Service chain determination method and device, equipment and storage medium

Abstract

The invention discloses a service chain determination method and device, equipment and a storage medium. The method comprises the following steps: constructing a network topology structure; the network topology structure comprises at least one network node; determining a service application sub-model, a virtual machine resource sub-model and a data routing sub-model of the network topology structure based on the service demand; generating a vertical arrangement model according to the service application sub-model, the virtual machine resource sub-model and the data routing sub-model; and performing iterative optimization on the vertical arrangement model to obtain a target service chain. According to the method, the service application sub-model, the virtual machine resource sub-model and the data routing sub-model are respectively constructed, the three-layer service chain vertical arrangement model taking the total network cost as the optimization target is generated based on the three sub-models, and the vertical arrangement model is solved through the optimization algorithm to obtain the target service chain. The accuracy and quality of the target service chain are ensured, and the reliability and cost effectiveness of VNF deployment in service chain arrangement are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network function virtualization (NFV) networking service orchestration, and in particular to a service chain determination method, device, equipment and storage medium. Background Art

[0002] NFV uses mature virtualization technology to decouple software instances from hardware platforms, and transfer network functions from dedicated hardware to virtualized network functions (VNFs) running on virtual machines, thereby achieving the goal of decoupling basic hardware network functions from hardware devices. NFV allows different network functions to be deployed at different locations in the network as needed, such as data centers, network nodes, and terminal nodes at the edge of the network.

[0003] In the NFV architecture, network services can be represented by a series of ordered connected VNFs, namely the Service Function Chain (SFC), also known as the business chain, which is divided into unidirectional and bidirectional according to the state requirements of network functions. Many common functions (such as DPI and firewall) usually require bidirectional connections to ensure the consistency of flow states. The business chain deployment problem specifically refers to the process of determining the optimal VNF location and routing path for the SFC under the conditions of meeting service requirements and resource constraints.

[0004] The network services created and deployed in NFV require the definition of the number of VNFs, the order of each VNF in the chain, and the resource allocation of the chain in NFVI. Since the order of VNFs in SFC is determined by the service requirements, one of the main challenges in deploying SFC is how to efficiently and appropriately place the VNFs required by SFC in the underlying network. The vertical orchestration between each layer is particularly challenging in terms of the order in which VNFs are arranged.

[0005] Regarding the deployment of service chains under NFV, existing related work mainly focuses on technical issues such as reducing the end-to-end delay of SFC, ensuring the strong reliability requirements of SFC, static SFC optimization and deployment, and NFV multicast deployment, and has achieved certain results. However, there is relatively little research on the vertical orchestration of NFV service chains, that is, the three-layer vertical orchestration based on the business application layer, virtual machine resource layer, and data routing layer.

[0006] Therefore, how to build a vertical orchestration model of the NFV service chain and how to minimize the network costs of the service application layer, virtual machine resource layer and data routing layer after orchestration are the technical problems that the present invention aims to solve. Summary of the invention

[0007] The present invention provides a service chain determination method, device, equipment and medium to solve the problems in the prior art of how to build a NFV service chain vertical orchestration model and how to minimize the network costs of the service application layer, virtual machine resource layer and data routing layer after orchestration.

[0008] In a first aspect, an embodiment of the present invention provides a service chain determination method, including:

[0009] Constructing a network topology structure, wherein the network topology structure includes at least one network node;

[0010] Determine the business application sub-model, virtual machine resource sub-model and data routing sub-model of the network topology structure based on the service requirements;

[0011] Generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model;

[0012] The vertical orchestration model is iteratively optimized to obtain a target service chain.

[0013] Optionally, determining the service application sub-model of the network topology structure based on service requirements includes:

[0014] Determine the virtual network function VNF instance based on service requirements;

[0015] Determine the total cost required to deploy the VNF instance on each network node;

[0016] A business application sub-model is generated based on the total cost and the first constraint condition; wherein the first constraint condition includes resource constraints and service quality constraints for deploying the VNF instance.

[0017] Optionally, the total cost required to deploy the VNF instance on each network node is expressed as:

[0018] ;

[0019] in, represents the total cost required to deploy the VNF instance on each network node, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates that the network node For service needs Deploy VNF Cost, VNF Indicates a VNF instance. represents a Boolean decision variable;

[0020] The resource constraints of the VNF instance are expressed as:

[0021] ;

[0022] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, represents a Boolean decision variable, Indicates service demand, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes;

[0023] The service quality constraint is expressed as:

[0024] ;

[0025] in, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Represents VNF The quality of service transmission, Indicates the current data transfer expectations, represents a Boolean decision variable.

[0026] Optionally, determining the virtual machine resource sub-model of the network topology structure based on the service demand includes:

[0027] Determine, based on each network node and service requirements, the deployment of VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration request of the VNF instances;

[0028] Determine the total cost required to run the VNF instance on each network node;

[0029] A virtual machine resource sub-model is generated based on the total cost and the second constraint condition; wherein the second constraint condition includes the resource allocation constraint condition of each network node and the deployment order and resource dependency constraint condition of the VNF instance.

[0030] Optionally, the total cost required to run the VNF instance on each network node is expressed as:

[0031] ;

[0032] in, represents the total cost required to run the VNF instance on each network node, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Indicates that the network node Running VNFs on operating costs, Indicates that the network node Running VNFs on Energy cost of VNF Indicates a VNF instance. represents a Boolean decision variable;

[0033] The resource allocation constraint condition of each network node is expressed as:

[0034] ;

[0035] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable;

[0036] The constraints of the deployment order and resource dependency of the VNF instances are expressed as:

[0037] ;

[0038] in, Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable, Indicates the VNF in the service chain Another VNF instance with which there is a resource dependency, Indicates the pre-set VNF and VNF The resource dependency coefficient between Indicates the preset maximum resource sharing amount.

