Path selection method for software defined network based on Q learning

Abstract

The invention discloses a path selection method for a software defined network based on Q learning. A software defined network infrastructure layer receives a service request, constructs a virtual network, and allocates a proper network path to complete the service request, and the path selection method is characterized in that the proper network path is acquired in a Q learning mode: (1) setting a plurality of service nodes P on the constructed virtual network, and correspondingly allocating corresponding bandwidth resources to each service node; (2) decomposing the received service request into available actions a, and attempting to select a path capable of arriving at a terminal according to eta-greedy; (3) recording data summarization as a Q value table, and updating the Q value table; and (4) finding the proper path according to recorded data in the Q value table. According to the path selection method disclosed by the invention, a network path with short forwarding path, little time consumption, little bandwidth resource occupation and suitable for dynamic and complex networks can be found by the Q learning manner, and meanwhile other service requests can be satisfied as many as possible.

Description

technical field

[0001] The invention relates to the field of communication technology, in particular to a Q-learning-based path selection method for a software-defined network, which can find the most suitable service path to satisfy a service request on the basis of an existing virtual network. Background technique

[0002] In recent years, people have diversified requirements for the types of information obtained in the network, and the requirements for the quality and security of information obtained in the network have also been continuously improved. The amount of information carried by various networks is rapidly expanding, the scale of the network is constantly expanding, and more and more users, applications, and services are connected to the network. Network construction, expansion, optimization, and security work have become important contents of network construction and maintenance. However, in the face of these complex and changing needs, the original Internet a...

Examples

Embodiment 1

[0026] Embodiment one: see figure 1 , 2As shown, a path selection method for software-defined networks based on Q-learning, the software-defined network infrastructure layer receives service requests, and the software-defined network controller constructs a virtual network according to the required service components and combination methods, and allocates suitable The network path completes the service request and finally reaches the terminal, and the suitable network path is obtained through the Q learning method in reinforcement learning, and the method steps are:

[0027] (1) Set up several service nodes P on the established virtual network, and each service node is assigned a corresponding bandwidth resource B;

[0028] (2) Classify the received service requests into actions a that can be taken, and try to select each path that can reach the terminal according to the ε-greedy strategy, that is, each action a passes through the corresponding service node P to complete the ...

technical field

[0001] The invention relates to the field of communication technology, in particular to a Q-learning-based path selection method for a software-defined network, which can find the most suitable service path to satisfy a service request on the basis of an existing virtual network. Background technique

[0002] In recent years, people have diversified requirements for the types of information obtained in the network, and the requirements for the quality and security of information obtained in the network have also been continuously improved. The amount of information carried by various networks is rapidly expanding, the scale of the network is constantly expanding, and more and more users, applications, and services are connected to the network. Network construction, expansion, optimization, and security work have become important contents of network construction and maintenance. However, in the face of these complex and changing needs, the original Internet a...

Examples

Embodiment 1

[0026] Embodiment one: see figure 1 , 2As shown, a path selection method for software-defined networks based on Q-learning, the software-defined network infrastructure layer receives service requests, and the software-defined network controller constructs a virtual network according to the required service components and combination methods, and allocates suitable The network path completes the service request and finally reaches the terminal, and the suitable network path is obtained through the Q learning method in reinforcement learning, and the method steps are:

[0027] (1) Set up several service nodes P on the established virtual network, and each service node is assigned a corresponding bandwidth resource B;

[0028] (2) Classify the received service requests into actions a that can be taken, and try to select each path that can reach the terminal according to the ε-greedy strategy, that is, each action a passes through the corresponding service node P to complete the ...

Images