Intelligent SWIPT-Assisted UAV-IRS Architecture

• 出版年: IEEE Access
• 主要な著者: Yogesh Kumar Rathore, Pragya Swami, Deepak Kumar Dewangan, Aditya Trivedi, Rishav Dubey
• フォーマット: 論文
• 言語: 英語
• 出版事項: IEEE 2025-01-01
• 主題: Deep reinforcement learning; energy harvesting; intelligent reflecting surface; simultaneous wireless information and power transfer (SWIPT); unmanned aerial vehicle; SDG 7
• オンライン･アクセス: https://ieeexplore.ieee.org/document/11130181/

The use of drones (UAVs) is rapidly increasing in areas like surveillance, communication, and monitoring the environment. But one major problem is that their batteries don’t last long. To solve this, drones are now being combined with a smart technology called Intelligent reflecting surfaces (IRS). This setup allows them to collect both energy and data from wireless signals at the same time, using a method known as Simultaneous Wireless Information and Power Transfer (SWIPT). To make this system work better in changing wireless conditions, researchers used an advanced AI method called Deep Reinforcement Learning (DRL). Simulation results showed that this AI-powered system was very efficient at harvesting energy—almost as good as trying every possible option manually providing high energy efficiency. Among the different AI techniques tested, one called Proximal Policy Optimization (PPO) performed the best, beating others like Softmax Deep Double Deterministic Policy Gradient (SD3). This research supports the United Nations Sustainable Development Goals, particularly SDG 7 (Affordable and Clean Energy) by improving energy efficiency, and SDG 9 (Industry, Innovation, and Infrastructure) through intelligent aerial systems.