Committed to connecting the world

CANFIS Model and Telecommunication Network Traffic

​Title

Application of CANFIS Model in the Prediction of Multiple-Input Telecommunication Network Traffic

Abstract

Telecommunication network traffic prediction is an important approach that ensure efficient network planning and management. Telecommunication network traffic is  univariate and prediction models have mostly been concentrated on single-input and single-output traffic. This study proposes a new approach, the multiple-input multiple-output Coactive Neuro-Fuzzy Inference System (CANFIS) model to predict a five time span univariate hourly, daily, weekly, monthly and quarterly time series of 3G downlink traffic simultaneously. In the modelling process several parameters were used in the configuration of the network. The best model for predicting five-input telecommunication traffic was CANFIS (5-2-5) which employed a Bell membership function, Axon transfer function and Momentum learning rule and the membership function per input of 2. The performance of the model was evaluated by comparing the predicted traffic with actual traffic obtained from a 3G network operator and the results indicate a minimum accuracy measure value of MSE = 0.000486, NRMSE = 0.01120 and percent error = 12.33%.

Keywords

3G downlink, CANFIS, multiple-input, multiple-output, prediction, telecommunication network traffic.

Authors

Francis Kwabena Oduro-Gyimah
(Ghana Technology University College, Ghana)

Francis Kwabena Oduro-Gyimah is a lecturer in the Department of Telecommunications Engineering of Ghana Technology University College, Accra, Ghana. He is currently the Coordinator of Faculty of Engineering, Ghana Technology University College, Accra, Ghana. He has over 14 years working experience in the telecommunications industry with the Ghana Telecommunications Company Ltd, Vodafone Ghana and Huawei Technologies (SA) Ltd. He obtained Master of Philosophy in Electrical and Electronic Engineering in 2017, from University of Mines and Technology, Tarkwa, Ghana. He has a Post-Graduate Diploma in Teaching and Learning in Higher Education in 2014, from University of Education, Winneba, Ghana. He was awarded Master of Science in Industrial Mathematics in 2011, from Kwame Nkrumah University of Science and Technology, Kumasi, Ghana and Bachelor of Engineering in Electronics and Communication in 2008 from Kwame Nkrumah University of Science and Technology, Kumasi, Ghana (All Nations University College, Koforidua, Ghana). He obtained his Diploma in Telecommunications Engineering in 2001, from Multimedia University, Melaka, Malaysia. He has supervised 30 undergraduate final-year project work in Telecommunications Engineering. He has published in over 13 journals and conference proceedings with research interest in Telecommunication Network Traffic analysis, Artificial Intelligence, Time series analysis and Forecasting, Microwave Engineering, Performance Modelling and Optimization of Telecommunication Networks and Next Generation Wireless Networks.
 
 
Kwame Osei Boateng
(Kwame Nkrumah University of Science and Technology, Ghana)

Kwame Osei Boateng holds a Doctorate in Systems Engineering from the Graduate School of Engineering and Science of Ehime University, Japan, Masters in Computer Science from the same university and BSc. (Hons.) degree in Electrical/Electronic Engineering from the University of Science and Technology, Ghana. For about three years he was involved in R&D activities for the development of computer-aided design and test of very large scale integrated (VLSI) circuits at Fujitsu Laboratories Ltd., Japan, where he worked as a researcher. Since March 2003, he has been working for Kwame Nkrumah University of Science and Technology (KNUST) first as a senior lecturer, later as an associate professor and currently as a professor. For six years he doubled as an ICT consultant and exercised a technical supervisory role in the design/expansion and maintenance of the university internetwork and information system software development and deployment. He was the first head of the Department of Computer Engineering, KNUST. For two years from February 2016 he was the dean of Faculty of Electrical and Computer Engineering of the College of Engineering. Currently he is the Director of KNUST's Institute of Distance Learning (IDL). He has supervised undergraduate final-year project work of 250 students, 19 second degree theses and three PhD theses. Currently he is supervising three PhD theses. He is a member IEEE and IEEE Computer Society. He was a member of technical programme committees for the 11th IEEE Asian Test Symposium and IEEE VLSI Test Symposium and as member of technical committee and chair of local arrangements for IEEE International Conference on Adaptive Science and Technology. His present research interests are in traffic modelling in telecommunication, test and diagnosis of logic circuits, PLL testing, network security protocols, applications of residual number systems, image processing and smart metering.