[0039] Optionally, determining a data routing sub-model of the network topology structure based on service requirements includes:

[0040] Determine a data transmission path in a network topology system based on each business application and a business chain corresponding to each business application, wherein the business chain is defined by the service requirement;

[0041] Determine the total cost required for each business link;

[0042] A data routing sub-model is generated based on the total cost and the third constraint condition, wherein the third constraint condition includes the delay and bandwidth constraint conditions of each transmission path.

[0043] Optionally, the total cost required for the service link is expressed as:

[0044] ;

[0045] in, Represents the total cost required for the business link, Indicates the business link. Represents a collection of business links. Indicates the total number of service links. Indicates business applications. Represents a collection of business applications. Indicates the total number of business applications. Indicates the service link The utilization rate, Indicates the service link The transmission cost per unit flow, Indicates the service link infrastructure costs, is a Boolean decision variable;

[0046] The delay constraint condition of each transmission path is expressed as:

[0047] ;

[0048] in, Indicates the business link. Indicates business applications. Indicates business applications An available path for Represents a collection of business applications. Indicates the total number of business applications. It is a business link The delay, Indicates pre-defined business applications The maximum delay, is a Boolean decision variable;

[0049] The bandwidth constraint condition of each transmission path is expressed as:

[0050] ;

[0051] in, Indicates the business link. Indicates business applications. Represents a collection of business links. Indicates the total number of service links. Represents a collection of business applications. Indicates the total number of business applications. Indicates business applications The bandwidth requirement, Indicates the service link The maximum bandwidth, is a Boolean decision variable.

[0052] In a second aspect, an embodiment of the present invention provides a service chain determination device, including:

[0053] A construction module, used to construct a network topology structure; wherein the network topology structure includes at least one network node;

[0054] A determination module, used to determine a business application sub-model, a virtual machine resource sub-model and a data routing sub-model of the network topology structure based on service requirements;

[0055] A generation module, used to generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model;

[0056] The iterative optimization module is used to iteratively optimize the vertical orchestration model to obtain a target service chain.

[0057] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0058] at least one processor; and

[0059] a memory communicatively connected to the at least one processor; wherein,

[0060] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service chain determination method described in any embodiment of the present invention.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the service chain determination method described in any embodiment of the present invention when executed.

[0062] The technical solution of the embodiment of the present invention is to construct a network topology structure, wherein the network topology structure includes at least one network node; determine the business application sub-model, virtual machine resource sub-model and data routing sub-model of the network topology structure based on service requirements; generate a vertical orchestration model according to the business application sub-model, virtual machine resource sub-model and data routing sub-model; iteratively optimize the vertical orchestration model to obtain a target business chain, thereby solving the problems of how to construct a NFV business chain vertical orchestration model in the prior art and how to minimize the network cost of the business application layer, virtual machine resource layer and data routing layer after orchestration, and construct a business application sub-model, a virtual machine resource sub-model and a data routing sub-model by respectively considering the VNF deployment costs of the business application layer, virtual machine resource layer and data routing layer in the NFV environment, and generate a three-layer business chain vertical orchestration model with the total network cost as the optimization target according to the business application sub-model, virtual machine resource sub-model and data routing sub-model, and solve the vertical orchestration model through an optimization algorithm to obtain a target business chain, thereby not only ensuring the accuracy and quality of the target business chain, but also improving the reliability and cost-effectiveness of VNF deployment in business chain orchestration.

[0063] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0065] Figure 1 A flowchart of a service chain determination method provided in Embodiment 1 of the present invention;

[0066] Figure 2 A flowchart of a service chain determination method provided in Embodiment 2 of the present invention;

[0067] Figure 3 A pseudo code schematic diagram using a greedy algorithm for optimization provided in Embodiment 2 of the present invention;

[0068] Figure 4 A pseudo code schematic diagram using genetic algorithm optimization provided in the second embodiment of the present invention;

[0069] Figure 5 A schematic diagram of the convergence of a genetic algorithm provided in the second embodiment of the present invention;

[0070] Figure 6 A schematic diagram of the total network cost of a greedy algorithm and a genetic algorithm under different network node numbers provided in the second embodiment of the present invention;

[0071] Figure 7 A schematic diagram of the total network cost of a greedy algorithm and a genetic algorithm under different edge probability conditions provided in the second embodiment of the present invention;

[0072] Figure 8 A schematic diagram of the structure of a service chain determination device provided in Embodiment 3 of the present invention;

[0073] Fig. 9 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0075] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0076] Embodiment 1

[0077] Figure 1 This is a flow chart of a service chain determination method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of performing service chain orchestration. The method can be executed by a service chain determination device. The service chain determination device can be implemented in the form of hardware and / or software. The service chain determination device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0078] S110: Construct a network topology structure, wherein the network topology structure includes at least one network node.

[0079] Among them, network topology can refer to a virtual network topology, which is a layout of various virtual network nodes interconnected by transmission. Specifically, it can be understood as a specific virtual arrangement of network nodes. A network node can refer to a virtual electronic device connected to the network that can send, receive or forward information through a communication channel.

[0080] Specifically, the network topology describes the connection mode between nodes in the network and the layout of the data transmission path. Common network topologies include star, bus, ring, tree, mesh, etc. When constructing a network topology, at least one network node must be included because it is the basis for forming the network. A network node can specifically refer to a network node on which a VNF instance can be deployed. The node can specifically include a general hardware platform, a virtualized environment, and a device that supports specific VNF functions.

[0081] In this embodiment, you can first construct a A network topology structure of network nodes, where n represents the total number of network nodes in the network topology structure.

[0082] S120: Determine a business application sub-model, a virtual machine resource sub-model, and a data routing sub-model of the network topology structure based on service requirements.

