network node, and the virtualization sandbox simulation node communicates with the discrete event simulation node through the virtual network interface; and the data packet is transmitted between the discrete event simulation and the virtual sandbox simulation, and is mutually connected through the virtual network interface to obtain a simulation result of the computer network graph data.

Description

Technical Field

[0001] The present invention relates to the field of computer networks and network simulation systems, and particularly to a computer network simulation method and system based on discrete events and virtualized sandboxes. Background Art

[0002] Computer network simulation is an important means for pre-verifying network configurations and services. Through computer network simulation, technical indicators such as network configuration correctness verification, network abnormal behavior analysis, and network data flow completion time verification can be obtained. Existing network simulation technologies are mainly divided into two categories. The first category is discrete event simulation represented by NS3. The characteristic of this type of technology is to use a mathematical model to simulate the arrival and processing process of data packets. The other category is virtualized sandbox simulation represented by MiniNet. The characteristic of this type of technology is to run the functions of network devices in a virtualized manner on a general server, so as to simulate the status of network devices and applications in real time and more realistically. And there are many open-source network virtualization devices such as OVS and FRR that can be directly used in this type of simulation.

[0003] The problem with discrete event-based simulation is that the complexity of data packet processing cannot be too high, otherwise it will lead to an increase in simulation time under the same simulation task. The problem with virtualization-based simulation is that the number of simulation nodes cannot be too large, otherwise it will lead to exhaustion of CPU and memory resources. Based on the problems existing in the above two network simulation schemes. The inventor found that under large-scale simulation requirements, neither NS3 nor MiniNet can meet the simulation requirements. Summary of the Invention

[0004] The present invention proposes a hybrid simulation scheme that combines discrete event simulation and virtualized sandbox simulation. By deploying the network topology to be simulated in the discrete event simulation NS3 and the virtualized sandbox technology simulation MiniNet respectively, and connecting them through a virtual network interface, while realizing the network simulation function, the scale of the topology that can be simulated is improved. Through the hybrid simulation of NS3 and MiniNet, the problem that the scale of the existing network simulation system cannot be too large is solved. The following two technical problems are mainly solved. 1) The optimal allocation problem of network nodes in the simulation topology between NS3 and MiniNet; 2) The problem of high-speed communication between NS3 and MiniNet.

[0005] Specifically, the present invention proposes a computer network simulation method based on discrete events and virtualized sandboxes, which includes:

[0006] Step 1, obtain computer network diagram data for computer network simulation, where the nodes in the computer network diagram data are computing devices, and the edges between the nodes in the computer network diagram data are the required bandwidth between computing devices;

[0007] Step 2: According to the required bandwidth of each node, allocate a discrete event simulation scheme or a virtualized sandbox simulation scheme to the nodes in the computer network diagram data; by calling the node creation tool for discrete event simulation installed on the physical machine, create the nodes belonging to the discrete event simulation scheme as discrete event simulation nodes; by calling the node creation tool for virtualized sandbox simulation installed on the physical machine, create the nodes belonging to the virtualized sandbox simulation scheme as virtualized sandbox simulation nodes;

[0008] Step 3: Use a high-speed user space protocol stack as the virtual network interface of the simulation network node, and the virtualized sandbox simulation node communicates with the discrete event simulation node through this virtual network interface;

[0009] Step 4: Start the discrete event simulation and the virtualized sandbox simulation. The data packets are transmitted between the discrete event simulation and the virtualized sandbox simulation and are interconnected through the virtual network interface to achieve hybrid simulation, and obtain the simulation result of the computer network diagram data.

[0010] The computer network simulation method based on discrete event and virtualized sandbox, wherein step 2 includes

[0011] The computer network diagram data is an undirected graph G=(V, E); for any node v belonging to V, the weight u of the node v represents the physical resources occupied by the node; for any edge e belonging to E, the weight w of the edge e represents the bandwidth resources occupied by the edge; the importance p of each node i is the sum of the weights of the edges connected to the node p i =∑ e∈N{i} w e , where N{i} represents the set of edges connected to the i-th node; by performing integer optimization on the following formula, allocate a simulation scheme to the nodes in the computer network diagram data:

[0012]

[0013]

[0014] p i x i ≤P

[0015]

[0016] where the variable x i represents the simulation scheme of node i; x i =0 indicates that node i is a virtualized sandbox simulation scheme, x i= 1 indicates that node i is a discrete event simulation scenario; P is the upper limit of the node importance in this discrete event simulation; C is the upper limit of the physical resources of the physical machine; λ is the proportion of physical resources occupied by the node deployed in this discrete event simulation, where λ < 1; the objective of this integer optimization is to minimize the communication cost between nodes; β1, β2, and β3 respectively represent the proportions of communication bandwidth occupied by node pairs in the discrete event simulation, in the virtualization sandbox simulation, and in the case of spanning the virtualization sandbox and the discrete event simulation; solve this integer optimization problem to obtain the value of x i value.

