To search, Click below search items.


All Published Papers Search Service


Clustering Approach for Congestion in Mobile Networks


J. Usha, Ajay Kumar, A.D. Shaligram


Vol. 10  No. 2  pp. 113-118


The fast growing mobile networks demands faster and efficient approaches to handle the congestion in the network. This paper describes the clustering approaches like Partition around Medoids and Nearest Neighbour, used to determine the status of the base stations for mobile traffic load. This enables us to determine the number of channels to be borrowed from the co-channel cells to meet the increase in traffic load. Short-term traffic prediction is obtained by applying the radial basis function network. The traditional methods are not efficient in enhancing the performances because heavily-loaded cells sometimes cannot borrow unused nominal channels from their neighbouring cells which are idle or moderately loaded, as it may lead to cascading effect. The performance of the base stations can be increased if short-term traffic load can be predicted. The predicted results can then be used for channel borrowing from the idle or moderately loaded cells for long term use. These clustering approaches enhance the performance compared to traditional approaches. Simulation results also corroborate that the clustering methods enables the system to work with better performance than the traditional methods.


Cluster, Partition around Medoids, Nearest Neighbour, radial basis function network, base station