[0083] Among them, service requirements can refer to the expectations and needs of customers or users for service products. These requirements can be functional, performance, reliability, or related to user experience. For each service requirement, a service chain corresponding to the service requirement can be defined, and the service chain contains a series of VNF instances arranged in sequence. The business application submodel can refer to a model for minimizing deployment costs of orchestrating the business application layer; the virtual machine resource submodel can refer to a model for minimizing operating costs of orchestrating the virtual machine resource layer; the data routing submodel can refer to a model for minimizing the total link cost of orchestrating the data routing layer.

[0084] Specifically, the core goal of the business application layer orchestration is to convert high-level service requirements and service quality assurance into a series of VNF instance deployment decisions. When deploying VNFs at this layer, it is necessary not only to calculate the cost of VNF deployment, but also to consider the requirements of each VNF for computing resources and storage resources to ensure that the network nodes can support the deployed services. The resource requirements for deploying VNFs on each network node must be less than or equal to the available resources of the node in the system, and in order to ensure user experience, the service chain must meet certain quality of service (QoS) parameters. Therefore, based on the orchestration of the business application layer, a minimized VNF deployment cost model, namely the business application sub-model, can be established to ensure that the network nodes can support the VNFs corresponding to the deployed service requirements, ensure user experience, and ensure that the data transmission in the service chain can meet user expectations.

[0085] The virtual machine resource layer orchestration is mainly to abstract physical resources and allocate them to VNF tasks and includes the virtual machine migration function. For each network node and service demand, the virtual machine resource layer orchestration decision includes selecting the VNF deployed on a specific node, determining the resource allocation amount of each VNF, and processing the virtual machine migration request. Among them, virtual machine migration can refer to the process of migrating a running virtual machine from one physical host to another; virtual machine migration can improve the resource utilization of network nodes, achieve load balancing, and provide high availability and fault recovery capabilities. However, in order to ensure that QoS is guaranteed, it is also necessary to consider operating costs and energy efficiency. Therefore, the resource allocation of each network node cannot exceed the available amount of the node, and the resource scheduling of the service chain also needs to consider the deployment order and resource dependencies of the VNF. Therefore, based on the orchestration of the virtual machine resource layer, a minimized VNF operating cost model, namely the virtual machine resource sub-model, can be established to ensure that the network node can support the VNF corresponding to the running service demand. Through reasonable resource scheduling, the efficient operation and stability of the service chain can also be ensured.

[0086] The orchestration of the data routing layer is mainly to formulate the data transmission strategy in the network, including the selection of paths and the scheduling of traffic. For each business application and the business chain corresponding to each business application, it is necessary to determine the data transmission path in the network to optimize the overall network performance and cost. Among them, the business chain is defined by the service requirements; business applications can refer to software systems developed to meet specific business requirements, and service requirements are the specific conditions and expectations that these business applications need to meet. In order to ensure the quality of service, each path needs to meet specific delay and bandwidth requirements. Therefore, based on the orchestration of the data routing layer, a model that minimizes the total link cost, namely the data routing sub-model, can be established to optimize the overall network performance and cost to ensure the quality of service.

[0087] In this embodiment, by considering the VNF deployment costs of the business application layer, virtual machine resource layer, and data routing layer in the NFV environment respectively, the business application sub-model, virtual machine resource sub-model, and data routing sub-model of the network topology structure are determined based on service requirements. This not only provides a new research idea for NFV resource configuration optimization, but also more effectively ensures the reliability and cost-effectiveness of VNF deployment in service chain orchestration.

[0088] S130: Generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model, and the data routing sub-model.

[0089] The vertical orchestration model may refer to a three-layer service chain vertical orchestration model consisting of a service application sub-model, a virtual machine resource sub-model, and a data routing sub-model, with the goal of minimizing the total network cost.

[0090] In this embodiment, a three-layer service chain vertical orchestration model is generated by combining the service application sub-model, the virtual machine resource sub-model and the data routing sub-model. Based on the three-layer service chain vertical orchestration model, multiple service chains corresponding to the service applications can be obtained.

[0091] S140: Iteratively optimize the vertical orchestration model to obtain a target service chain.

[0092] The target service chain may refer to a service chain with the smallest total network cost.

[0093] Specifically, the vertical orchestration model can be iteratively optimized by an optimization algorithm, and the algorithm parameters can be adjusted based on the convergence of the selected optimization algorithm, and the minimum total network cost and the corresponding target parameters can be output, and the target service chain can be determined based on the minimum total network cost and the corresponding target parameters. The target parameters can be the number of network nodes, the service link weight, etc. Exemplarily, the established three-layer vertical orchestration optimization problem can be solved by a greedy algorithm and a genetic algorithm respectively, and the algorithm parameters can be adjusted based on the convergence of the algorithm used, and the algorithm with a better orchestration result can be selected, and the corresponding target parameters and the total network cost can be output.

[0094] In this embodiment, a network topology structure is constructed, wherein the network topology structure includes at least one network node; a business application sub-model, a virtual machine resource sub-model and a data routing sub-model of the network topology structure are determined based on service requirements; a vertical orchestration model is generated according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model; and the vertical orchestration model is iteratively optimized to obtain a target business chain, thereby solving the problems of how to construct a NFV business chain vertical orchestration model in the prior art and how to minimize the network cost of the business application layer, the virtual machine resource layer and the data routing layer after orchestration. By considering the VNF deployment costs of the business application layer, the virtual machine resource layer and the data routing layer in the NFV environment respectively, a business application sub-model, a virtual machine resource sub-model and a data routing sub-model are constructed, and a three-layer business chain vertical orchestration model with the total network cost as the optimization target is generated according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model, and the vertical orchestration model is solved by an optimization algorithm to obtain a target business chain, thereby not only ensuring the accuracy and quality of the target business chain, but also improving the reliability and cost-effectiveness of VNF deployment in business chain orchestration.

[0095] Embodiment 2

[0096] Figure 2 This is a flow chart of a service chain determination method provided in Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above embodiment. Figure 2 As shown, the method includes:

[0097] S210: Construct a network topology structure, wherein the network topology structure includes at least one network node.

