Dynamic metasurface antennas improve wireless energy efficiency by 20 percent
World Model for Energy Efficiency Maximization in Dynamic Metasurface Antennas
Information Theory
Summary
Wireless networks use antennas to send and receive signals, but making these antennas both powerful and energy efficient is hard. This paper looks at a special type of antenna called a dynamic metasurface antenna (DMA) that can change how it works over time to use energy better. The authors develop a computer model that learns how the antenna behaves in different conditions and plans ahead to improve energy use. Their tests show this new approach uses about 20% less energy on average compared to older methods, and it keeps the system working properly while adapting to changing signals.
What this means in practice
- •For wireless network engineers: Improve energy usage in large-scale next-generation wireless antenna systems that adapt to changing channel conditions.
- •For telecommunications system designers: Design smarter antenna arrays combining digital and physical element adjustments to meet power and data rate constraints efficiently.
Authors
Abdolrasoul Sakhaei Gharagezlou, Mehdi Monemi, Matti Latva-aho, Mehdi Rasti
Abstract
Dynamic metasurface antennas (DMAs) have emerged as a promising technology for realizing large-scale antenna arrays in next-generation wireless networks owing to their ability to enable dense and energy-efficient antenna architectures. However, jointly optimizing digital beamforming and DMA element weights under time-varying channel conditions remains challenging due to their coupled effects on the received signal and interference powers. We formulate this problem to maximize time-averaged energy efficiency (EE) under time-varying channel conditions, subject to transmit power constraints, Lorentzian phase limitations, and minimum rate requirements. To enable long-term planning and improve sample efficiency compared with model-free reinforcement learning, we develop a world model framework that learns latent system dynamics from interactions with the environment and jointly optimizes digital beamforming and DMA element weights through imagined trajectories. Furthermore, we incorporate feasibility-preserving action mappings and safety cost signals to ensure constraint satisfaction during policy learning. Simulation results demonstrate that the proposed framework improves the time-averaged EE by approximately 20% compared with the deep Q-network baseline, while achieving higher sample efficiency and more reliable constraint satisfaction.