Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/5976
PIRA download icon_1.1View/Download Full Text
Title: Fingerprint type intelligent switching decision method based on fuzzy logic and system
Other Title: 一种基于模糊逻辑的指纹式智能切换判决方法及系统
Authors: Yao, G
Cao, J 
Zhang, C
Issue Date: 15-May-2013
Source: 中国专利 ZL 200910166265.8
Abstract: The invention relates to a fingerprint type intelligent switching decision method based on fuzzy logic. Switching decision is divided into two stages: the first stage is a switching decision study stage during network deployment and the second stage is a switching decision executing stage during network operation. The first stage comprises the following steps of: carrying out fuzzy treatment on accurate measurements of various switching indicators to form a fingerprint; and the set of fingerprints forms a decision reference knowledge base which is also called a fingerprint base. The second stage comprises the following steps of: carrying out fuzzy treatment on real-time input accurate measurements of various switching indicators; carrying out fuzzy logic matching computation with the fingerprints of the decision reference knowledge base; and switching the decision. The invention also discloses a system using the method. The method and the system disclosed by the invention can be used for transferring a part of treating expense after switching the decision from an operating stage to a network deployment stage, and therefore, the real-time treating expense of the operating stage is reduced and the operating speed and efficiency are enhanced.
本发明涉及一种基于模糊逻辑的指纹式智能切换判决方法,将切换判决分解成两个阶段:第一阶段是网络部署时的切换判决学习阶段,第二阶段是网络运行时的切换判决执行阶段;第一阶段包括如下步骤:对各类切换指示器的精确测量值进行模糊处理,形成一条“指纹”;“指纹”的集合构成判决参考知识库,也即“指纹库”;第二阶段包括如下步骤:对实时输入的所有类别切换指示器的精确测量值进行模糊化处理;与判决参考知识库的“指纹”进行模糊逻辑匹配计算;切换判决。本发明还公开了使用上述方法的系统。利用本发明公开的方法和系统,可以把切换判决的一部分处理开销从运行阶段转移到网络部署阶段,从而降低了运行阶段的实时处理开销,提高了运行速度和效率。
Publisher: 中华人民共和国国家知识产权局
Rights: 专利权人: The Hong Kong Polytechnic University.
Appears in Collections:Patent

Files in This Item:
File Description SizeFormat 
ZL200910166265.8.pdf939.46 kBAdobe PDFView/Open
Show full item record

Page views

189
Last Week
1
Last month
Citations as of Apr 14, 2024

Downloads

35
Citations as of Apr 14, 2024

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.