Precision agriculture and smart farming have received significant attention due to the advancements made in remote sensing technology to support agricultural efficiency. In large-scale agriculture, the role of unmanned aerial vehicles (UAVs) has increased in remote monitoring and collecting farm data at regular intervals. However, due to an open environment, UAVs can be hacked to malfunction and report false data. Due to limited battery life and flight times requiring frequent recharging, a compromised UAV wastes precious energy when performing unnecessary functions. Furthermore, it impacts other UAVs competing for charging times at the station, thus disrupting the entire data collection mechanism. In this paper, a fog computing-based smart farming framework is proposed that utilizes UAVs to gather data from IoT sensors deployed in farms and offloads it at fog sites deployed at the network edge. The framework adopts the concept of a charging token, where upon completing a trip, UAVs receive tokens from the fog node. These tokens can later be redeemed to charge the UAVs for their subsequent trips. An intrusion detection system is deployed at the fog nodes that utilize machine learning models to classify UAV behavior as malicious or benign. In the case of malicious classification, the fog node reduces the tokens, resulting in the UAV not being able to charge fully for the duration of the trip. Thus, such UAVs are automatically eliminated from the UAV pool. The results show a 99.7% accuracy in detecting intrusions. Moreover, due to token-based elimination, the system is able to conserve energy. The evaluation of CPU and memory usage benchmarks indicates that the system is capable of efficiently collecting smart-farm data, even in the presence of attacks.

The convergence of urban informatics and vehicle intelligence has given rise to smart connected vehicles, which have immense potential as edge computing platforms for various applications. However, harnessing the full efficiency of these platforms presents challenges due to the diverse resource requirements, capabilities, and vehicle types, as well as unpredictable vehicle movements. To address these obstacles, a novel task offloading framework based on Digital Twin (DT) technology has been proposed for the Internet of Vehicles (IoV). This DT-based framework capitalizes on historical data and workload predictions to optimize the utilization of edge devices. It streamlines the offloading process by enabling tasks to be accepted and processed by the source vehicle without relying on external devices. The proposed system is designed to learn and forecast vehicle mobility patterns and computation waiting times, facilitating efficient allocation of computing resources at edge locations. Consequently, this approach enhances the quality of service by ensuring swift and effective task processing, irrespective of the vehicles’ unpredictable movements. The proposed approach is compared with a deep sequential model based on reinforcement learning, collaborative multiaccess edge computing (MEC), and energy-efficient MEC via reinforcement learning model. Our method demonstrates an improvement in task execution and overall offloading performance compared to these techniques during peak vehicle arrival rates. Likewise, substantial enhancements are observed in other benchmark parameters.

The Internet of Things (IoT) relies on embedded sensors in pervasive computing devices to interconnect heterogeneous systems, enabling smart environments. Despite these advancements, the Internet of Vehicles (IoV) faces challenges with scarce computational and energy resources, leading to increased service delays and data transfer overheads. Unstable networking and limited local task processing exacerbate these issues, especially when vehicle-to-vehicle connections fail. This research proposes a layered computational framework to support stream processing applications through a collaborative offloading approach. Instead of relying on traditional data re-transmission methods, our solution addresses re-transmission issues in stream processing through data-aware stream offloading and dynamic vehicle selection policy. These algorithms facilitate efficient data streaming among dynamically selected vehicular nodes in IoVs. Simulation-based experiments validate the efficacy of our approach, showing a 33.5 % efficiency improvement compared to traditional methods. Additionally, proposed framework demonstrates improvement in task offloading and execution time, task reception-delivery-failure rate, and energy consumption.