A task-aware service dynamic deployment method

Abstract

The application relates to a task-aware service dynamic deployment method, and belongs to the technical field of wireless communication. The method constructs a multifunctional time expansion graph model, and constructs a service request model, a time delay model and an energy cost model of a task on the model, so that effective management and control of network resources are realized. Meanwhile, a dynamic volatile self-adaptive ant colony optimization algorithm is adopted, a heuristic weight is adjusted in real time according to the service quality requirement of the task, path selection and virtual network function deployment are more in line with the task requirement, the utilization rate and service completion rate of network resources are improved, system energy consumption is effectively reduced, and the diversified requirements of different task flows are met.

Description

Technical Field

[0001] This invention belongs to the field of wireless communication technology and relates to a task-aware service dynamic deployment method. Background Technology

[0002] With the rapid development of communication technology, traditional terrestrial networks have achieved high capacity and low latency, making them applicable to scenarios such as the Industrial Internet of Things (IIoT) and the Internet of Vehicles (IoV). However, the infrastructure of traditional terrestrial networks is fixedly deployed, resulting in a lack of flexibility and limited coverage. Compared to terrestrial networks, space and air networks are suitable for large-scale remote data sensing, collection, and dissemination. However, air nodes have scarce storage and computing resources, making it difficult to efficiently handle intensive computing tasks. The construction of space-air-ground networks achieves a comprehensive integration of space, air, and terrestrial networks. These networks fully complement the advantages of the three network segments, providing advantages such as wide coverage, high reliability, strong flexibility, and high bandwidth. However, space-air-ground networks are highly dynamic and heterogeneous, posing significant challenges for network operators in areas such as traffic allocation, routing protocol design, and load balancing. In such large-scale and dynamic network scenarios, traditional proprietary network architectures and dedicated hardware are no longer able to cost-effectively and reliably orchestrate network resources for multi-dimensional service requirements.

[0003] Software-defined networking (SDN) and network function virtualization (NFV) offer effective strategies for managing and controlling large-scale, dynamic, heterogeneous networks. Introducing SDN / VNF into space-air-ground networks is crucial for improving network performance and enhancing management and control flexibility. With the continuous expansion of application scenarios, meeting diverse user QoS requirements in complex and dynamically changing network environments has become a key research focus and challenge. Under the SDN / VNF architecture, Virtualized Network Function (VNF) components are logically and systematically combined to form a Service Function Chain (SFC). Task flows are then guided through the SFC according to specific strategies to provide services to the task flows. For space-air-ground networks, this architecture provides an effective technical approach for achieving dynamic resource management and diversified QoS enhancement.

[0004] In SDN / VNF-based air-space-ground networks, how to deploy Service Controllers (SFCs) to improve resource utilization and ensure diverse QoS requirements for tasks is an important research topic. In terrestrial networks, SFC deployment has been relatively well-established. However, terrestrial SFC deployment only addresses static network topologies. In air-space-ground network environments, effectively coordinating and allocating network resources to meet the QoS requirements of different task flows, especially under high load and dynamic changes, remains a challenge. Therefore, designing a task-aware dynamic service deployment method that can meet diverse user needs while improving task completion rates and reducing overall network costs is of significant research importance. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a task-aware service dynamic deployment method.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A task-aware method for dynamic service deployment, comprising the following steps:

[0008] S1: In the air-space-ground network that combines software-defined networking and network function virtualization, a multi-functional time-spread graph model is constructed to address the dynamic heterogeneity of the network, and a service request model, latency model and energy cost model for tasks are built on this model.

[0009] S2: Construct a task-aware service deployment model in a space-air-ground network;

[0010] S3: A dynamic volatile adaptive ant colony optimization algorithm is proposed, which dynamically adjusts the heuristic weights according to the service quality requirements of the task, so that path selection and virtual network function deployment are more in line with the task requirements.

