A cooperative neural network approach for enhancing data traffic prediction

Authors : Salihu Aish ABDULKARIM, İsa Abdullahi LAWAL

Pages : 4746-4756

View : 21 | Download : 9

Publication Date : 0000-00-00

Article Type : Research Paper

Abstract :This paper addresses the problem of learning a regression model for the prediction of data traffic in a cellular network. We proposed a cooperative learning strategy that involves two Jordan recurrent neural networks insert ignore into journalissuearticles values(JNNs); trained using the firefly algorithm insert ignore into journalissuearticles values(FFA); and resilient backpropagation algorithm insert ignore into journalissuearticles values(Rprop);, respectively. While the cooperative capability of the learning process ensures the effectiveness of the regression model, the recurrent nature of the neural networks allows the model to handle temporally evolving data. Experiments were carried out to evaluate the proposed approach using high-speed downlink packet access data demand and throughput measurements collected from different cell sites of a universal mobile telecommunications system-based cellular operator. The proposed model produced significantly superior results compared to the results obtained on the same problems from the traditional method of separately training a JNN with FFA and Rprop.
Keywords : Neural networks, cooperative methods, throughput prediction, firefly algorithm, resilient propagation algorithm