Metaheuristic Optimization of Time Series Models for Predicting Networks Traffic

Traffic prediction of wireless networks attracted many researchers and practitioners during the past decades. However, wireless traffic frequently exhibits strong nonlinearities and complicated patterns, which makes it challenging to be predicted accurately. Many of the existing approaches for predicting wireless network traffic are unable to produce accurate predictions because they lack the ability to describe the dynamic spatial-temporal correlations of wireless network traffic data. In this paper, we proposed a novel meta-heuristic optimization approach based on fitness grey wolf and dipper throated optimization algorithms for boosting the prediction accuracy of traffic volume. The proposed algorithm is employed to optimize the hyper-parameters of long short-term memory (LSTM) network as an efficient time series modeling approach which is widely used in sequence prediction tasks. To prove the superiority of the proposed algorithm, four other optimization algorithms were employed to optimize LSTM, and the results were compared. The evaluation results confirmed the effectiveness of the proposed approach in predicting the traffic of wireless networks accurately. On the other hand, a statistical analysis is performed to emphasize the stability of the proposed approach.