[0011] Furthermore, in S1, based on the air-space-ground network combining software-defined networking and network function virtualization, a multi-functional time-spread graph model is constructed to address the dynamic heterogeneity of the network, specifically as follows:

[0012] In a space-air-ground network combining software-defined networking and network function virtualization, considering the network state within a time range T, the time range T = [t0, t...] Q The time slots are divided into Q consecutive time slots {τ1, τ2, ..., τ...} q ,…,τ Q}, network topology in time slot τ q The interior can be considered static. In the static time slot τ... qWithin this framework, the connectivity relationships between UAVs, satellites, and ground station nodes are mapped onto a multi-functional time-spread graph. These connections include those between UAVs and satellites, UAVs and ground stations, satellites and satellites, satellites and ground stations, ground stations and satellites, and ground stations and ground stations. This is done within time slot τ. q and τ q+1 Between nodes, there are storage links for storing information from the previous time slot. In this model, UAVs are considered as nodes for collecting ground task information, while ground stations and satellites are considered as task processing nodes. Therefore, in the time-spread graph model, VNFs are deployed on satellite nodes and ground station nodes, and virtualization technology is used to virtualize these nodes into multiple virtual functional nodes. Each VNF is deployed on a different virtual functional node, enabling the description of scenarios where multiple VNFs are embedded in the same node.

[0013] Furthermore, in step S1, based on the constructed functional time extension graph model, a service request model for the task is constructed on this model, specifically as follows:

[0014] Use binary variables To represent in time slot τ q Internal task flow k Is the c-th VNF embedded in the virtual function node? In, it is represented as:

[0015]

[0016] Use binary variables To represent time slot τ q Internal task flow k Has the link (N) been passed? i N j ), represented as:

[0017]

[0018] Furthermore, in step S1, based on the constructed functional time extension graph model, a task latency model and an energy cost model are constructed on this model, specifically as follows:

[0019] The latency for each task mainly considers communication latency, computation latency, and propagation latency.

[0020] For LEO satellite and ground station nodes, the energy consumption mainly considers the energy consumption of the data transceiver and the energy consumption of data processing. For UAV source nodes, which are not embedded VNFs and therefore do not process received tasks, their energy consumption mainly considers the energy consumption of the data transmitter.

[0021] Furthermore, in S2, a task-aware service deployment model is constructed in the air-space-ground network to minimize the total energy cost of the network while satisfying task QoS, specifically as follows:

[0022]

[0023] in, N F,VP ,1q Q,1M M i} represents the task flow l k The c-th VNF Is it embedded in virtual function nodes? middle; E F ,1q Q} represents the task flow l k Whether through link (N) i N j )∈E F , For task flow l k The latency requirements; This represents the total energy cost of a LEO satellite node. This represents the total energy cost of the drone node. E represents the total energy cost of the ground station node; F,AS E represents the transmission link for all input LEO satellite nodes. F,SA Indicates the transmission link of all output LEO satellite nodes; E F,AG and E F,GA These represent the transmission links for all input and output ground station nodes, respectively. Constraint C1 is the capacity constraint of the transmission link; C2 is the computing resource constraint of the node; C3 is the latency constraint; C4 and C5 are the flow conservation constraints; C6 is the VNF deployment constraint; and C7 is the constraint on binary variables X and Y.

[0024] Furthermore, in S3, a dynamic evaporation-based adaptive ant colony optimization algorithm is used, specifically:

[0025] At the start of each iteration, the pheromone evaporation coefficient ρ is dynamically adjusted based on the current iteration number k and the maximum iteration number K. k This allows for increased exploratory activity in the early stages of the search, followed by a focus on the optimal path later on.

[0026] Place M ants at the starting node of the task flow. Based on the QoS heuristic mechanism, its heuristic function can be expressed as:

[0027]

[0028] Where Capacity(i,j) represents the link capacity from node i to node j, used to guarantee bandwidth requirements; Delay(i,j) represents the link transmission delay, mainly considering transmission and propagation delays, used to select low-latency links; Reliability(i,j) represents the reliability of the link transmission task; w capacity w delay With w Reliability Each factor has a weight, and the sum of the weights is 1. By dynamically adjusting the weights, the optimal balance is found among different task flows and network segments, thus completing the selection of the optimal path and the deployment of VNF.

[0029] The beneficial effects of this invention are as follows: By constructing a multifunctional time-spreading graph model and combining software-defined networking and network function virtualization technologies, efficient deployment and management of task flows are achieved in a space-air-ground network. A dynamic volatile adaptive ant colony optimization algorithm is employed to adjust heuristic weights in real time based on the service quality requirements of the task, making path selection and virtual network function deployment more aligned with task needs. This method significantly improves network resource utilization and service completion rate, effectively reduces system energy consumption, and meets the diverse needs of different task flows. With its adaptability and resource optimization effect in dynamic heterogeneous environments, this invention has broad application value in task-intensive scenarios.

