Vertical switching method of isomerization network fusion system based on fuzzy neural network

Abstract

The invention provides a heterogeneous network involvement system vertical switch system based on a fuzzy neural network which mainly includes three phases: pre-adjudging pre-treating, fuzzy neural network treating and vertical switch adjudging. Firstly, a signal point need to post-treated is reduced through pre-adjudging and pre-treating, the system cost is reduced; secondly, a group of sluggish level value hy and a residence time value tdw are generated dynamically according with a signal intension difference value DRSSk received by the fuzzy neural network theory colligating two networks, a moving current dirk of a mobile terminal MT relative to WLAN network access point AP, and a movement velocity v and WLAN network present usable band BW; finally, a switch factor is adjudged whether satisfying a switch touching condition according with hy and tdw generated by the fuzzy neural network, and an optimizing network is selected. The method solves problem that MT with multi-network access technique selects the optimizing network in the heterogeneous network involvement system through the vertical switch method.

Description

technical field [0001] The invention is a vertical switching method of a heterogeneous network fusion system, which is based on fuzzy neural network theory and belongs to the technical field of mobile communication. Background technique [0002] The future mobile communication environment will include various wireless access networks with different transmission rates, coverage areas, system capacities and service levels. In order to make full use of the characteristics of different access networks, give full play to the advantages of their respective networks, provide users with ubiquitous services, and meet users' requirements for broadband, personal and intelligent services, the assistance and integration of heterogeneous networks is the focus of attention at present. Mobility management technology, especially handover technology, is one of the key technologies to realize heterogeneous network convergence. In a heterogeneous network, in addition to the handover control w...

AI Technical Summary

Problems solved by technology

The fuzzy logic method has the advantages of easy understanding of the reasoning process, better use of expert knowledge, and lower requirements for samples, but it also has the disadvantages of manual intervention, slow reasoning speed, and low precision, and does not have the ability of adaptive learning. function, and it is difficult to automatically generate and adjust the membership function and fuzzy rules; the neural network method has strong self-learning and association functions, less manual intervention, higher precision, and less use of expert knowledge, but the disadvantages are Can't process and describe fuzzy information, can't make good use of existing experience and knowledge, especially the learning and problem solving has black box characteristics, its work is not interpretable, and it has high requirements for samples

Images