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.

We present a novel investigation into the impact of inter-drone interference on delivery efficiencies within multi-drone skyway networks . We conduct controlled experiments to analyze the behavior of drones in an indoor testbed environment. Our study compares performance between solo flights and concurrent multi-drone operations along predefined routes. This analysis captures interference occurring during both flight and at charging stations, providing a comprehensive evaluation of its effects on overall network performance. We conduct a comprehensive series of experiments across diverse scenarios to systematically understand and model the dynamics of inter-drone interference. Key metrics, such as power consumption and delivery times , are considered. This generates a comprehensive dataset for in-depth analysis of interference at both the node and segment levels. These findings are then formalized into a predictive model. The results validate the effectiveness of the developed model, demonstrating its potential to accurately forecast inter-drone interferences.

Precise drone landing remains a persistent challenge due to the high level of accuracy needed. We propose a novel technique that collects actual drone landing data and employs machine learning algorithms to predict errors in autonomous landing. Our model considers variables like battery charge, flight path, altitude, and velocity for prediction. Various trends associated with the drone’s flight and landing are determined and visualised. We propose neural network models that use time series data from the drone’s flight before landing to predict its landing position. Our best model reduced landing error to 2.34 cm, a 7% improvement over the baseline. • A novel framework for predicting drone landing errors precisely. • A comprehensive dataset of real drone landings to ascertain influential factors impacting landing accuracy. • Application of advanced machine learning approaches to forecast the exact landing coordinates of drones.

We conduct a survey on drones used as a service, denoted as drone-as-a-service (DaaS). We develop a novel taxonomy based on DaaS functions, research tasks, and application domains. We provide a discussion on drones and their associated capabilities based on their type of use. We propose a three-layered DaaS system architecture that vertically integratescloudcomputing,drones, andservicesas a reference framework to compare existing drone service implementations. Additionally, we propose a representative uncertainty-aware DaaS model for delivery scenarios, illustrating how service definitions can incorporate both functional and nonfunctional attributes under dynamic environmental conditions. Finally, we identify and discuss future research directions and open problems related to the use of drones for service delivery.

We propose a novel dynamic and immersive 3D framework designed to facilitate the setup and customization of drone scheduling algorithms for evaluating service-based drone delivery systems. This framework features a robust system architecture that supports user-defined behavior logic. It also incorporates real-time data communication protocols for relaying timely instructions to the drones. Additionally, it integrates a comprehensive drone energy consumption model that accurately simulates the physics of drone operations and accounts for both internal and external factors affecting energy usage. The framework includes a sophisticated 3D visualization component, depicting drone deliveries from source to destination through a realistic skyway network within an interactive virtual urban environment. It also enables automated data tracking, which is crucial for testing algorithms and collecting data to support data-driven decisions and optimizations. We evaluate the framework by conducting a comprehensive usability test to assess its user interface and overall user experience. Additionally, we test the framework using a drone swarm to execute delivery requests under both simple and complex energy consumption models. The results show that the framework has a user-friendly interface and effectively supports drone delivery simulations under the complex physics-based energy consumption model.

We propose a failure-resilient Swarm-based Drones-as-a-Service (SDaaS) framework for reliable delivery services. Our framework is specifically tailored to address soft failures, characterized by degradation in drone performance. Failures within drone swarms are an inherent part of real-world scenarios and should be factored to ensure the reliability of services. This framework emphasizes post-assessment of failures as a critical step in preplanning for subsequent service compositions. The framework detects soft service failures from tolerable behavior deviations using margin-aware pruning. Furthermore, a failure severity score is computed using signal-based heuristic. Our aim is to minimize the impact of soft failures on consumers by delivering services within the expected time. This is achieved through formation reordering and service recomposition. Experimental results prove the efficiency of the proposed model with respect to failure correlation scores and service delivery times.

We propose a novel failure-aware reactive UAV delivery service composition framework. A skyway network infrastructure is presented for the effective provisioning of services in urban areas. We present a formal drone delivery service model and a system architecture for reactive drone delivery services. We develop radius-based, cell density-based, and two-phased algorithms to reduce the search space and perform reactive service compositions when a service failure occurs. We conduct a set of experiments with a real drone dataset to demonstrate the effectiveness of our proposed approach.

