This work proposes an optimal pricing scheme– OPUS– for UAV-as-a-Service (UaaS) using a bargaining game. In a UaaS platform, multiple actors participate– end-users request services, UAV owners lease their UAVs, and a centralized service provider allocates UAVs equipped with heterogeneous onboard sensors. A UAV can support multiple applications by moving across task locations, where both its mobility and the operations of its onboard sensors contribute to overall energy consumption. Consequently, energy use directly affects the price charged to end-users. On the other hand, the service provider aims to maximize revenue, while end-users seek to pay a minimum chargeable price without compromising the service quality. Thus, the challenge is to design an efficient pricing mechanism that balances these conflicting objectives. Therefore, in this work, we aim to design a pricing scheme, OPUS, capable of determining an optimal chargeable price by jointly considering energy consumption, time of use, resource utilization, and UAV reputation. Specifically, time-based pricing accounts for the duration of UAV engagement, resource-based pricing captures operational overheads such as transmission and storage, and reputation-based pricing reflects UAV reliability and past performance. We formulate the problem using the Rubinstein bargaining model to ensure a fair trade off between the service provider's profit and the end-user's satisfaction. Extensive experimental results demonstrate that OPUS outperforms existing schemes– QUEST, TMSC, and Yu's strategy– for UaaS. Specifically, OPUS improves service provider profit by an average of 33.7%.

In this work, we propose a UAV Service Hand-off scheme (Serv-HU) for the UAV-as-a-Service (UaaS) platform to provide seamless UAV services to the end-users. Traditionally, a service provider of a UaaS platform serves a limited application area due to the unavailability of adequate resources such as UAVs. Failing to deliver the service by the service providers for the requested entire application area by the end-user affects the reputation of the service providers. Consequently, the service delivery for a partial application area impacts the overall business, which is unacceptable for a Service-Oriented Architecture. To address this issue, we design a service hand-off scheme that enables the service providers to serve the entire requested application area by the end users with the help of other available service providers. We consider the presence of two types of service providers – Primary (PSP) and Secondary (SSP) in a UaaS platform. We apply a two-stage approach for the UAV service delivery to the end-users. In the first stage, a PSP optimally selects the SSPs for serving the uncovered application area by the PSP. The end-users request the service from the PSP, and on failing to provide the service for the entire application area, the PSP makes the service available from the optimally selected SSPs. In the second stage, we design an optimal pricing strategy that helps in determining the price charged to the end-users considering the involvement of PSPs and SSPs. We apply the Lagrangian multiplier method and Karush-Kuhn-Tucker (KKT) conditions to achieve the outcomes of these two stages. The simulation results depict that the charged price is reduced by$10.3 - 12.7\%$while we apply the optimal SSP selection strategy as compared to the random selection of SSPs.

This work proposes a novel customer segment-based pricing scheme, CuPric, tailored for Mobile Sensors-as-a-Service (mSe-aaS) architecture for IoT Applications. mSe-aaS offers flexible and scalable mobile sensor services for different IoT applications. However, multiple actors involved in an mSe-aaS architecture participate in order to earn profit or access services. Therefore, such financial transactions among the actors lead to the need to develop an optimal pricing scheme. On the other hand, Customer segmentation is necessary to classify users based on their specific usage patterns and resource requirements, ensuring customized service offerings and optimized pricing strategies. CuPric utilizes customer segmentation techniques, including Recency-Frequency-Monetary (RFM) analysis and K-Means clustering. We modify the RFM technique by replacing the monetary component with computation resources fitting into the context of mSe-aaS. Further, we model the proposed pricing problem as an optimization problem and apply the Lagrangian multipliers while ensuring the infrastructure is allocated efficiently, service provider expenses are covered, and the Sensor-Cloud Service Provider (SCSP) profit is maximized. The proposed scheme, CuPric, adapts to varying resource demands and provides insights into user behavior, leading to more strategic infrastructure allocation and enhanced overall service efficiency. Through extensive simulations, we demonstrate that introducing customer segmentation earns at least 37% better profit. Additionally, 95% of users are charged less than half the maximum price charged to any user in the CuPric.

