Deep Learning for Adaptive Modulation and Coding with Payload Length in Vehicle-to-Vehicle Communications Systems

Adaptive modulation and coding (AMC) technique plays an important role in vehicle-to-vehicle (V2V) systems. It enables smart vehicles to keep a good quality of communication for a better driving experience. However, the existing AMC methods for V2V system did not consider multiple scenarios and the amount of calculation is relatively large. In this paper, we propose a simple convolutional neural networks (CNN)-based AMC method which can extract features of channel and noise estimation from receiver, the transmitter will adjust in the light of modulation strategy to ensure the quality of V2V communication. Simulation results reveal that our proposed method performs better in terms of packet error rate (PER), throughput, classification accuracy with a lower prediction time.