Joint 3D Trajectory and High-Dimensional PhaseShift Optimization for Reconfigurable Intelligent Surface (RIS)-Assisted UAV Networks: A Deep Reinforcement Learning Approach

  • Iranna Makarabbi Smt. Kamala & Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar-582116
  • Akash , Smt. Kamala & Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar-582116
  • Sneha K Smt. Kamala & Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar-582116
  • Swati H Smt. Kamala & Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar-582116
  • Smita D Smt. Kamala & Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar-582116
Keywords: reconfigurable intelligent surface (RIS), unmanned aerial vehicle (UAV), deep reinforcement learning (DRL), DDPG, energy efficiency, offshore wind, Gulf of Khambhat, 6G, mmWave

Abstract

This paper investigates the joint optimization of a three-dimensional (3D) rotary-wing unmanned aerial vehicle (UAV) trajectory and the high-dimensional phase-shift vector of a large reconfigurable intelligent surface (RIS) deployed on offshore energy infrastructure. Motivated by India’s emerging offshore wind program, a cascaded air-to-ground/ground-to-air channel model and a propulsion-aware energy consumption model are combined to formulate a long-horizon cumulative energy-efficiency (EE) maximization problem under mobility and unit-modulus RIS constraints. A deep deterministic policy gradient (DDPG) framework is adopted to learn continuous control policies for both UAV motion and RIS phases. Representative plots demonstrate convergence behavior, trajectory characteristics, EE scalability with the number of RIS elements, and throughput sensitivity to UAV speed. A real-world case study is constructed around India’s planned 500 MW offshore wind project site in the Gulf of Khambhat (Gujarat), consistent with national policy and tender documents.

References

[1] Ministry of New and Renewable Energy (MNRE), Government of India, “Offshore Wind,” National Offshore Wind Energy Policy context and NIWE nodal agency description, accessed 2026.
Published
2026-04-19
How to Cite
Makarabbi, I., , A., K, S., H, S., & D, S. (2026). Joint 3D Trajectory and High-Dimensional PhaseShift Optimization for Reconfigurable Intelligent Surface (RIS)-Assisted UAV Networks: A Deep Reinforcement Learning Approach. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 12(1), 218-220. Retrieved from https://asianssr.org/index.php/ajct/article/view/1552

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.