| Autor: |
Neeraj Joshi, Ishan Budhiraja, Abhay Bansal, Sahil Garg, Bong Jun Choi, Mohammad Mehedi Hassan |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Alexandria Engineering Journal, Vol 107, Iss , Pp 103-116 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
1110-0168 |
| DOI: |
10.1016/j.aej.2024.06.097 |
| Popis: |
Devices that are employed in applications related to the Internet of Things (IoT) are constrained by limited energy resources. Consequently, ensuring a continuous supply of energy while also maintaining uninterrupted connectivity within IoT units (IoTUs) is of great importance. In this particular context, we present a scheme that facilitates both, the transfer of wireless power and the transmission of information for IoTUs along with the capability of harvesting solar energy. This scheme is further supported by the utilization of unmanned aerial vehicles (UAV) and the deployment of reconfigurable intelligent surfaces (RIS) for communication purposes. To be more precise, initially, IoTUs obtain energy from the UAV through the process of wireless power transmission (WPT). Subsequently, in the second stage, the UAV retrieves data from the IoTUs using transmitting information. In order to simplify the complexity of the communication issue, we assume that a solar-powered UAV remains stationary at a predetermined altitude. Our objective is to maximize the energy efficiency (EE) of the entire network by coordinating the scheduling of IoTU energy harvesting (EH) and UAV trajectory optimization. We suggest a multi-agent federated reinforcement learning (MFRL) algorithm that maximizes EE through parameter optimization in order to achieve this goal. By utilizing the collective experiences of several agents and reducing energy usage, this algorithm also improves the overall performance of the system. The proposed technique achieves 96.3% and 97.5% accuracy in communication rounds and RIS elements, with a 9−33% increase in EE compared to the best-performing benchmark scheme. The suggested approach outperforms the benchmark algorithms in terms of EE, trajectory optimization, and learning accuracy, according to simulation findings. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
