Resilient Composition of Drone Services for Delivery
arXiv:2009.09549 · doi:10.1016/j.future.2020.09.023
Abstract
We propose a novel resilient drone service composition framework for delivery in dynamic weather conditions. We use a skyline approach to select an optimal set of candidate drone services at the source node in a skyway network. Drone services are initially composed using a novel constraint-aware deterministic lookahead algorithm using the multi-armed bandit tree exploration. We propose a heuristic-based resilient service composition approach that adapts to runtime changes and periodically updates the composition to meet delivery expectations. Experimental results prove the efficiency of the proposed approach.
arXiv comment48 pages, 16 figures. This is an accepted paper and it is going to appear in Future Generation Computer Systems journal Elsevier. Content may change prior to final publication
References in corpus (6)
- Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges
- Vehicle Routing Problems for Drone Delivery
- Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges
- Bandit Algorithms for Tree Search
- Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (2007)
- A Hybrid Tabu Scatter Search Algorithm for Simulation-Based Optimization of Multi-Objective Runway Operations Scheduling