MetaLearn: Optimizing routing heuristics with a hybrid meta-learning approach in vehicular ad-hoc networks

Abstract

Routing protocols in vehicular ad-hoc networks (VANETs) are typically challenged by high vehicular mobility and changing network topology. It becomes more apparent as the inherently dispersed nature of VANETs affects the Quality-of-Service (QoS), which makes it challenging to find a routing algorithm that maximizes the network throughput. Integrating Reinforcement Learning (RL) with Meta-Heuristic (MH) techniques allow for solving constrained, high dimensional problems such as routing optimization. Motivated by this fact, we introduce MetaLearn, a technique akin to global search, which employs a parameterized approach to remove future rewards uncertainty as well as vehicular state exploration to optimize the multilevel network structure. The proposed technique searches for the optimum solution that may be sped up by balancing global exploration using Grey Wolf Optimization (GWO) and exploitation through Temporal Difference Learning (particularly Q(λ)). MetaLearn approach enables cluster heads to learn how to adjust route request forwarding according to QoS parameters. The input received by a vehicle from previous evaluations is used to learn and adapt the subsequent actions accordingly. Furthermore, a customized reward function is developed to select the cluster head and identify stable clusters through GWO. An in-depth experimental demonstration of the proposed protocol addresses applicability and solution challenges for hybrid MH-RL algorithms in VANETs.