Maximizing VANETs Secrecy Data Rate Using Dueling Double Deep Q-networks

Vehicular Ad Hoc Networks (VANETs) expand the application business of intelligent transportation systems. However, open communication environment issues a new challenge to the security of transmitting data. Data transmissions is vulnerable to malicious attacks, and the jamming attack interrupts the legitimate communications by transmitting jamming signals. To this end, we concern about the security of communication between vehicles and Road-side Units. We propose a novel dueling double deep Q-networks-based secrecy data rate maximization (D3QNSDR) algorithm for VANETs. Under the transmission power constraints, the secrecy data rate is maximally improved by the joint optimization of bandwidth allocation and transmission power. To get the optimal ant-jamming response policy, a decision making of the bandwidth allocation and transmission power is formalized as a Markov Decision Process (MDP) optimization. Then, a novel D3QN algorithm is designed to obtain the solution of the MDP. The experimental results show that the performance of D3QN-SDR outperforms benchmarks in terms of the attack success rate and secrecy data rate