[0017] The computer network simulation method based on discrete event and virtualization sandbox, where step 2 includes: determining the network topology to be simulated on the discrete event simulation, including nodes, links, and application configurations, and the configurations include simulation parameters such as simulation time and data packet generation rate; creating images of virtual network devices in the virtualization sandbox simulation, including switches, routers, hosts, etc., and configuring parameters of the virtual network devices, such as IP addresses, port configurations, etc.

[0018] The computer network simulation method based on discrete event and virtualization sandbox, where step 3 includes:

[0019] Adding a virtual network card to the discrete event simulation node, connecting the virtual network interface of the virtualization sandbox simulation node to OVS, and connecting the virtual network card of the discrete event simulation node to the DPDK-OVS of the virtualization sandbox simulation to achieve the interconnection and intercommunication between the discrete event simulation node and the virtualization sandbox simulation node.

[0020] The present invention also proposes a computer network simulation system based on discrete event and virtualization sandbox, which includes:

[0021] Module 1, obtaining computer network diagram data to be computer network simulated, where the nodes in the computer network diagram data are computing devices, and the connections between the nodes in the computer network diagram data are the required bandwidths between the computing devices;

[0022] Module 2, allocating discrete event simulation scenarios or virtualization sandbox simulation scenarios to the nodes in the computer network diagram data according to the required bandwidths of each node; by calling the node creation tool of the discrete event simulation installed on the physical machine, creating the nodes belonging to the discrete event simulation scenario as discrete event simulation nodes; by calling the node creation tool of the virtualization sandbox simulation installed on the physical machine, creating the nodes belonging to the virtualization sandbox simulation scenario as virtualization sandbox simulation nodes;

[0023] Module 3, using a high-speed user space protocol stack as the virtual network interface of the simulation network node, and the virtualization sandbox simulation node communicates with the discrete event simulation node through this virtual network interface;

[0024] Module 4 starts the discrete event simulation and the virtualized sandbox simulation. Data packets are transmitted between the discrete event simulation and the virtualized sandbox simulation and are interconnected via the virtual network interface to achieve hybrid simulation, obtaining the simulation results of the computer network diagram data.

[0025] The described computer network simulation system based on discrete events and virtualized sandboxes, wherein module 2 includes

[0026] The computer network diagram data is an undirected graph G=(V, E); for any node v belonging to V, the weight u of the node v represents the physical resources occupied by the node; for any edge e belonging to E, the weight w of the edge e represents the bandwidth resources occupied by the edge; the importance p of each node i is the sum of the weights of the edges connected to the node p i =∑ e∈N{i} w e , where N{i} represents the set of edges connected to the i-th node; by performing integer optimization on the following formula, a simulation scheme is assigned to the nodes in the computer network diagram data:

[0027]

[0028]

[0029] p i x i ≤P

[0030]

[0031] where the variable x i represents the simulation scheme of node i; x i =0 indicates that node i is a virtualized sandbox simulation scheme, and x i =1 indicates that node i is a discrete event simulation scheme; P is the upper limit of the node importance of the discrete event simulation; C is the upper limit of the physical resources of the physical machine; λ is the proportion of the physical resources occupied by the node deployed in the discrete event simulation, λ<1; the objective of the integer optimization is to minimize the communication cost between nodes; β1, β2, and β3 respectively represent the proportions of the communication bandwidth occupied by node pairs in the discrete event simulation, in the virtualized sandbox simulation, and in the case of crossing the virtualized sandbox and the discrete event simulation; solve the integer optimization problem to obtain the value of x i .

[0032] The described computer network simulation system based on discrete event and virtualized sandbox, wherein module 2 includes: determining the network topology to be simulated in the discrete event simulation, including nodes, links, and application configurations, and the configuration includes simulation parameters such as simulation time and data packet generation rate; creating images of virtualized network devices in the virtualized sandbox simulation, including switches, routers, hosts, etc., and configuring parameters of the virtual network devices, such as IP addresses, port configurations, etc.

