A Hybrid CNN–LSTM Deep Learning Framework for URLLC-Enabled Intelligent V2X Communication Systems

Safe and efficient vehicular networks in modern Intelligent Transportation Systems (ITS) rely heavily on ultra-reliable and low-latency communication (URLLC) as a fundamental requirement. To address this, researchers propose a hybrid deep learning–based Vehicle-to-Everything (V2X) framework that integrates Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks to enhance real-time decision-making. The framework initially collects heterogeneous V2X data from Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), Vehicle-to-Pedestrian (V2P), and Vehicle-to-Network (V2N) sources, including GPS coordinates, vehicle speed, Received Signal Strength Indicator (RSSI), and channel state information. Data preprocessing employs normalization techniques such as Min–Max scaling, sliding window methods, dimensionality reduction, and time-series transformations to generate model-ready inputs. CNN components extract spatial features such as road layouts, vehicle density, and interference patterns, while LSTM modules capture temporal dynamics including signal fluctuations, handover delays, and congestion evolution. The proposed framework was evaluated using a dataset of 10,000 V2X communication samples collected at a sampling frequency of 10 Hz to capture dynamic vehicular network conditions. By fusing spatial and temporal representations, the framework predicts optimal communication strategies, enabling adaptive routing, dynamic power control, and stable link selection. This hybrid approach improves computational efficiency and predictive accuracy, supporting autonomous driving, enhanced traffic management, real-time safety, and congestion forecasting in next-generation V2X networks.