[0098] S220. Determine a virtual network function VNF instance based on service requirements, determine the total cost required to deploy the VNF instance on each network node, and generate a business application sub-model based on the total cost and the first constraint.

[0099] Among them, the VNF instance may refer to a virtualized instance of a network function running in an NFV (network function virtualization) architecture. These instances implement network functions that were originally completed by dedicated hardware devices through software, such as routing, firewalls, load balancing, etc. The total cost required to deploy a VNF instance may refer to the deployment cost of the VNF instance and the VNF's demand for computing resources and storage resources. Among them, the first constraint includes resource constraints for deploying the VNF instance and service quality constraints. The resource constraint for deploying the VNF instance may refer to that the resource requirement for deploying the VNF on each node must be less than or equal to the available resources of the node; the service quality constraint may refer to that the service chain must meet the pre-set quality of service (Quality of Service, QoS) parameters.

[0100] Specifically, based on the service requirements, the specific requirements of the service chain or service function chain (i.e., business chain) to be deployed are clarified, including traffic processing capabilities, latency requirements, reliability, etc. Different business scenarios have different requirements for network functions. For example, a data center network may require services such as load balancing and firewalls; a mobile network may need to virtualize EPC (Evolved Packet Core) functions. The business chain contains a series of sequentially arranged VNF instances. Based on a series of sequentially arranged VNFs, the total cost required to deploy the VNF instances on each network node is calculated according to the deployment cost of the VNF instances and the VNF's requirements for computing resources and storage resources. , total cost Subject to the first constraint, the minimized VNF deployment total cost model is determined as the business application sub-model.

[0101] In this embodiment, the service chain is defined by the service demand, and then a series of sequentially arranged VNF instances included in the service chain are determined, the total cost required to deploy the VNF instances on each network node is calculated, and the total cost is constrained based on the first constraint condition, thereby ensuring that the network nodes can support the VNFs corresponding to the deployed service demands, ensuring user experience, and ensuring that data transmission in the service chain can meet user expectations; and the minimized VNF deployment total cost model is determined as the business application sub-model, thereby improving the cost-effectiveness of VNF deployment in service chain orchestration.

[0102] S230. Based on each network node and service demand, determine the deployment of the VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration requests of the VNF instances, determine the total cost required to run the VNF instances on each network node, and generate a virtual machine resource sub-model based on the total cost and the second constraint.

[0103] Among them, the second constraint condition includes the resource allocation constraint condition of each network node and the deployment order and resource dependency constraint condition of the VNF instance; the resource allocation constraint condition may refer to that in order to ensure that QoS parameters are met while taking into account the operating cost and energy efficiency, the resource allocation of each network node cannot exceed the available amount of the network node; the deployment order and resource dependency constraint condition of the VNF instance may refer to that the resource scheduling of the service chain also needs to consider the deployment order and resource dependency of the VNF, so the resource dependency coefficient between the VNF instance in the service chain and another VNF instance with which there is a resource dependency, and the product of the Boolean decision variables of the two VNF instances on the network node, is less than or equal to the pre-set or adjusted acceptable maximum resource sharing amount.

[0104] The deployment of VNF instances may refer to installing and configuring a virtualization platform on a network node, creating a virtual machine on the virtualization platform, and allocating an independent virtual machine to each VNF instance; specifically, downloading and installing the software image of the VNF, and performing necessary configuration and parameter settings according to the documentation provided by the VNF. The resource allocation amount of a VNF instance may refer to the proportion of a VNF instance in a network node to the total resources of the node. Processing migration requests for VNF instances may refer to ensuring that in an NFV environment, when a network node fails or resource allocation needs to be optimized, the VNF instance can be smoothly migrated from the current location to the new location. The total cost required to run the VNF instance on each network node may refer to the operating cost and energy cost of running the VNF instance on each network node.

[0105] Specifically, according to each network node and service requirements, the orchestration decision based on the virtual machine resource layer can directly determine the VNF instance to be deployed on a specific node, the resource allocation amount of each VNF instance, and the processing migration request of the VNF instance; then calculate the operation cost and energy cost required to run the VNF instance on each network node, and obtain the total cost required to run the VNF instance on each network node. Total cost Subject to the second constraint, the minimized VNF operating total cost model is determined as the business application sub-model.

[0106] In this embodiment, for each network node and service demand, the deployment of VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration requests of the VNF instances are determined based on the orchestration decision of the virtual machine resource layer. The total cost required to run the VNF instances on each network node is calculated based on the deployment of the VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration requests of the VNF instances. The total cost is constrained based on the second constraint condition to ensure that the network nodes can support the VNFs corresponding to the running service demands. Through reasonable resource scheduling, the efficient operation and stability of the service chain can also be ensured. The minimized VNF operation total cost model is determined as the business application sub-model, which improves the cost-effectiveness of VNF deployment in business chain orchestration.

[0107] S240. Based on each business application and the business chain corresponding to each business application, determine the transmission path of the data in the network topology system, wherein the business chain is defined by the service demand, determine the total cost required for each business link, and generate a data routing sub-model based on the total cost and the third constraint condition.

[0108] Among them, the third constraint condition includes the delay and bandwidth constraints of each transmission path. The delay constraint condition may refer to that the product of the delay of the service link and the Boolean decision variable is less than or equal to the maximum delay of the service application set or adjusted in advance. The bandwidth constraint condition may refer to that the product of the bandwidth requirement of the service application and the Boolean decision variable is less than or equal to the maximum bandwidth of the service link. The transmission path of data in the network topology system may refer to the appropriate path selection algorithm selected according to the specific service requirements of each business application and the corresponding business chain characteristics, under the premise of ensuring that the selected network node has sufficient computing and storage resources and network bandwidth to support data transmission, for example, Bellman-Ford algorithm, Dijkstra algorithm, etc., to calculate the optimal data transmission path. The service chain is defined by the service requirements, which can be understood as the service requirements are the basis and basis for the generation of the service chain. According to different service requirements, it is necessary to select appropriate service functions, determine the service order and dependencies, so as to build a service chain that meets the service requirements. The total cost required for each service link may refer to the sum of the transmission cost of the unit flow on each service link and the infrastructure cost.

