Self-Adapted Resource Allocation in V2X Communication

The intelligent transportation system (ITS) along with vehicular communications are making our daily life safer and easier e.g., saving time, traffic control, safe driving, etc. Many transmission mode selection resource allocation schemes mitigating to full the quality of service requirements minimum latency negligible interference. For message far away vehicles realistic cellular link is a bottleneck, however, for nearby devices, safety critical information needs V2V links. Reinforcement learning (RL) Deep (DL) have reshaped communication in new model where act like human beings take their decisions autonomously without intervention. In work, we investigate Vehicle-to-vehicle (V2V) Vehicle-to-infrastructure each takes decision find optimal subband power level. We investigated case connected Vehicle-to-Infrastructure (V2I) satisfying stringent constraints while minimizing exploit RL DL develop highly performance agents effectively learn select share spectrum V2I.