Fast routing decision algorithm based on Q learning and LSTM neural network

Abstract

The invention discloses a fast routing decision algorithm based on Q learning and a LSTM neural network. The algorithm is mainly divided into two stages including model training and dynamic routing decision; and the model training stage is mainly used for calculating an optimal or a relatively better path which satisfies a constraint condition according to different QoS requests through a heuristic algorithm. Then, input and corresponding output of the heuristic algorithm are combined to form a training set of a machine learning model, and the training set is taken as a target Q value of different routing to train a decision model. On the basis, when a controller receives a new QoS request, correspondingly, the machine learning model jointly takes the current network state and the constraint condition in the request as input of the model, corresponding Q value can be calculated quickly through the routing decision model in which LSTM and Q learning are combined, and prediction is completed and an optimal path can be output. Time for the process is greatly reduced in comparison with the heuristic algorithm, but the result is very similar.

Description

technical field [0001] The invention relates to a fast routing decision algorithm based on Q learning and LSTM neural network, belonging to the technical field of wireless communication. Background technique [0002] Traditional IP networks integrate control and forwarding in one device, while software-defined networking (Software Defined Networking, SDN) separates control and forwarding. The advantage of this structure is that on the one hand, developers can program the controller through the open northbound interface, which can quickly realize personalized control of the network and meet the different needs of the business on the network; on the other hand, the controller can And the standard OpenFlow protocol communicates with the switch at the data forwarding layer, which reduces the dependence on the underlying forwarding device and makes the deployment more flexible. The present invention mainly utilizes the characteristic that the network control plane and the data p...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a fast routing decision algorithm based on Q-learning and LSTM neural network, which solves the problems of slow convergence and long training process of traditional heuristic algorithms, and can save a lot of time and cost

Images