[0109] Specifically, each business application corresponds to a business chain. The corresponding business chain can be generated according to the specific service requirements of each business application. Based on the service requirements and the corresponding business chain characteristics, and on the premise of ensuring that the selected network nodes have sufficient computing and storage resources and network bandwidth to support data transmission, the appropriate path selection algorithm is selected, such as the Bellman-Ford algorithm, the Dijkstra algorithm, etc., to calculate the optimal data transmission path; based on the determined data transmission path, the transmission cost and infrastructure cost of the unit traffic on each business link are calculated, and then the total cost C3 required for each business link is obtained. In order to ensure the QoS service transmission quality of the business chain, each path needs to meet specific delay and bandwidth requirements. The total cost C3 is subject to the third constraint condition, and the minimized link total cost model is the data routing sub-model.

[0110] In this embodiment, based on each business application and the business chain corresponding to each business application, the transmission path of data in the network topology system is determined, wherein the business chain corresponding to each business application is defined by the service demand; the total cost required for each business link is determined according to the transmission path of data in the network topology system; the total cost required for each business link is constrained by a third constraint condition to ensure the service transmission quality of the business chain; a data routing sub-model is generated based on the total cost and the third constraint condition; and the cost-effectiveness of VNF deployment in business chain orchestration is improved.

[0111] S250: Generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model, and the data routing sub-model.

[0112] Specifically, the total cost of a three-layer vertically orchestrated network consisting of the business application layer, virtual machine resource layer, and data routing layer is the sum of the deployment costs of each layer, expressed as:

[0113] ;

[0114] The three-layer vertical orchestration model with the optimization goal of minimizing the total network cost is described as follows:

[0115] .

[0116] S260: Iteratively optimize the vertical orchestration model to obtain a target service chain.

[0117] Specifically, model parameters can be pre-set, including: a collection of network nodes , Service Chain , a collection of business links , Business link weight , the service requirements set corresponding to the VNF instance , network nodes Available resources , a collection of business applications , Business Link Maximum bandwidth , Business Applications Maximum delay , at the network node For service needs Deploy VNF Cost , at the network node Running VNFs on Operating costs , at the network node Running VNFs on Energy costs , Business Link Transmission cost per unit flow , Business Link Infrastructure costs For example, Table 1 is a simulation experiment parameter table provided in Embodiment 1 of the present invention. As shown in Table 1, specific values ​​of various parameters may be known a priori according to the actual operating environment.

[0118] Table 1

[0119]

[0120] According to the model parameter settings, the corresponding adjacency matrix is ​​randomly generated according to the network node, and a simulated network topology diagram of three-layer vertically arranged network nodes is constructed. Then, the performance and stability of the greedy algorithm and the genetic algorithm are tested through the complete graph and random weights respectively, and the relationship image between the total network cost and the algorithm parameters of the algorithm used under the current network node is generated to judge the convergence of the algorithm. If the algorithm converges, the total network cost under different network node numbers and different link weights is further calculated. If the algorithm does not converge, the algorithm parameters are adjusted until the algorithm converges under the current number of nodes. By generating a comparison image of the total network cost of the greedy algorithm and the genetic algorithm under different network node numbers and different link weights, the algorithm with a better total network cost is selected, and the number of network nodes, service link weights and total network cost of the corresponding algorithm are output.

[0121] In this embodiment, by considering the VNF deployment costs of the business application layer, virtual machine resource layer, and data routing layer in the NFV environment respectively, a three-layer business chain vertical orchestration model is constructed with the total network cost as the optimization goal, and the model is solved by a greedy algorithm and a genetic algorithm respectively. After analyzing the convergence of the two algorithms, the best one is selected, which further ensures the accuracy and quality of the solution and improves the reliability and cost-effectiveness of VNF deployment in business chain orchestration.

[0122] Optionally, the total cost required to deploy the VNF instance on each network node is expressed as: ;

[0123] in, represents the total cost required to deploy the VNF instance on each network node, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates that the network node For service needs Deploy VNF Cost, VNF Indicates a VNF instance. represents a Boolean decision variable; specifically, The expression is:

[0124] ;

[0125] The resource constraints of the VNF instance are expressed as:

[0126] ;

[0127] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, represents a Boolean decision variable, Indicates service demand, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes;

[0128] The service quality constraint is expressed as:

[0129] ;

[0130] in, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Represents VNF The quality of service transmission, Indicates the current data transfer expectations, represents a Boolean decision variable.

[0131] In this embodiment, the service application sub-model is generated based on the total cost required to deploy the VNF instance on each network node and the first constraint condition:

[0132] .

[0133] Optionally, the total cost required to run the VNF instance on each network node is expressed as:

[0134] ;

[0135] in, represents the total cost required to run the VNF instance on each network node, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Indicates that the network node Running VNFs on operating costs, Indicates that the network node Running VNFs on Energy cost of VNF Indicates a VNF instance. represents a Boolean decision variable; The expression is:

[0136] ;

[0137] The resource allocation constraint condition of each network node is expressed as:

[0138] ;

[0139] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable;

[0140] The constraints of the deployment order and resource dependency of the VNF instances are expressed as:

[0141] ;

[0142] in, Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable, Indicates the VNF in the service chain Another VNF instance with which there is a resource dependency, Indicates the pre-set VNF and VNF The resource dependency coefficient between Indicates the preset maximum resource sharing amount.

[0143] In this embodiment, the virtual machine resource sub-model generated based on the total cost required to run the VNF instance on each network node and the second constraint condition is:

[0144] .

