Virtual network mapping method and model training method and device thereof

Abstract

The invention provides a virtual network mapping method and a model training method and device thereof, and the model training method comprises the steps: obtaining a training set according to the node information in a physical network, preprocessing the training set, and obtaining index information of the node information in the training set; inputting a preprocessed training set into a coding unit of a model for training to obtain a first training result; inputting the first training result into a decoding unit of the model for training to obtain a second training result; calculating a lossvalue of the model by using a preset loss function according to the second training result; updating model parameters through the loss value; judging whether the loss value meets a preset loss threshold value or not; if yes, training is ended, and a model used for virtual network mapping is obtained. Through the plurality of encoders in the encoding unit and the plurality of decoders in the decoding unit and by adopting a reinforcement learning algorithm for training, the mapping effect of the model on the virtual network is improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a virtual network mapping method and its model training method and device. Background technique [0002] Network virtualization is a technology that simulates multiple logical networks in a physical network. With the development of artificial intelligence technology, algorithms in the field of machine learning can be used to realize network virtualization, thereby solving the problem of virtual network mapping. For example, RNN (Recurrent Neural Network, cyclic neural network) is used to extract physical network information, and sequentially output mapping results, which can simulate the mapping process of the actual virtual network. However, the existing models can only process serially when extracting the information of each node in the physical network, and the efficiency is low. At the same time, due to too many neurons in the existing model, gradient disappearance or ...

AI Technical Summary

Problems solved by technology

However, the existing model can only process serially when extracting the information of each node in the physical network, and the efficiency is low

At the same time, due to too many neurons in the existing model, gradient disappearance or gradient explosion is prone to occur, which affects the final virtual network mapping effect of the model.

Images