Service function chain deployment method based on reinforcement learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A service function chain and reinforcement learning technology, applied in machine learning, software deployment, program control design, etc., can solve problems that are not very applicable, and achieve the effect of improving the average benefit-cost ratio
Active Publication Date: 2020-12-15
CHONGQING UNIV +1
View PDF4 Cites 16 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
The disadvantage is that these methods are mainly suitable for SFC deployment in offline state, when considering online scenarios, these methods are not very applicable
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0046] see Figure 1 to Figure 2 , a method for deploying a service function chain based on reinforcement learning, comprising the following steps:
[0047] 1) Read the current physical network information and service function chain request (SFC).
[0048] The virtual network function set requested by the service function chain is denoted as V={VNF1, VNF2, VNF3, . . . , VNFn}. n is the number of virtual network functions requested by the service function chain.
[0049] 2) Using the Monte Carlo tree search method and the heuristic measure-local resource capacity to generate a placement scheme for the virtual network function set on the physical network.
[0050] The steps to generate a placement plan for a virtual network function set on a physical network are as follows:
[0051] 2.1) Create the root node of the search tree and initialize the state of the root node. The root node status includes current physical network information and service function chain request;
[...
Embodiment 2
[0084] A method for deploying a service function chain based on reinforcement learning, the method comprising the following steps:
[0085] 1) Initialization program, read the current physical network topology and service function chain request;
[0086] 2) Using the Monte Carlo Tree Search (MCTS) method and the heuristic measure-Local Resource Capacity (LRC) to sequentially generate placement schemes for the VNFs in the SFC on the physical network;
[0087] Such as figure 2 As shown, in step 2), the specific method of "using MCTS and LRC to sequentially generate a placement plan on the physical network for the VNF in the SFC request" includes the following steps:
[0088] 2.1) Create the root node of the search tree and initialize the state of the root node. The root node status includes current physical network information and service function chain request;
[0089] Initialize the number of visits σ of the root node root = 0, initialize the node value n of the root nod...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a service function chain deployment method based on reinforcement learning. The method comprises the following steps: 1) reading a current physical network topology and a service function chain request; 2) generating a placement scheme of the virtual network function set on the physical network; 3) judging whether each virtual network function in the virtual network function set has a server for placing the virtual network function or not, if so, entering the step 4), and otherwise, entering the step 6); 4) judging whether a link meeting the requirement of the placementscheme exists in the physical network or not, if so, forming a link mapping scheme of the service function chain request, and entering a step 5), otherwise, entering a step 6); 5) receiving a servicefunction chain request, deploying the service function chain request according to the placement scheme and the link mapping scheme, updating the physical network topology, and returning to the step 1); and 6) rejecting the service function chain request, and returning to the step 1). According to the invention, the problem of online service function chain deployment in a scene with a known VNF sequence is solved.
Description
technical field [0001] The invention relates to the field of service function chains, in particular to a method for deploying service function chains based on reinforcement learning. Background technique [0002] A Service Function Chain (SFC) consists of a set of linked Network Functions (NetworkFunctions, NFs) that need to be traversed in a specific order by a given network flow. For example, a video-on-demand service may need to pass through a set of NFs (e.g., ). In order to provide various services, infrastructure providers (InPs) usually need to link various NFs to meet different users' demands. Usually, NF is deployed on expensive and short-lived hardware devices, and it is very cumbersome and difficult to dynamically add new functions to these hardware devices. [0003] In recent years, Network Function Virtualization (NFV) has been proposed as a promising networking paradigm, where NF is decoupled from dedicated hardware devices and implemented on a virtualized ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more