QGrid: Q-learning based routing protocol for vehicular ad hoc networks

In Vehicular Ad Hoc Networks (VANETs), moving vehicles are considered as mobile nodes in the network and they are connected to each other via wireless links when they are within the communication radius of each other. Efficient message delivery in VANETs is still a very challenging research issue. In this paper, a Q-learning based routing protocol (i.e., QGrid) is introduced to help to improve the message delivery from mobile vehicles to a specific location. QGrid considers both macroscopic and microscopic aspects when making the routing decision, while the traditional routing methods focus on computing meeting information between different vehicles. QGrid divides the region into different grids. The macroscopic aspect determines the optimal next-hop grid and the microscopic aspect determines the specific vehicle in the optimal next-hop grid to be selected as next-hop vehicle. QGrid computes the Q-values of different movements between neighboring grids for a given destination via Q-learning. Each vehicle stores Q-value table learned offline, then selects optimal next-hop grid by querying Q-value table. Inside the selected next-hop grid, we either greedily select the nearest neighboring vehicle to the destination or select the neighboring vehicle with highest probability of moving to the optimal next-hop grid predicted by the two-order Markov chain. The performance of QGrid is evaluated by using real life trajectory GPS data of Shanghai taxies. Simulation comparison among QGrid and other existing position-based routing protocols confirms the advantages of proposed QGrid routing protocol for VANETs.