Abstract
This research explores the intelligent integration and optimal scheduling of hybrid renewable energy sources—solar, wind, thermal, microwave, and fuel cell—for electric vertical take-off and landing (eVTOL) aircraft and satellite systems. With growing interest from organizations such as NASA, the Canadian Space Agency (CSA), Bombardier, and Boeing, the demand for weight-efficient, AI-driven energy autonomy has become critical. Leveraging cutting-edge deep learning architectures including deep reinforcement learning, federated learning, and neural combinatorial optimization, this study proposes a unified model to enhance the energy efficiency of solar-powered UAVs, wind-harvesting aerial vehicles, and deep-space exploration platforms. Our methodology is grounded in an in-depth review and synthesis of the most recent and impactful research (2020–2024) across IEEE and related peer-reviewed journals, including ten key papers that span energy optimization, trajectory scheduling, federated UAV learning, and hybrid microgrid control.
Keywords
References
- S. Agarwal et al., IEEE Access, 2023 – Fuel Cell-Solar UAV Microgrid Optimization.Google Scholar ↗
- Li Dong et al., arXiv, 2024 – Deep Reinforcement Learning for UAVMEC Scheduling.Google Scholar ↗
- Tengchan Zeng et al., arXiv, 2020 – Federated Learning in UAV Swarms.Google Scholar ↗
- Yaxiong Yuan et al., arXiv, 2020 – Actor-Critic Scheduling Optimization.Google Scholar ↗
- Aidin Ferdowsi et al., arXiv, 2020 – Neural DRL for Age-Optimal UAV Networks.Google Scholar ↗
- T. Dragicevic et al., IEEE TPEL, 2019 – AI-Aided Power Electronic Reliability.Google Scholar ↗
- Safae Bourhnane et al., SN Applied Sciences, 2020 – ML for EnergyPrediction.Google Scholar ↗
- Sidra Kanwal et al., IJEPES, 2021 – Weighted Scheduling in Microgrids.Google Scholar ↗
- P. K. Mohanty et al., IEEE POWERCON, 2020 – AI-Based Energy Management.Google Scholar ↗
- Isabella Foster, EIT, 2021 – Smart Grid Enhancement via ML.Google Scholar ↗