The Community for Technology Leaders
2016 International Conference on Frontiers of Information Technology (FIT) (2016)
Islamabad, Pakistan
Dec. 19, 2016 to Dec. 21, 2016
ISBN: 978-1-5090-5300-1
pp: 35-39
ABSTRACT
The recent years have witnessed a sharp increase in the use of smart phones for internet applications, video calling, social networking and emails, etc. resulting in an unprecedented increase in the worldwide wireless network traffic. During the deployment of the wireless network topologies the prime focus has to be given towards the requirement for the bandwidth, user capacities and provision of the quality of service (QoS) to the end-users. The next generation wireless networks (3G/4G) provide such services to meet the amplified capacity, higher data rates, seamless mobile connectivity as well as the dynamic ability of reconfiguration and self-organization. However, to achieve the quality of service (QoS) there is a need to make the base-station intelligent instead of operating the network under the control of central backend system. In this paper, different frameworks of Neural networks are used to analyze the traffic behavior over time and a model is proposed serving as an intelligent agent at the base-station level for monitoring the traffic pattern, storing such data in memory and predicting the forthcoming demand from the end-users in a time series manner. The NN frameworks employed include the backpropagation feedforward, nonlinear autoregressive with external input (NARX) and the self-organized map (SOM).
INDEX TERMS
Wireless networks, Quality of service, Artificial neural networks, Forecasting, Bandwidth, Base stations, Data models,Time-series, Data mining, Feedforward, NextGen wireless network, Resource management, Self-organization
CITATION
M. Ahsan Latif, M. Adnan, "ANN-Based Data Mining for Better Resource Management in the Next Generation Wireless Networks", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 35-39, 2016, doi:10.1109/FIT.2016.015
97 ms
(Ver 3.3 (11022016))