Unmanned Aerial Vehicles (UAVs) are like modern weather surveyors, flying through the skies and collecting valuable atmospheric data with their instrumentation. However, collecting accurate timing data involves a delicate balance between energy conservation and high-speed operation across a variety of computing devices. In order to address this issue, we created a unique Federated Learning computer system designed for the development of weather forecasting using data collected from UAVs. This dynamic variation now reduces operational completion instances through outlier detection and a softmax weight allocation. In the long run, the weather forecast’s overall performance and effectiveness have been greatly improved. A splendid innovation in our framework is creating Federated Weighted Average (FedWAvg) set of rules, specifically designed to deal with delays due to outliers or inaccuracies at some stage in the discussion. FedWAvg allows quick convergence without compromising statistical accuracy, increasing the trustworthiness of weather forecasting in real-world conditions. Putting those advancements together, we have made significant improvements to make weather forecasting more reliable and useful, for the people and the businesses that rely on weather forecasting to get better rewards.

Unmanned Aerial Vehicles (UAVs) play a vital role in modern Internet of Things (IoT) ecosystems by providing services like task offloading. Although simultaneous execution can be done through resource optimization and offloading, it is crucial to choose which task to be executed where considering a trade-off between energy consumption and execution delay. Considering these constraints, in this work, we propose a Federated Learning (FL) aided framework for multi-device task offloading in UAV-enabled edge networks while reducing energy consumption and task execution delay. The proposed approach involves a two-step process to execute tasks on various computing devices. In the first step, a task's priority is determined, considering factors like delay deadlines (maximum allowed delay) and resource requirements which include memory, storage and CPU instructions. In the second step, we leverage FL to dynamically calculate energy and delay of the task for different paradigms. This approach aims to maintain a balance between minimizing energy consumption by the UAV and reducing task execution delay. The effectiveness of the proposed framework is evaluated through experiments in terms of energy efficiency and end-to-end execution delay of the UAVs.

The technological advancements in Unmanned Aerial Vehicles (UAVs) have brought significant changes in various domains including surveillance, agriculture and disaster rescue. The convergence of Machine Learning (ML) and UAV networks contributes significantly to their automation and decision-making capabilities. Traditional ML techniques are centralized, i.e., they face many issues such as privacy due to data sharing, scalability and single-point failure. In this work, we propose a hierarchical decentralized framework for Federated Learning (FL) that addresses all the aforementioned issues. The proposed framework, Cluster Based Pseudo Hierarchical Decentralized Federated Learning (PHDFL), is tailored to UAV networks for learning where the learning and aggregation tasks are distributed among different UAVs in the network. This also introduces the concept of pseudo-hierarchy as all the UAVs are at the same level due to Decentralized Federated Learning (DFL) but the learning happens in a hierarchical manner where the network is divided into clusters and each cluster has a cluster head which in then communicates with other cluster heads. The effectiveness of the proposed framework is evaluated through experiments in terms of learning time, energy consumed and convergence of the model.

In recent times, Unmanned Aerial Vehicles (UAVs) have played a significant role in various fields like agriculture, defense, environmental monitoring, and many more. By minimizing the latency, energy consumption and improving the quality of services (QoS) while offloading the tasks, UAVs have played an outstanding role in the Internet of Things (IoT). Despite having a huge advantage, as the UAVs have limited computation, they cannot handle all the tasks that require intensive computation. To tackle the above problem, we have adopted the Deep Reinforcement Learning (DRL) technique in the UAV network, which helps in handling computationally expensive tasks by sharing the workload among the UAVs. The DRL-based strategy helps in reducing latency and energy consumption while maximizing the resource utilization of UAVs. Experiments have shown the significance of the adopted DRL strategy in reducing energy consumption by at least 16% compared to traditional algorithms.