Development of an ANFIS-based QoS model for a GSM service provider (MTN Nigeria Kano region network)

Author

Garba, S. ; Bajoga, B.G. ; Mu´azu, M.B. ; Dajab, D.D. ; Abdu-Aguye, U.

Author_Institution

Dept. of Electr. Eng., Ahmadu Bello Univ., Zaria, Nigeria

fYear

2011

fDate

24-26 Nov. 2011

Firstpage

165

Lastpage

173

Abstract

MTN Nigeria is one of the leading GSM service providers in Nigeria with 40 million subscribers and as such Quality of Service (QoS) is of vital importance. Due to the mobility of subscribers and the complexity of radio waves in propagation, the radio part (GSM Capacity) is mostly the decisive factor affecting the Quality of Service of the GSM network. GSM Logical Control channels Data obtained from May 2006 to December 2009 from MTN, Kano region, were partitioned into training data set (142 data pairs represents 75% of the entire data) and checking data set (48 data pairs represents 25% of the entire data). Data obtained from January to March 2010 were used as validation data. The developed Adaptive Neuro Fuzzy Inference System (ANFIS) model was tested for Quality of Service on Logical Control Channel variables using Average Percentage Error (APE) and Performance comparison of data distribution.

Keywords

adaptive systems; cellular radio; fuzzy reasoning; quality of service; radiowave propagation; telecommunication computing; wireless channels; ANFIS model; ANFIS-based QoS model; APE; GSM logical control channel; GSM service provider; MTN Nigeria Kano region network; adaptive neurofuzzy inference system model; average percentage error; data distribution; decisive factor; quality of service; radiowave propagation; subscriber mobility; Adaptation models; Data models; GSM; Mathematical model; Quality of service; Training; Training data; ANFIS; APE; Logical Control Channels; Mobility; QoS;

fLanguage

English

Publisher

ieee

Conference_Titel

Adaptive Science and Technology (ICAST), 2011 3rd IEEE International Conference

Conference_Location

Abuja

Print_ISBN

978-1-4673-0758-1

Type

conf

DOI

10.1109/ICASTech.2011.6145169

Filename

6145169