Applying artificial intelligence for cellular networks optimization

2019

Closed access Metadata (CSL-JSON)
DOI 10.1117/12.2536857
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Artificial Intelligence may be used to solve complex technical and practical problems. Moreover, such Artificial Intelligence techniques as Fuzzy Systems, Artificial Neural Networks, Evolutionary and Genetic Algorithms have a great potential in providing optimization, prediction and management of communication system in a dynamic wireless environment. Artificial Intelligence approach provides optimized results in a challenging task of the call admission control process in cellular networks. The paper proposes a methodology for developing a genetic neuro-fuzzy controller for call admission in cellular networks. A structure of the access fuzzy controller was suggested. Linguistic variables, their terms as well as membership functions for input and output values were determined. A rule base was proposed. A Neuro-fuzzy System on the base of the fuzzy-controller was designed and simulated. A genetic algorithm was proposed for optimizing the rule base.