Towards Situation-Aware Meta-Optimization of Adaptation Planning Strategies

Platooning is a promising approach for optimizing the usage of the existing road infrastructure by driving in convoys with low inter-vehicle distances. Platooning coordination fosters advantages like an increased road throughput and reduced fuel consumption. Diverse so-called platooning coordination strategies exist in the literature and according to the no-free-lunch theorem, each has individual assets and drawbacks, making them best applicable for different traffic situations. This paper proposes a layered system model and a feedback loop for meta-optimization of self-adaptive systems. We apply our concept on platooning coordination as a case study and provide an experience report. The platooning coordination strategy is exchangeable and its input parameters are tuned to fit the current traffic situation. Our evaluation results show that the choice of the platooning coordination strategy is situation-dependent. Further, our meta-optimization of the input parameters of these strategies for the traffic situation is favorable compared to a static approach.