[0033] The described computer network simulation system based on discrete event and virtualized sandbox, wherein module 3 includes:

[0034] Adding a virtual network card to the discrete event simulation node, connecting the virtual network interface of the virtualized sandbox simulation node to OVS, and connecting the virtual network card of the discrete event simulation node to the DPDK-OVS of the virtualized sandbox simulation to achieve interconnection and interoperability between the discrete event simulation node and the virtualized sandbox simulation node.

[0035] The present invention also proposes a server, which includes the described computer network simulation device based on discrete event and virtualized sandbox.

[0036] The present invention also proposes a storage medium for storing a computer program of the described computer network simulation method based on discrete event and virtualized sandbox.

[0037] As can be seen from the above solutions, the advantages of the present invention are:

[0038] Under the condition that the physical resources used in computer network simulation remain unchanged, the scale of the network topology that can be simulated is improved, and the overall data packet processing performance of the network simulation system is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] In order to achieve the above technical effects, the discrete event simulation of the present invention takes NS3 as an example, and the virtualized sandbox simulation takes MiniNet as an example. The present invention includes the following key technical points:

[0041] Key point 1, an optimal allocation method based on the "importance" of nodes;

[0042] Since NS3 is sensitive to the complexity of packet processing and MiniNet is sensitive to the number of simulation nodes, which network nodes in the simulation topology are deployed in NS3 and which are deployed in MiniNet will affect the scale that can be simulated. The present invention proposes an optimal node allocation scheme based on the "importance" of nodes. The "importance" of a node is proportional to the packet rates sent and received by the node in the topology. The present invention utilizes the "importance" of nodes and obtains an optimal node allocation scheme by establishing and solving a mixed integer optimization problem. Key point 1 improves the simulable topology scale under the same physical resources;

[0043] Key point 2, a high-speed communication scheme between nodes based on DPDK (Data Plane Development Kit);

[0044] The communication mechanism between simulation nodes restricts the performance of the simulation. The present invention proposes to use a high-speed user-space protocol stack based on DPDK as the virtual network interface of the simulation network nodes, bypassing the kernel's processing of packets and improving the packet transmission speed. For the simulation nodes in NS3, use the DPDK-based network device (DpdkNetDevice module) in NS3 to establish a virtual network device for each node. For the nodes in MiniNet, connect their virtual network cards to the OVS implemented based on DPDK. Key point 2 improves the packet transmission performance of the simulation system and enhances the communication performance between accelerated simulation nodes.

[0045] To make the above features and effects of the present invention more clearly and understandably described, specific embodiments are hereinafter given and will be described in detail in conjunction with the accompanying drawings of the specification. This specification discloses one or more embodiments incorporating the features of the present invention. The disclosed embodiments are only for illustrative purposes. The protection scope of the present invention is not limited to the disclosed embodiments, and the present invention is defined by the appended claims.

[0046] To solve the scale and performance limitations of existing network simulation systems, the present invention provides an implementation method as Figure 1 shown to describe in detail how to implement a hybrid network simulation system:

[0047] Step 1: Prepare the simulation environment

[0048] Install NS3 and MiniNet on the physical machine. Determine the network topology structure to be simulated, the types of nodes, and the bandwidth requirements of the connections. The types of nodes can be servers, switches, routers, firewalls, network intermediate devices, etc.

[0049] Step 2: Optimal topology allocation

[0050] 2.1 In this step, according to the functions and importance of nodes, network nodes are divided into two categories: one category is suitable for simulation in NS3, and the other is suitable for simulation in MiniNet. Let the network topology to be simulated be an undirected graph G=(V, E). For any node v belonging to V, we define the weight of the node as u v , which represents the physical resources occupied by the node and is proportional to the processing complexity of the node for data packets; for any edge e belonging to E, we define the weight of the edge as w e , which represents the bandwidth resources occupied by the edge and is proportional to the data packet rate sent and received on the edge. The importance p i of each node is defined as the sum of the weights of the edges connected to the node p i = ∑ e∈N{i} w e , where N{i} represents the set of edges connected to node i. We determine which nodes are deployed in NS3 and which are deployed in MiniNet by solving the following integer optimization problem.

