Reconfigurable Intelligent Surfaces

Also known as RIS

Overview

Reconfigurable intelligent surfaces use controllable electromagnetic elements to shape wireless propagation, helping extend coverage, focus signals, and support tasks such as localization and edge computing. Researchers optimize element phases, amplitudes, placement, and beamforming through mathematical methods such as alternating optimization, as well as deep and multi-agent reinforcement learning, graph neural networks, and learned channel estimation. Designs range from passive and active surfaces to simultaneous transmitting-and-reflecting and stacked metasurfaces, including systems that perform signal processing in the wave domain. A central challenge is making control scalable and reliable when channel-state information is costly or unavailable, while accounting for hardware constraints, mobility, energy use, and fair resource allocation.

Latest papers

CardsList

32 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Securing SIM-Assisted Wireless Networks via Quantum Reinforcement Learning

    Jan 29, 2026Le-Hung Hoang, Quang-Trung Luu, Dinh Thai Hoang +2Wireless CommunicationsWireless Resource Allocation

  2. DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization

    Jul 9, 2024Ashok S. Kumar, Nancy Nayak, Sheetal Kalyani +2Reconfigurable Intelligent SurfacesFair Resource Allocation