PSO of Neural Networks to Predict Busy Times of Cellular Traffic for Assignment to TV Idle Channels by Cognitive Radio

摘要

Kenya has identified radio spectrum as a keydriver in its development. Yet, globally, radio spectrum isinefficiently utilized due to ITU's static spectrum allocation.In Kenya, mobile operators are running short of bandwidthdue to deployment of 4G services, which enable superfastmobile broadband/internet. In the USA and UK, FCC andOfcom, respectively, have made effort to allow opportunistic'poaching' of licensed spectrum as long as communication oflicensed user is not interfered with. This has focusedresearch on use of cognitive radio, which would use itssensor networks to establish which TV channels are idle inorder to allocate them temporarily to cellular networks.Enabling the cognitive radio to predict which channels shalllie idle at what times introduces better planning and moretemporally-efficient allocation. This study explores theviability of predicting the times of mobile telephony trafficjam for a mobile service operator with poor QoS ratingwithin a cell of perennial mobile traffic jam in order toexplore whether those times can map well with the TVspectrum holes. The times of the TV spectrum holes shall bedetermined in a later study.