Vertical switching method based on neural network multi-attribute judgment

Abstract

The invention discloses a vertical switching method based on neural network multi-attribute judgment, and particularly relates to the technical field of seamless switching of communication networks. The method comprises the following steps: setting a network environment in which five types of networks, namely UMTS, GSM, WLAN, 4G and 5G, coexist, constructing respective three-layer BP neural network models, and designing structures of an input layer, a hidden layer and an output layer; enabling the terminal to collect values of the six attribute elements, inputs the values into the model for training, numerical approximation and prediction; finally performing performance evaluation on the whole network to obtain related numerical values such as a switching success rate and the like, and providing feedback information for an operation process of the whole algorithm according to an evaluation analysis result. According to the method, the success rate of vertical switching between the wireless networks can be effectively improved, the ping-pong effect is reduced, seamless switching between the multi-element heterogeneous networks is successfully achieved, and high-quality operation ofthe wireless networks in the whole heterogeneous convergence network environment is effectively maintained.

Description

technical field [0001] The invention belongs to the technical field of seamless switching of communication networks, and in particular relates to a vertical switching method based on multi-attribute judgment of a neural network in a heterogeneous fusion network. Background technique [0002] In recent years, with the rapid development of wireless communication network technology and the rapid improvement of network access technology under the framework of heterogeneous integration, many different forms of wireless networks exist at the same time. Different networks not only compete with each other but also complement each other, resulting in the coexistence of various network relations. In order to adapt to the needs of users at different levels and the development of various types of services, wireless networks of different architectures have formed a multiple comprehensive network under the state of heterogeneous integration. Among them, the WLAN network and the Cellular (...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problems existing in the prior art, the present invention proposes a vertical handover method based on neural network multi-attribute judgment, which solves the problem of low handover success rate and unstable performance of the vertical handover algorithm under the condition of heterogeneous converged network environment

Images