[0030] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0031] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0032] Figure 1 This is a network system framework diagram of the present invention;

[0033] Figure 2 This is a multi-functional time-spreading diagram based on a network system framework in this invention;

[0034] Figure 3 A flowchart illustrating the dynamic deployment of services for this invention. Detailed Implementation

[0035] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0036] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0037] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0038] Please see Figures 1-3 The task-aware service dynamic deployment method of the present invention specifically includes the following steps:

[0039] Step 1: In the air-space-ground network that combines software-defined networking and network function virtualization, a multi-functional time-spread graph model is constructed to address the dynamic heterogeneity of the network. On this model, a service request model, a latency model, and an energy cost model for tasks are built.

[0040] Step 1.1: In a space-air-ground network combining software-defined networking and network function virtualization, consider the network state within a time range of T, defining the time range T = [t0, t...]. Q The time slots are divided into Q consecutive time slots {τ1, τ2, ..., τ...} q ,…,τ Q}, network topology in time slot τ q The interior can be considered static. In the static time slot τ... qWithin this framework, the connectivity relationships between UAVs, satellites, and ground station nodes are mapped onto a multi-functional time-spread graph. These connections include those between UAVs and satellites, UAVs and ground stations, satellites and satellites, satellites and ground stations, ground stations and satellites, and ground stations and ground stations. This is done within time slot τ. q and τ q+1 Between nodes, there are storage links for storing information from the previous time slot. In this model, UAVs are considered as nodes for collecting ground task information, while ground stations and satellites are considered as task processing nodes. Therefore, in the time-spread graph model, VNFs are deployed on satellite nodes and ground station nodes, and virtualization technology is used to virtualize these nodes into multiple virtual functional nodes. Each VNF is deployed on a different virtual functional node, enabling the description of scenarios where multiple VNFs are embedded in the same node.

[0041] Step 1.2: Using binary variables To represent in time slot τ q Internal task flow k Is the c-th VNF embedded in the virtual function node? In, it is represented as:

[0042]

[0043] Use binary variables To represent time slot τ q Internal task flow k Has the link (N) been passed? i N j ), represented as:

[0044]

[0045] Step 1.3: The latency of each task mainly considers communication latency, computation latency, and propagation latency, using... Indicates task flow l k Transmission delay on the transmission link, This represents the computational latency for virtual functional nodes to process tasks. Indicates task flow l k The propagation delays are expressed as follows:

[0046]

[0047] in For task flow; k Data size, For the transmission link in the current time slot E F,TE For the transmission link in the multi-functional time extension graph, C congestionThe real-time congestion coefficient ranges from 0 to 1, where 0 indicates no congestion and 1 indicates extreme congestion. k is an adjustment coefficient that can be used to adjust the degree of congestion's impact on communication delay according to the actual situation. Indicates time slot τ q Internal task flow k The amount of computational data for the c-th VNF is The node corresponding to this time slot The computing power, N F,G and N F,S S represents the ground node and LEO satellite node in the multi-functional time-extended diagram, respectively. scheduling This is an intelligent resource scheduling factor that dynamically adjusts the allocation of computing resources based on the real-time idle rate of nodes and the complexity of tasks. Its value ranges from 0 to 2, where 0 indicates extremely unreasonable resource allocation and 2 indicates that optimal resource allocation can greatly improve computational efficiency. F,A Represents the set of air links. Represents time slot τ q Internal task flow k The corresponding transmission links through which the flow occurs The length of T, c is the speed of light in a vacuum, and T topo This is the network topology dynamic coefficient, with a value ranging from 0 to 1. 0 indicates a stable topology, while 1 indicates a significant change in the topology.