[0051]

[0052]

[0053] p i x i ≤ P

[0054]

[0055] Among them, we use the variable x i to represent the location of the node. x i = 0 means the node is in MiniNet, and x i = 1 means the node is in NS3. P is the upper limit of the node importance that NS3 can accept. C is the upper limit of the physical resources of the physical machine. λ is the relative proportion of the physical resources occupied by the node deployed in NS3 (λ < 1), and the relative proportion of the resources occupied by the node deployed in MiniNet is 1. The optimization objective of this problem is to minimize the sum of the communication costs between nodes. Among them, β1, β2, and β3 respectively represent the relative proportions of the communication bandwidth occupied by node pairs in NS3, in MiniNet, and in the case of crossing NS3 and MiniNet. Solving the above problem to obtain the solution of x i is the location where the node should be placed.

[0056] 2.2. Virtual Node Construction: According to the above results, call the respective node creation APIs in NS3 and MiniNet to create the corresponding nodes. Define the network topology to be simulated on NS3, including nodes, links, and application configurations. Configure the simulation parameters, such as simulation time, packet generation rate, etc. Create images of virtual network devices in MiniNet, including switches, routers, hosts, etc. Configure the parameters of virtual network devices, such as IP addresses, port configurations, etc.

[0057] Step 3: High-Speed Node Communication

[0058] 3.1. For NS3 Simulation Nodes: Add the DpdkNetDevice module as the virtual network card for each node deployed in NS3 to achieve high-speed packet transmission based on DPDK.

[0059] 3.2. For MiniNet Virtual Network Devices: For the simulation nodes deployed in MiniNet, connect their virtual network interfaces to the virtual switch OVS implemented based on DPDK to improve the packet transmission speed.

[0060] 3.3 Connect the virtual network cards of the nodes in NS3 based on the DpdkNetDevice module to the virtual switch (DPDK-OVS) implemented based on DPDK in MiniNet to achieve interconnection and interoperability between NS3 nodes and MiniNet nodes.

[0061] Step 4: Execute Hybrid Simulation

[0062] 4.1. Start Simulation: Start the NS3 simulation environment and the MiniNet simulation environment. Packets are transmitted between the two environments and are interconnected via virtual network interfaces to achieve hybrid simulation.

[0063] Through the above steps, the hybrid network simulation system of the present invention can make full use of the advantages of NS3 and MiniNet under large-scale simulation requirements, improve the simulation performance and the scale of topologies that can be simulated. At the same time, through the optimal allocation method based on node "importance" and the high-speed communication scheme based on DPDK, the problems and disadvantages existing in the existing network simulation systems are solved, and more efficient and more realistic network simulation is achieved.

[0064] The following is the system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in cooperation with the above embodiment. The relevant technical details mentioned in the above embodiment are still valid in this embodiment, and in order to reduce repetition, they will not be elaborated here. Correspondingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0065] The present invention also provides a computer network simulation system based on discrete events and virtualized sandboxes, which includes:

[0066] Module 1: Obtain the computer network diagram data to be simulated by the computer network. In this computer network diagram data, the nodes are computing devices, and the connections between the nodes in this computer network diagram data are the required bandwidths between the computing devices.

[0067] Module 2: According to the required bandwidth of each node, allocate a discrete event simulation scheme or a virtualized sandbox simulation scheme to the nodes in this computer network diagram data; by calling the node creation tool for discrete event simulation installed on the physical machine, create the nodes belonging to this discrete event simulation scheme as discrete event simulation nodes; by calling the node creation tool for virtualized sandbox simulation installed on the physical machine, create the nodes belonging to this virtualized sandbox simulation scheme as virtualized sandbox simulation nodes.

[0068] Module 3: Use a high-speed user-space protocol stack as the virtual network interface of the simulation network nodes. The virtualized sandbox simulation nodes communicate with the discrete event simulation nodes through this virtual network interface.

[0069] Module 4: Start this discrete event simulation and this virtualized sandbox simulation. The data packets are transmitted between this discrete event simulation and this virtualized sandbox simulation and are interconnected through this virtual network interface to achieve hybrid simulation, and obtain the simulation results of this computer network diagram data.