We propose a novel framework for achieving precision landing in drone services. The proposed framework consists of two distinct decoupled modules, each designed to address a specific aspect of landing accuracy. The first module is concerned with intrinsic errors, where new error models are introduced. This includes a spherical error model that takes into account the orientation of the drone. Additionally, we propose a live position correction algorithm that employs the error models to correct for intrinsic errors in real time. The second module focuses on external wind forces and presents an aerodynamics model with wind generation to simulate the drone’s physical environment. We utilize reinforcement learning to train the drone in simulation with the goal of landing precisely under dynamic wind conditions. Experimental results, conducted through simulations and validated in the physical world, demonstrate that our proposed framework significantly increases landing accuracy while maintaining a low onboard computational cost.

We propose a novel failure-sentient framework for swarm-based drone delivery services. The framework ensures that those drones that experience a noticeable degradation in their performance (called soft failure) and which are part of a swarm, do not disrupt the successful delivery of packages to a consumer. The framework composes a weighted continual federated learning prediction module to accurately predict the time of failures of individual drones and uptime after failures. These predictions are used to determine the severity of failures at both the drone and swarm levels. We propose a speed-based heuristic algorithm with lookahead optimization to generate an optimal set of services considering failures. Experimental results on real datasets prove the efficiency of our proposed approach in terms of prediction accuracy, delivery times, and execution times.

We propose a novel framework for swarm-based drone delivery services with in-flight energy recharging. The framework aims to enhance the delivery time of multiple packages by reducing the number of stops and recharging times at intermediate stations. The proposed framework considers variousintrinsic and extrinsicdelivery constraints. We propose to usesupport droneswhose sole purpose is to recharge other drones in the swarm during their flight. In this respect, we compute the optimal set of optimal support drones to minimize the probability of delivery services and recharging time at the next stations. We also use two settings to position the support drones in a flight formation for comparative purposes. Two novelenergy sharingmethods are proposed, namely, Priority-based and Fairness-based methods. A re-ordering method of the delivery drones is presented to facilitate the in-flight energy composition process. An enhanced A* algorithm is implemented to compose the optimal services in terms of delivery time. Experimental results prove the efficiency of our proposed approach.

We propose a novel framework for the recommendation of swarm-based drone delivery services based on the consumers preferences. We propose a density-based pruning approach that uses the concept of partnerships with charging station providers to reduce the search space of swarm-based drone service delivery providers. A weighted service composition algorithm is proposed that considers the providers capabilities and consumers’ preferences in selecting the best next service. We propose a voting-based recommendation algorithm to select the best providers. We conduct a set of experiments to evaluate the efficiency of the framework in terms of consumer satisfaction, run-time, and search space reduction cost.

We propose a novel framework for the allocation of drone swarms for delivery services known as Swarm-based Drone-as-a-Service (SDaaS). The allocation framework ensures minimum cost (aka maximum profit) to drone swarm providers while meeting the time requirement of service consumers. The constraints in the delivery environment (e.g., limited recharging pads) are taken into consideration. We propose three algorithms to select the best allocation of drone swarms given a set of requests from multiple consumers. We conduct a set of experiments to evaluate and compare the efficiency of these algorithms considering the provider's profit, feasibility, requests fulfilment, and drones utilization level.

We propose a novel framework for composing Swarm-based Drone-as-a-Service (SDaaS) for delivery. Two composition approaches, i.e., sequential and parallel are designed considering the different behaviors of drone swarms. The proposed framework considers various constraints, e.g., recharging time and limited battery to meet delivery deadlines. We propose SDaaS composition algorithms using a modified A* algorithm. A cooperative behavior model is incorporated to reduce recharging and waiting time in a delivery. Experimental results prove the efficiency of the proposed approach.

Swarm of drones are increasingly being asked to carry out missions that can’t be completed by one drone. Particularly, in delivery, issues arise due to the swarm’s limited flight endurance. Hence, we propose a novel formation-guided framework for selecting Swarm-based Drone-as-a-Service (SDaaS) for delivery. A detailed study is carried out to highlight the effect of swarm formations on energy consumption. Two SDaaS selection approaches, i.e. Fixed and Adaptive, are designed considering the different formation decisions a swarm can take. The proposed framework considers extrinsic constraints including wind speed and direction. We propose SDaaS selection algorithms for each approach. Experimental results prove the efficiency of the proposed algorithms.