Adaptively tuning candidates forwarding set sizes via extended Q-learning in opportunistic vehicular routing schemes

Key Points

• The adaptive tuning of candidate forwarding set sizes leads to improved vehicular routing efficiency and reduced delays.
• Findings show that using extended Q-learning improves performance metrics significantly in dynamic traffic conditions.
• Analysis of routing schemes combines opportunistic methods with adaptive tuning strategies to enhance data delivery rates.
• This approach suggests potential for real-time vehicle communication systems, but may need validation in diverse traffic scenarios.