[0070] In the described computer network simulation system based on discrete events and virtualized sandboxes, Module 2 includes

[0071] This computer network diagram data is an undirected graph G=(V, E); for any node v belonging to V, the weight u of the node v represents the physical resources occupied by the node; for any edge e belonging to E, the weight w of the edge e represents the bandwidth resources occupied by the edge; the importance p of each node i is the sum of the weights of the edges connected to this node p i =∑ e∈N{i} w e , where N{i} represents the set of edges connected to the i-th node; by performing integer optimization on the following formula, allocate a simulation scheme to the nodes in this computer network diagram data:

[0072]

[0073]

[0074] p i x i ≤P

[0075]

[0076] Among them, the variable x i represents the simulation scheme of node i; x i = 0 indicates that node i is a virtualized sandbox simulation scheme, and x i = 1 indicates that node i is a discrete event simulation scheme; P is the upper limit of the node importance of this discrete event simulation; C is the upper limit of the physical resources of this physical machine; λ is the proportion of physical resources occupied by the node deployed in this discrete event simulation, and λ < 1; the goal of this integer optimization is to minimize the communication cost between nodes; β1, β2, and β3 respectively represent the proportions of communication bandwidth occupied by node pairs in the discrete event simulation, in the virtualized sandbox simulation, and in the case of crossing the virtualized sandbox and the discrete event simulation; solve this integer optimization problem to obtain the value of x i .

[0077] The computer network simulation system based on discrete event and virtualized sandbox, wherein module 2 includes: determining the network topology to be simulated in this discrete event simulation, including nodes, links, and application configurations, and the configuration includes simulation parameters such as simulation time and data packet generation rate; creating images of virtual network devices in this virtualized sandbox simulation, including switches, routers, hosts, etc., and configuring parameters of the virtual network devices, such as IP addresses, port configurations, etc.

[0078] The computer network simulation system based on discrete event and virtualized sandbox, wherein module 3 includes:

[0079] Adding a virtual network card to the discrete event simulation node, connecting the virtual network interface of the virtualized sandbox simulation node to OVS, and connecting the virtual network card of the discrete event simulation node to the DPDK-OVS of the virtualized sandbox simulation to realize the interconnection and interoperability between the discrete event simulation node and the virtualized sandbox simulation node.

[0080] The present invention also proposes a server, which includes a computer network simulation device based on discrete event and virtualized sandbox as described above.

[0081] The present invention also proposes a storage medium for storing a computer program of a computer network simulation method based on discrete event and virtualized sandbox as described above.

[0082] Although the embodiments of the present invention have been disclosed as above, it is not limited to only the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those familiar with the field, additional modifications can be easily made. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to specific details and the illustrations shown and described herein.

Claims

1. A computer network simulation method based on discrete events and virtualized sandboxes, characterized in that, Including: Step 1: Obtain the computer network diagram data to be computer network simulated. The nodes in the computer network diagram data are computing devices, and the connections between the nodes in the computer network diagram data are the required bandwidths between the computing devices; Step 2: According to the required bandwidth of each node, allocate a discrete event simulation scheme or a virtualization sandbox simulation scheme to the nodes in the computer network diagram data; by invoking the node creation tool for discrete event simulation installed on the physical machine, create the nodes belonging to the discrete event simulation scheme as discrete event simulation nodes; by invoking the node creation tool for virtualization sandbox simulation installed on the physical machine, create the nodes belonging to the virtualization sandbox simulation scheme as virtualization sandbox simulation nodes; Step 3: Use a high-speed user-space protocol stack as the virtual network interface of the simulation network node, and the virtualization sandbox simulation node communicates with the discrete event simulation node through this virtual network interface; Step 4: Start the discrete event simulation and the virtualization sandbox simulation. Packets are transmitted between the discrete event simulation and the virtualization sandbox simulation, and are interconnected through this virtual network interface to achieve hybrid simulation, and obtain the simulation result of the computer network diagram data.

2. The computer network simulation method based on discrete events and virtualized sandboxes according to claim 1, characterized in that This Step 2 includes The computer network graph data is an undirected graph G=(V, E); for any node v belonging to V, the weight u of the node v represents the physical resources occupied by the node; for any edge e belonging to E, the weight w of the edge e represents the bandwidth resources occupied by the edge; the importance p of each node i is the sum of the weights of the edges connected to the node p i =Σ e∈N{i} w e , where N{i} represents the set of edges connected to the i-th node; by performing integer optimization on the following formula, a simulation scheme is allocated to the nodes in the computer network graph data: p i x i ≤P Among them, λ is the proportion of physical resources occupied by nodes in this discrete event simulation, and λ < 1; the objective of this integer optimization is to minimize the communication cost between nodes; β1, β2, and β3 respectively represent the proportions of communication bandwidth occupied by node pairs in the discrete event simulation, in the virtualization sandbox simulation, and in the case of spanning the virtualization sandbox and the discrete event simulation; solve this integer optimization problem to obtain the value of x i value.