[0048] Step 1.4: For LEO satellite nodes, the energy consumption mainly considers the energy consumption of the data transceiver and the energy consumption of data processing. The energy cost of the LEO satellite receiver is expressed as... The energy cost of the transmitter can be expressed as The energy cost of data processing on LEO satellite nodes is expressed as follows: The total energy cost of the LEO satellite is:

[0049]

[0050] For the UAV source node, it is not an embedded VNF, therefore it does not process the received tasks. Its energy consumption primarily considers the energy consumption of the data transmitter, and the energy cost of its transmitter is expressed as... use Let represent the basic energy cost for maintaining UAV operation. Then, the total energy cost of a UAV node is:

[0051]

[0052] For ground nodes, the energy consumed mainly comes from the energy consumption of the data transceiver and the energy consumption of data processing. The energy cost of the ground station receiver is expressed as... The energy cost of the ground station transmitter is expressed as When a ground node can act as a VNF embedded node to process tasks, its energy cost for data processing is expressed as: use This represents the energy cost per unit of computing resources at a ground node. Let $\frac{ ...

[0053]

[0054] Step 1.5: Construct a task-aware service deployment model in the air-space-ground network as follows:

[0055]

[0056] in, N F,VP ,1q Q,1M M i} represents the task flow; k The c-th VNF Is it embedded in virtual function nodes? middle; E F ,1q Q} represents the task flow; k Whether through link (N) i N j )∈E F , For task flow; k The latency requirement; E F,AS E represents the transmission link for all input LEO satellite nodes. F,SA Indicates the transmission link of all output LEO satellite nodes; E F,AG and E F,GA These represent the transmission links for all input and output ground station nodes, respectively. Constraint C1 is the capacity constraint of the transmission link; C2 is the computing resource constraint of the node; C3 is the latency constraint; C4 and C5 are the flow conservation constraints; C6 is the VNF deployment constraint; and C7 is the constraint on binary variables X and Y.

[0057] Step 1.6: For the proposed dynamic evaporation-based adaptive ant colony optimization algorithm:

[0058] (1) Initialization settings:

[0059] The parameters of the dynamic evaporation adaptive ant colony optimization algorithm are set, including the number of ants M, the maximum number of iterations K, the heuristic factor α, the expectation factor β, the initial pheromone concentration τ0, and the initial evaporation coefficient ρ. initialInput the service requests and QoS requirements of the task flow, and define the service function chain for each task flow, i.e., the order of virtual network functions required by the task flow.

[0060] (2) Dynamic adjustment of pheromones:

[0061] At the start of each iteration, the pheromone evaporation coefficient ρ is dynamically adjusted based on the current iteration number k and the maximum iteration number K. k This allows for increased exploratory activity in the early stages of the search, followed by a focus on the optimal path later on.

[0062]

[0063] (3) Path selection and VNF deployment:

[0064] Place M ants at the starting node of the task flow. Based on the QoS heuristic mechanism, its heuristic function can be expressed as:

[0065]

[0066] Where Capacity(i,j) represents the link capacity from node i to node j, used to guarantee bandwidth requirements; Delay(i,j) represents the link transmission delay, mainly considering transmission and propagation delays, used to select low-latency links; Reliability(i,j) represents the reliability of the link transmission task; w capacity w delay With w Reliability Each factor has a weight, and the sum of the weights is 1. By dynamically adjusting the weights, the optimal balance is found among different task flows and network segments, thus completing the selection of the optimal path and the deployment of VNF.

[0067] Ants rely on heuristic information and pheromone concentration τ ij Calculate the path selection probability and select the next node according to the probability to complete the path deployment of the task flow. On the selected path, deploy VNFs according to the computing resources of the nodes, prioritizing nodes with sufficient resources to meet QoS requirements. Record the deployment plan and update the computation and transmission latency of the task flow based on the resources of the selected nodes.

[0068] (4) Pheromone renewal:

[0069] After each ant selects a path and completes VNF deployment, it performs a local pheromone update on the path it has traversed. The pheromone update formula is:

[0070] τ ij =(1-ρ k )×τ ij +Δτ ij

[0071] Where Δτ ij This represents the pheromone increment for the path, which is related to the path's QoS satisfaction and energy consumption.

[0072] After each iteration, all paths found by ants are evaluated, and the optimal path is globally updated with pheromones to increase its pheromone concentration, thereby increasing the preference of subsequent ants for the preferred path.

[0073] (5) Record the optimal path and VNF deployment scheme:

[0074] After each iteration, record the optimal path found in this iteration and its corresponding VNF deployment scheme. If the optimal path satisfies the QoS requirements of the task flow and has the minimum global cost, then save the scheme. Determine whether the convergence condition is met; if it is, end the iteration.

