Optimizing QoS of the LTE network using a machine-learning-based spatio-temporal distribution and Tabu search metaheuristic

Network traffic congestion is a crucial issue facing mobile operators at various locations depending on the time of day and year. Traffic congestion generally occurs at peak times in urban or suburban areas. This is because the evolved NodeBs’ (eNBs) maximum capacity is very quickly exceeded by the number of users since the resource blocks (RBs) and the bandwith are limited. To best manage network congestion, it is necessary to optimize the allocation of the network resources. The resource allocation problem, which is known to be NPhard, is commonly formulated as an optimization problem under constraints. The objective is to minimize the number of uncovered users for a service required on an eNB in a given scenario. The territory under study is the city of Lomé, the data used for the analysis come from the geographical data of the OpenStreetMap (OSM) database. We propose an approach allowing the dynamic configuration of the network based on a model for predicting users mobility and a heuristic for optimizing Long Term Evolution (LTE) network resources. A Greedy algorithm and a Tabu Search algorithm have been implemented and tested. The results showed the potential of the Tabu Search algorithm to outperform the Greedy algorithm.