Mesfin Leranso - 21DOCS Test Area

Mesfin Leranso

Postdoctoral Fellow

He received his B.Sc. degree in Computer Science from Hawassa University, in 2012, in Ethiopia, and his M.Sc. degree in Information Technology from the University of Madras, 2016, India. He received a Ph.D. degree in Information and Communication Engineering from the University of Electronic Science and Technology of China (UESTC). From 2018 to 2022, he served as a lecturer and member of the postgraduate committee at Wachemo University, Ethiopia. He also worked as a member of the Ubiquitous Wireless Networks research team at UESTC. He reviews many prominent journals, including IEEE Sensors, Journal of Systems Architecture, IEEE Transactions on Wireless Communications, IEEE Transactions on Vehicular Technology, and other conferences. His research interests include:- Unmanned aerial vehicle networks,5G/6G wireless networks, machine learning, vehicular networks, the Internet of Things, and mobile computing.

China

Public Documents 1

UAV-Assisted-Smart Farming for Agricultural Monitoring in a Large Scale WSN area

Mesfin Leranso

and 3 more

September 26, 2022

With the aid of multiple autonomous unmanned aerial vehicles (UAVs), data collection from the large-scale Wireless Sensor Network (WSN) is a highly efficient, but challenging solution. In this paper, to minimize the total energy consumption of both UAVs, and the effective use of sink nodes’ power, we optimize both the number of sink nodes and the trajectories of multiple UAVs in WSN. To do this, the UAV can start from the docking station and come back to the same dock station after the completion of the mission. To increase the lifetime WSN, we specifically use the Genetic Algorithm to choose the number of sink nodes. Then, we utilize a Deep Q-network-based method providing a Markov decision pr to establish all trajectory paths. We can show that our method can expedite the process of identifying the best answers by simulating its performance and contrasting it with other traditional heuristic benchmark techniques.