Improving QoS in V2X Communication by observing Area-Level Network Nodal Points

Typically, a vehicle's full path may not have access to mobile networks. Moving vehicles may occasionally be unable to maintain constant communication with the center due to high-rise structures and isolated places. One needs to be aware of when they can share the info in a brief amount of time during this period. Strategic sites inside a network where data communication and routing choices are optimized for dependable and efficient transmission are known as Network Nodal Points. Identifying nodal points in 5G networks is crucial for efficient data transfer and enhanced Quality of Service (QoS) in network management. In this paper, we propose a technique that uses data rate prediction in a wireless communication network to locate network nodal points for differentareas on the route. We want to investigate the differences in nodal points along the path between areas to suggest for the improvement. Two specialized methods, XGBoost and Deep Neural Networks (DNN), have been utilized to estimate the data rate factors, such as downlink secondary and main cell modulation and coding scheme (MCS), transport block (TB) size, and number of resource blocks (RBs). We also investigate how precipitation intensity and ping affect network data rate prediction. Intelligent routing in the Vehicle-to-Everything (V2X) network for the future 6G can benefit greatly from the proposed technique.The technique's efficacy is evaluated using the Berlin V2X dataset, and the results demonstrate surprisingly positive trends in the forecast for most of the areas. Our method can help to optimize the network and improve user's predicted QoS in wireless communication networks.