[0145] Optionally, the total cost required for the service link is expressed as:

[0146] ;

[0147] in, Represents the total cost required for the business link, Indicates the business link. Represents a collection of business links. Indicates the total number of service links. Indicates business applications. Represents a collection of business applications. Indicates the total number of business applications. Indicates the service link The utilization rate, Indicates the service link The transmission cost per unit flow, Indicates the service link infrastructure costs, is a Boolean decision variable; The expression is:

[0148] ;

[0149] The delay constraint condition of each transmission path is expressed as:

[0150] ;

[0151] in, Indicates the business link. Indicates business applications. Indicates business applications An available path for Represents a collection of business applications. Indicates the total number of business applications. It is a business link The delay, Indicates pre-defined business applications The maximum delay, is a Boolean decision variable;

[0152] The bandwidth constraint condition of each transmission path is expressed as:

[0153] ;

[0154] in, Indicates the business link. Indicates business applications. Represents a collection of business links. Indicates the total number of service links. Represents a collection of business applications. Indicates the total number of business applications. Indicates business applications The bandwidth requirement, Indicates the service link The maximum bandwidth, is a Boolean decision variable.

[0155] In this embodiment, the data routing sub-model generated based on the total cost required by each service link and the third constraint condition is:

[0156] .

[0157] In a specific embodiment, the SFC (i.e., service chain) includes an initial node and multiple destination nodes, and the minimum Steiner tree construction is involved in determining the multicast routing involved. Therefore, the three-layer vertical orchestration model is an NP-hard problem and the optimal solution cannot be obtained in polynomial time. The present invention can solve the established three-layer vertical orchestration optimization problem through a greedy algorithm and a genetic algorithm respectively, adjust the algorithm parameters based on the convergence of the algorithm used, select the algorithm with better orchestration results, and output the corresponding target parameters and the total network cost.

[0158] Specifically, the specific steps of iteratively optimizing the vertical arrangement model may be:

[0159] 1. Set the model parameters of the three-layer vertical orchestration model, including: the collection of network nodes The number of internal network nodes is set to 10 to 30, and the service chain and Set up one VNF on each node and connect the service links to the As an edge set, use the combination number to generate a fully connected network and convert the business link weight As the edge weight, set to a random number between 0 and 20, the service demand set The number of service requirements is set to 2, and the network nodes Available resources Set to a random number between 100 and 300, a collection of business applications The number of internal business applications is set to 2, and the business link The maximum bandwidth is set to a random number between 100 and 200. Maximum delay Set to a random number between 10 and 15, in the network node For service needs Deploy VNF Cost Set to a random number between 0 and 1, in the network node Running VNFs on Operating costs Set to a random number between 0 and 1, in the network node Running VNFs on Energy costs Set to a random number between 0 and 1, business link Transmission cost per unit flow Set to a random number between 0 and 1, business link Infrastructure costs Set to a random number between 0 and 1;

[0160] 2. Optimize the vertical arrangement model through greedy algorithm and genetic algorithm respectively. Figure 3 A pseudo code schematic diagram using a greedy algorithm for optimization provided in Embodiment 2 of the present invention; Figure 4 A pseudocode schematic diagram of genetic algorithm optimization is provided for the second embodiment of the present invention; under the same number of network nodes, the corresponding adjacency matrix is ​​randomly generated to simulate the real network topology environment, and the performance and stability of the greedy algorithm and the genetic algorithm are tested using a complete graph and random weights. When all network nodes and edges exist, the algorithm needs to process more possible paths and the situation is more complicated, so that the effect of the algorithm can be better evaluated.

[0161] Specifically, taking the number of nodes 30 as an example, Figure 5 A schematic diagram of the convergence of a genetic algorithm provided in the second embodiment of the present invention is shown in FIG. Figure 5 As shown in the figure, the vertical axis of 60-95 represents the total cost of the network, and the horizontal axis of 0-50 represents the population generation number, where the population generation number can refer to the number of iterations of the genetic algorithm. In the initial stage (0-5 generations), the best fitness drops rapidly from about 90 to about 77, indicating that the genetic algorithm can quickly find a solution that is better than the initial population in the initial stage. In the first few generations, the genetic algorithm has extensively explored the search space and quickly eliminated the poor individuals. In the middle stage (6-9 generations), the improvement of fitness has slowed down, but it is still gradually optimizing. During this period, the fitness is stable at about 67, indicating that the algorithm has found relatively good individuals and is continuing to fine-tune. In the stable stage (20-50 generations), the best fitness remains unchanged and stabilizes at about 67, indicating that the algorithm has converged and found a global optimal or near-global optimal solution. In this stage, the algorithm mainly conducts local searches near the existing best solution and does not find a better solution. It can be seen that the genetic algorithm is convergent in the face of this optimization problem.

[0162] 3. Obtain the parameters under the current algorithm convergence conditions. You can simulate the underlying physical network by changing the number of network nodes and selecting a fully connected graph when the number of network nodes is the same. Use the greedy algorithm and genetic algorithm to optimize the objective function respectively. Figure 6 A schematic diagram of the total network cost of a greedy algorithm and a genetic algorithm under different network node numbers provided in the second embodiment of the present invention; Figure 7 A schematic diagram of the total network cost of a greedy algorithm and a genetic algorithm under different edge probabilities provided in the second embodiment of the present invention, wherein different edge probabilities are different link weights. As the number of nodes increases, Figure 6 , Figure 7As shown in the figure, the total network cost of the genetic algorithm and the greedy algorithm presents different trends. First, the performance of the greedy algorithm fluctuates greatly. As the number of nodes increases, the total cost of the greedy algorithm increases significantly under certain node numbers (except 14, 16, and 24), indicating that the greedy algorithm selects a suboptimal path in these cases. Overall, the total cost of the greedy algorithm is not very stable and shows large fluctuations. As the number of nodes increases, more path selections cause the greedy algorithm to fall into the local optimum more easily, resulting in fluctuations and high total costs. In contrast, the performance of the genetic algorithm is relatively stable. Regardless of how the number of nodes changes, the total cost of the genetic algorithm remains at a low level. As the number of generations increases, the genetic algorithm continuously optimizes the path and finds a global optimal solution with a lower cost, so its total cost is low and stable.