[0075] (6) Output the optimal SFC deployment scheme:

[0076] After the iteration is completed, the final SFC deployment scheme is output, including the optimal path for each task flow, the VNF deployment location on the path, the total resource consumption, and the QoS satisfaction status.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for task-aware service dynamic deployment, characterized in that: The method comprises the following steps: S1: in the space-air-ground network combining software-defined network and network function virtualization, a multi-functional time-expanded graph model is constructed for the dynamic heterogeneity of the network, and a service request model, a delay model and an energy cost model of the task are constructed on the model; S2: a task-aware service dynamic deployment model is constructed in the space-air-ground network to minimize the total energy cost of the network while meeting the QoS of the task, specifically: in, Represents task flow The VNF Is it embedded in virtual function nodes? middle; Represents task flow Whether through the link , For task flow The latency requirements; This represents the total energy cost of a LEO satellite node. This represents the total energy cost of the drone node. This represents the total energy cost of the ground station node; This represents the transmission links for all input LEO satellite nodes. This represents the transmission link for all output LEO satellite nodes; and These represent the transmission links of all input and output ground station nodes, respectively; constraint C1 is the capacity constraint of the transmission link; constraint C2 is the computing resource constraint of the node; constraint C3 is the latency constraint; constraints C4 and C5 are flow conservation constraints; constraint C6 is the VNF deployment constraint; constraint C7 is the constraint of binary variables X and Y. S3: a dynamic volatile adaptive ant colony optimization algorithm is used to solve the task-aware service dynamic deployment model in the space-air-ground network.

2. The method of claim 1, wherein: In S1, a multi-functional time-expanded graph model is constructed for the dynamic heterogeneity of the network in the space-air-ground network combining software-defined network and network function virtualization, specifically: In the space-air-ground network combining software defined network and network function virtualization, considering network state in time range , the time range is divided into continuous time slots , and the network topology is considered static in the time slot ; in the static time slot , the connection relationship of unmanned aerial vehicle, satellite and ground station node is mapped into multi-functional time expansion graph, and the connection relationship includes the connection between unmanned aerial vehicle to satellite, unmanned aerial vehicle to ground station, satellite to satellite, satellite to ground station, ground station to satellite and ground station to ground station; between time slots and , each node has a storage link for saving the information of the last time slot; in the model, the unmanned aerial vehicle is taken as a node for collecting ground tasks, and the ground station and satellite are taken as task processing nodes; In the time-expanded graph model, VNFs are deployed on satellite nodes and ground station nodes, and virtualization technology is used to virtualize these nodes into multiple virtual functional nodes, each VNF is deployed on a different virtual functional node, realizing the description of embedding multiple VNFs in the same node.

3. The method of claim 2, wherein: In S1, according to the constructed functional time-expanded graph model, a service request model of the task is constructed on the model, specifically: Use binary variables To indicate in time slot In-task flow Is the c-th VNF embedded in the virtual function node? In, it is represented as: with binary variables to represent time slots intra-task flow whether the link is passed is represented as: 。 4. The method of claim 3, wherein: In S1, according to the constructed functional time-expanded graph model, a delay model and an energy cost model of the task are constructed on the model, specifically: For the delay of each task, communication delay, calculation delay and propagation delay are considered; For LEO satellites and ground station nodes, the energy consumed includes energy consumption of data transceivers and energy consumption of data processing; For UAV source nodes, not as embedded VNF, do not process the received tasks, the energy consumed includes energy consumption of data transmitters.

5. The method of claim 1, wherein: In S3, a dynamic volatile adaptive ant colony optimization algorithm is used, specifically: At the beginning of each iteration, the pheromone evaporation coefficient is dynamically adjusted according to the current iteration number k and the maximum iteration number K to increase the exploration in the early search and focus on the optimal path in the later search. M ants are placed in the starting node of the task flow; Based on the QoS heuristic mechanism, the heuristic function is represented as: wherein, represents the link capacity from node i to node j, used to guarantee the bandwidth requirement; represents the transmission delay of the link, considering the transmission and propagation delay, used to select the low-delay link; represents the reliability of the link transmission task; , and are the weights of respective factors, the sum of the weights is 1, and the optimal balance between different task flows and network segments is found by dynamically adjusting the weights, and the selection of the optimal path and the deployment of the VNF are completed.

Images