AI-Based Energy-Efficient UAV-Assisted IoT Data Collection with Integrated Trajectory and Resource Optimization | IEEE Journals & Magazine | IEEE Xplore

AI-Based Energy-Efficient UAV-Assisted IoT Data Collection with Integrated Trajectory and Resource Optimization


Abstract:

Using unmanned aerial vehicles (UAVs) for data collecting in remote places is advantageous because of UAVs' low cost and extended range mobility. To facilitate the operat...Show More

Abstract:

Using unmanned aerial vehicles (UAVs) for data collecting in remote places is advantageous because of UAVs' low cost and extended range mobility. To facilitate the operation of time-sensitive applications, the acquired data is processed as geographically close to the end user as is practically possible. The suggested paradigm for energy-efficient UAV-assisted Internet of Things data gathering integrates trajectory and resource optimization. The three essential features of the paradigm are data collection, the optimal UAV trajectory, and data scheduling. This work utilizes an innovative data gathering technique and an optimal scheduling paradigm that the authors explicitly devised for intelligent farms. While gathering data, the sensors are arranged in a manner which is entirely random to produce the best clustering that can be generated based on multiple objectives such as distance, latency, energy, trust, and quality of service (QoS). The lion mated with cats optimization (LMCO) is a novel hybrid optimization technique proposed to discover an ideal cluster head. The lion algorithm and the regular cat-mouse-based optimization method are brought together in this model to create the LMCO model. The UAV creates an ideal straight line collision-free path for its trajectory by utilizing the LMCO model and anticipated values for the received signal strength indicator. This enables the UAV to collect data from all clusters in the region that is being investigated. The data is delivered by the UAV to the base station (B5) closest to it. In the second step, the BS will choose the cloud node that is the most easily accessible based on the best possible combination of five factors: power efficiency, response rate, availability, execution time, and QoS. After that, an existing model is contrasted with the proposed model in terms of energy consumption, distance traveled, latency, and response time, among other metrics.
Published in: IEEE Wireless Communications ( Volume: 29, Issue: 6, December 2022)
Page(s): 30 - 36
Date of Publication: 29 December 2022

ISSN Information:


References

References is not available for this document.