[0163] Taking the number of nodes as 30 as an example, the optimal node path obtained by the greedy algorithm is 1→29→10→19→5→15→20→17→13→12→4→2→25→3→22→7→6→27→21→28→14→18→30→26→16, while the optimal path obtained by the genetic algorithm is 1→14→16. At the same time, the total cost of the greedy algorithm is higher and fluctuates greatly under different edge probabilities, that is, it fluctuates greatly under different link weights. After comprehensive consideration, the genetic algorithm can be selected as the solution method for the three-layer service chain vertical orchestration model, and the corresponding model parameters, algorithm parameters, and the total network cost under different node numbers and different edge probabilities are output.

[0164] In this embodiment, after determining the model parameters of the three-layer vertical orchestration model, the established three-layer vertical orchestration optimization problem is solved by the greedy algorithm and the genetic algorithm respectively, and the algorithm parameters are adjusted based on the convergence of the algorithm used. After analyzing the convergence of the algorithm, the optimal algorithm is selected, which further ensures the accuracy and quality of the solution and improves the reliability and cost-effectiveness of VNF deployment in the service chain orchestration; for example, the algorithm with better orchestration results, namely the genetic algorithm, can be selected as the optimization algorithm to effectively avoid falling into the local optimum and output the corresponding target parameters and the total network cost. Furthermore, it is also possible to consider integrating the genetic algorithm with heuristic algorithms such as the greedy algorithm and optimizing the model based on the integrated algorithm.

[0165] Embodiment 3

[0166] Figure 8 This is a schematic diagram of the structure of a service chain determination device provided by Embodiment 3 of the present invention. Figure 8 As shown, the device comprises:

[0167] A construction module 310 is used to construct a network topology structure; wherein the network topology structure includes at least one network node;

[0168] A determination module 320, configured to determine a business application sub-model, a virtual machine resource sub-model, and a data routing sub-model of the network topology structure based on service requirements;

[0169] A generation module 330, configured to generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model;

[0170] The iterative optimization module 340 is used to iteratively optimize the vertical orchestration model to obtain a target service chain.

[0171] Optionally, the determination module 320 is specifically configured to:

[0172] Determine the virtual network function VNF instance based on service requirements;

[0173] Determine the total cost required to deploy the VNF instance on each network node;

[0174] A business application sub-model is generated based on the total cost and the first constraint condition; wherein the first constraint condition includes resource constraints and service quality constraints for deploying the VNF instance.

[0175] Optionally, the total cost required to deploy the VNF instance on each network node is expressed as:

[0176] ;

[0177] in, represents the total cost required to deploy the VNF instance on each network node, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates that the network node For service needs Deploy VNF Cost, VNF Indicates a VNF instance. represents a Boolean decision variable;

[0178] The resource constraints of the VNF instance are expressed as:

[0179] ;

[0180] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, represents a Boolean decision variable, Indicates service demand, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes;

[0181] The service quality constraint is expressed as:

[0182] ;

[0183] in, Indicates service demand, Represents the service requirements set corresponding to the VNF instance. Indicates business applications. Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Represents VNF The quality of service transmission, Indicates the current data transfer expectations, represents a Boolean decision variable.

[0184] Optionally, the determination module 320 is specifically configured to:

[0185] Determine, based on each network node and service requirements, the deployment of VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration request of the VNF instances;

[0186] Determine the total cost required to run the VNF instance on each network node;

[0187] A virtual machine resource sub-model is generated based on the total cost and the second constraint condition; wherein the second constraint condition includes the resource allocation constraint condition of each network node and the deployment order and resource dependency constraint condition of the VNF instance.

[0188] Optionally, the total cost required to run the VNF instance on each network node is expressed as:

[0189] ;

[0190] in, represents the total cost required to run the VNF instance on each network node, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Indicates that the network node Running VNFs on operating costs, Indicates that the network node Running VNFs on Energy cost of VNF Indicates a VNF instance. represents a Boolean decision variable;

[0191] The resource allocation constraint condition of each network node is expressed as:

[0192] ;

[0193] in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable;

[0194] The constraints of the deployment order and resource dependency of the VNF instances are expressed as:

[0195] ;

[0196] in, Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable, Indicates the VNF in the service chain Another VNF instance with which there is a resource dependency, Indicates the pre-set VNF and VNF The resource dependency coefficient between Indicates the preset maximum resource sharing amount.

[0197] Optionally, the determination module 320 is specifically configured to:

[0198] Determine a data transmission path in the network topology system based on each business application and a business chain corresponding to each business application;

[0199] Determine the total cost required for each business link;

[0200] A data routing sub-model is generated based on the total cost and the third constraint condition, wherein the third constraint condition includes the delay and bandwidth constraint conditions of each transmission path.

[0201] Optionally, the total cost required for the service link is expressed as:

[0202] ;

[0203] in, Represents the total cost required for the business link, Indicates the business link. Represents a collection of business links. Indicates the total number of service links. Indicates business applications. Represents a collection of business applications. Indicates the total number of business applications. Indicates the service link The utilization rate, Indicates the service link The transmission cost per unit flow, Indicates the service link infrastructure costs, is a Boolean decision variable;

[0204] The delay constraint condition of each transmission path is expressed as:

[0205] ;

[0206] in, Indicates the business link. Indicates business applications. Indicates business applications An available path for Represents a collection of business applications. Indicates the total number of business applications. It is a business link The delay, Indicates pre-defined business applications The maximum delay, is a Boolean decision variable;

[0207] The bandwidth constraint condition of each transmission path is expressed as:

[0208] ;

[0209] in, Indicates the business link. Indicates business applications. Represents a collection of business links. Indicates the total number of service links. Represents a collection of business applications. Indicates the total number of business applications. Indicates business applications The bandwidth requirement, Indicates the service link The maximum bandwidth, is a Boolean decision variable.

