Energy-Predictive Planning for Optimizing Drone Service Delivery

Energy-Predictive Planning for Optimizing Drone Service Delivery Guanting Ren, Babar Shahzaad, Balsam Alkouz, Abdallah Lakhdari, Ath-man Bouguettaya An Energy-Predictive Drone Service (EPDS) framework to minimize the average delivery time. A heuristic-based optimization for drone services composition to reduce recharging and waiting time. Abstract We propose a novel Energy-Predictive Drone Service (EPDS) framework for efficient package delivery within a skyway network. The EPDS framework incorporates a formal modeling of an EPDS and an adaptive bidirectional Long Short-Term Memory (Bi-LSTM) machine learning model. This model predicts the energy status and stochastic arrival times of other drones operating in the same skyway network. Leveraging these predictions, we develop a heuristic optimization approach for composite drone services. This approach identifies the most time-efficient and energy-efficient skyway path and recharging schedule for each drone in the network. We conduct extensive experiments using a real-world drone flight dataset to evaluate the performance of the proposed framework. Introduction The Internet of Things (IoT) has become more mature and widespread, largely thanks to advancements in software and hardware technologies. Drones serve various purposes, including aiding in farm irrigation, capturing aerial imagery for entertainment, and facilitating the delivery of retail goods (Mohsan et al. (2023)). Drone delivery services are increasingly important because they can offer faster delivery times, lower operational costs, and potentially a greener alternative to traditional delivery methods (Eskandaripour and Boldsaikhan (2023)). Several key challenges, however, hinder the wider adoption of drones for delivery services (Sah et al. (2021)). A primary challenge is constrained battery capacity, which limits a drone's flight range (Huang et al. (2022)). With current lightweight batteries, delivery drones are not well-suited for long-distance trips, particularly when carrying heavy payloads. As a result, some studies propose using drones only for last-mile deliveries (Garg et al. (2023)). Despite these limitations, drones remain a clean, cost-effective, and ubiquitous alternative to land-based delivery in both urban and rural areas (Attenni et al. (2023)).