Downlink Throughput Prediction in LTE Cellular Networks Using Time Series Forecasting

Abstract

Long-Term Evolution (LTE) cellular networks have transformed the mobile business, as users increasingly require various network services such as video streaming, online gaming, and video conferencing. A network planning approach is required for network services to meet user expectations and meet their needs. The User DownLink (UE DL) throughput is considered the most effective Key Performance Indicator (KPI) for measuring the user experience. As a result, the forecast of UE DL throughput is essential in network dimensioning for the network planning team throughout the network design stage. The proposed system employs several KPIs to predict UE DL throughput by combining machine learning and deep learning framework for a time series forecasting rather than the traditional statistical technique based on downlink traffic only. The proposed scheme identifies the most significant KPIs that affect UE DL throughput and provides accurate results based on prediction.