[0210] The service chain determination device provided in the embodiment of the present invention can execute the service chain determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0211] Embodiment 4

[0212] Fig. 9 A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0213] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor 11, and the computer program is executed by the at least one processor 11 so that the at least one processor 11 can execute the method provided by the present invention.

[0214] The processor 11 can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 12 or a computer program loaded from a storage unit 18 into a random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0215] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0216] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a service chain determination method.

[0217] In some embodiments, the service chain determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the service chain determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the service chain determination method in any other appropriate manner (e.g., by means of firmware).

[0218] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0219] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0220] In the context of the present invention, a computer-readable storage medium stores computer instructions, which are used to implement the service chain determination method provided by the present invention when the processor executes. A computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0221] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD monitor)) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0222] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include: a Local Area Network (LAN), a Wide Area Network (WAN), a blockchain network, and the Internet.

[0223] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0224] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0225] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a service chain, characterized in that: include: Constructing a network topology structure; wherein the network topology structure includes at least one network node; Determine the business application sub-model, virtual machine resource sub-model and data routing sub-model of the network topology structure based on the service requirements; Generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model; The vertical orchestration model is iteratively optimized to obtain a target service chain.

2. The method according to claim 1, characterized in that The business application sub-model of the network topology structure is determined based on the service requirements, including: Determine the virtual network function VNF instance based on service requirements; Determine the total cost required to deploy the VNF instance on each network node; A business application sub-model is generated based on the total cost and the first constraint condition; wherein the first constraint condition includes resource constraints and service quality constraints for deploying the VNF instance.

3. The method according to claim 2, characterized in that The total cost required to deploy the VNF instance on each network node is expressed as: ； in, represents the total cost required to deploy the VNF instance on each network node, Indicates service demand, Represents the service requirement set corresponding to the VNF instance. Indicates business applications. Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates that the network node For service needs Deploy VNF Cost, VNF Indicates a VNF instance. represents a Boolean decision variable; The resource constraints of the VNF instance are expressed as: ； in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, represents a Boolean decision variable, Indicates service demand, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes; The service quality constraint is expressed as: ； in, Indicates service demand, Represents the service requirement set corresponding to the VNF instance. Indicates business applications. Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Represents VNF The quality of service transmission, Indicates the current data transfer expectations, represents a Boolean decision variable.

4. The method according to claim 1, characterized in that Determining the virtual machine resource sub-model of the network topology structure based on service requirements includes: Determine, based on each network node and service requirements, the deployment of VNF instances in each network node, the resource allocation amount of the VNF instances, and the processing migration request of the VNF instances; Determine the total cost required to run the VNF instance on each network node; A virtual machine resource sub-model is generated based on the total cost and the second constraint condition; wherein the second constraint condition includes the resource allocation constraint condition of each network node and the deployment order and resource dependency constraint condition of the VNF instance.

5. The method according to claim 4, characterized in that The total cost required to run the VNF instance on each network node is expressed as: ； in, represents the total cost required to run the VNF instance on each network node, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, Indicates a VNF instance. Represents a service chain, Indicates that the network node Running VNFs on operating costs, Indicates that the network node Running VNFs on Energy cost of VNF Indicates a VNF instance. represents a Boolean decision variable; The resource allocation constraint condition of each network node is expressed as: ； in, Indicates a VNF instance. Represents a service chain, Represents VNF of available resources, Represents a network node of available resources, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable; The constraints of the deployment order and resource dependency of the VNF instances are expressed as: ； in, Indicates a VNF instance. Represents a service chain, Represents a network node, Represents a collection of network nodes, Indicates the total number of nodes, represents a Boolean decision variable, Indicates the VNF in the service chain Another VNF instance with which there is a resource dependency, Indicates the pre-set VNF and VNF The resource dependency coefficient between Indicates the preset maximum resource sharing amount.

6. The method according to claim 1, characterized in that The data routing sub-model of the network topology is determined based on the service requirements, including: Determine a data transmission path in the network topology system based on each business application and the business chain corresponding to each business application; Determine the total cost required for each business link; A data routing sub-model is generated based on the total cost and the third constraint condition, wherein the third constraint condition includes the delay and bandwidth constraint conditions of each transmission path.

7. The method according to claim 6, characterized in that The total cost required for the service link is expressed as: ； in, Represents the total cost required for the business link, Indicates the business link. Represents a collection of business links. Indicates the total number of service links. Indicates business applications. Represents a collection of business applications. Indicates the total number of business applications. Indicates the service link The utilization rate, Indicates the service link The transmission cost per unit flow, Indicates the service link infrastructure costs, is a Boolean decision variable; The delay constraint condition of each transmission path is expressed as: ； in, Indicates the business link. Indicates business applications. Indicates business applications An available path for Represents a collection of business applications. Indicates the total number of business applications. It is a business link The delay, Indicates pre-defined business applications The maximum delay, is a Boolean decision variable; The bandwidth constraint condition of each transmission path is expressed as: ； in, Indicates the business link. Indicates business applications. Represents a collection of business links. Indicates the total number of service links. Represents a collection of business applications. Indicates the total number of business applications. Indicates business applications The bandwidth requirement, Indicates the service link The maximum bandwidth, is a Boolean decision variable.

8. A service chain determination device, characterized in that: include: A construction module, used to construct a network topology structure; wherein the network topology structure includes at least one network node; A determination module, used to determine a business application sub-model, a virtual machine resource sub-model and a data routing sub-model of the network topology structure based on service requirements; A generation module, used to generate a vertical orchestration model according to the business application sub-model, the virtual machine resource sub-model and the data routing sub-model; The iterative optimization module is used to iteratively optimize the vertical orchestration model to obtain a target service chain.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the service chain determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the service chain determination method according to any one of claims 1 to 7 when executed.

Images