Forecasting of mobile network traffic and spatio–temporal analysis using modLSTM

This paper introduces an innovative system and prediction model for forecasting network traffic in specific geographical locations using historical data. As Internet service providers increasingly rely on data analytics for decision-making, optimized network forecasting faces challenges such as data cleaning and preprocessing. Our approach utilizes an Artificial Recurrent Neural Network-based Modified Long Short-Term Memory model to provide continuous and precise predictions of network traffic. Notably, the proposed model outperforms conventional LSTM models, achieving a 61.9% reduction in Mean Absolute Percent Error. Our approach also integrates an interpolation technique to address the zero-component error. This further enhances the effectiveness and reliability of the model. The model promises to enhance resource utilization and lighten the load on traffic resource provisioning entities, promoting more efficient mobile network traffic management. The low training time of 3.26 min and prediction time of 0.14 s pave the way for real-time implementation of the model for network traffic forecasting and management. The comparative analysis with state-of-the-art models proves the supremacy of the proposed model.