Optimizing channel allocation techniques with GA-SVM for interference reduction in cellular networks
Sharada Narsingrao Ohatkar, Dattatraya Shankar Bormane, Shraddha V. Bodhe · 2016
In Cellular Communication Network the number of users is tremendously increasing with limited spectrum utilization. So the spectrum has to be efficiently utilized for the increasing numbers of users in the presence of interferences namely co-channel, adjacent channel and co-site. Fixed, Dynamic and Hybrid are the three channel allocation techniques in use for allocating the channels considering different constraints. An optimized Hybrid channel allocation technique with co-channel and co-site constraints is proposed by applying Support Vector Machine (SVM) classification to Genetic Algorithm (GA). GA is an optimization technique based on Darwinian principle of “survival of the fittest”, which finds the solution iteratively. SVM is a classification technique which is best in classifying non-linear dataset. The fitness function for allocating the channel efficiently in cellular network is designed using SVM and optimized by GA focusing on minimizing interference. The GA-SVM results are found to be better than reported literature in form of interfering edges, computation time and Signal to Interference (SIR) ratio.