3. The computer network simulation method based on discrete events and virtualized sandboxes according to claim 1, characterized in that This Step 2 includes: Determine the network topology to be simulated in the discrete event simulation, including nodes, links, and application configurations, and the configurations include simulation parameters such as simulation time and packet generation rate; create images of virtual network devices in the virtualization sandbox simulation, including switches, routers, hosts, etc., and configure the parameters of the virtual network devices, such as IP addresses, port configurations, etc.

4. The computer network simulation method based on discrete events and virtualized sandboxes as claimed in claim 1, wherein This Step 3 includes: Add a virtual network card to the discrete event simulation node, connect the virtual network interface of the virtualization sandbox simulation node to OVS, and connect the virtual network card of the discrete event simulation node to the DPDK-OVS of the virtualization sandbox simulation to achieve the interconnection and communication between the discrete event simulation node and the virtualization sandbox simulation node.

5. A computer network simulation system based on discrete events and virtualized sandboxes, characterized in that, Including: Module 1: Obtain the computer network diagram data to be computer network simulated. The nodes in the computer network diagram data are computing devices, and the connections between the nodes in the computer network diagram data are the required bandwidths between the computing devices; Module 2: According to the required bandwidth of each node, allocate a discrete event simulation scheme or a virtualization sandbox simulation scheme to the nodes in the computer network diagram data; by invoking the node creation tool for discrete event simulation installed on the physical machine, create the nodes belonging to the discrete event simulation scheme as discrete event simulation nodes; by invoking the node creation tool for virtualization sandbox simulation installed on the physical machine, create the nodes belonging to the virtualization sandbox simulation scheme as virtualization sandbox simulation nodes; Module 3: Use a high-speed user-space protocol stack as the virtual network interface of the simulation network node, and the virtualization sandbox simulation node communicates with the discrete event simulation node through this virtual network interface; Module 4 starts the discrete event simulation and the virtualized sandbox simulation. Data packets are transmitted between the discrete event simulation and the virtualized sandbox simulation and are interconnected via the virtual network interface to implement hybrid simulation, and the simulation results of the computer network diagram data are obtained.

6. The computer network simulation system based on discrete events and virtualized sandboxes according to claim 5, wherein Module 2 includes The computer network graph data is an undirected graph G = (V, E); for any node v belonging to V, the weight u of the node v represents the physical resources occupied by the node; for any edge e belonging to E, the weight w of the edge e represents the bandwidth resources occupied by the edge; the importance p of each node i is the sum of the weights of the edges connected to the node p i = Σ e∈N{i} w e , where N{i} represents the set of edges connected to the i-th node; by performing integer optimization on the following formula, a simulation scheme is allocated to the nodes in the computer network graph data: p i x i ≤P Among them, λ is the proportion of physical resources occupied by nodes in this discrete event simulation, and λ < 1; the goal of this integer optimization is to minimize the communication cost between nodes; β1, β2, and β3 respectively represent the proportions of communication bandwidth occupied by node pairs in discrete event simulation, in virtualized sandbox simulation, and in the case of spanning virtualized sandbox and discrete event simulation; solve this integer optimization problem to obtain the value of x i value.

7. The computer network simulation system based on discrete events and virtualized sandboxes as claimed in claim 5, wherein Module 2 includes: determining the network topology to be simulated on the discrete event simulation, including nodes, links, and application configurations, where the configuration includes simulation parameters such as simulation time and data packet generation rate; creating images of virtualized network devices in the virtualized sandbox simulation, including switches, routers, hosts, etc., and configuring parameters of the virtual network devices, such as IP addresses and port configurations.

8. The computer network simulation system based on discrete events and virtualized sandboxes according to claim 5, characterized in that Module 3 includes: Adding a virtual network card to the discrete event simulation node, connecting the virtual network interface of the virtualized sandbox simulation node to OVS, and connecting the virtual network card of the discrete event simulation node to the DPDK-OVS of the virtualized sandbox simulation to achieve interconnection and interoperability between the discrete event simulation node and the virtualized sandbox simulation node.

9. A server, characterized in that, It includes a computer network simulation device according to claims 5-8.

10. A storage medium for storing a computer program for executing the computer network simulation method based on discrete event and virtualized sandbox according to claims 1-4.

Images