Deep Unfolding-Empowered Energy Efficiency Optimization in RIS-Assisted Wireless Communications
Mobaraki, Pouya; T. Nguyen, Nhan; Juntti, Markku (2025-03-31)
ACM
31.03.2025
Mobaraki, P., T. Nguyen, N., & Juntti, M. (2024). Deep unfolding-empowered energy efficiency optimization in ris-assisted wireless communications. Proceedings of the 14th International Conference on the Internet of Things, 238–243. https://doi.org/10.1145/3703790.3703830
https://creativecommons.org/licenses/by/4.0/
© 2024 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution International 4.0 License.
https://creativecommons.org/licenses/by/4.0/
© 2024 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution International 4.0 License.
https://creativecommons.org/licenses/by/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202504092482
https://urn.fi/URN:NBN:fi:oulu-202504092482
Tiivistelmä
Abstract
Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for future wireless communications, with energy efficiency (EE) becoming a critical optimization goal in RIS-assisted systems. However, the current methods for EE optimization are often complex and have a slow convergence. In this paper, we tackle this challenge by formulating an EE optimization problem based on a realistic ON/OFF power consumption model for a RIS. The problem is non-convex and mixed-integer, making it computationally complex. Therefore, we relax it by considering continuous RIS phase shifts and propose a deep unfolding architecture using the gradient descent (GD) method for optimization. Our approach significantly reduces the number of iterations required for convergence compared to the conventional GD method, while maintaining interpretability and explainability. Numerical results demonstrate that our method achieves five times fewer iterations than conventional approaches, with comparably or improved energy efficiency.
Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for future wireless communications, with energy efficiency (EE) becoming a critical optimization goal in RIS-assisted systems. However, the current methods for EE optimization are often complex and have a slow convergence. In this paper, we tackle this challenge by formulating an EE optimization problem based on a realistic ON/OFF power consumption model for a RIS. The problem is non-convex and mixed-integer, making it computationally complex. Therefore, we relax it by considering continuous RIS phase shifts and propose a deep unfolding architecture using the gradient descent (GD) method for optimization. Our approach significantly reduces the number of iterations required for convergence compared to the conventional GD method, while maintaining interpretability and explainability. Numerical results demonstrate that our method achieves five times fewer iterations than conventional approaches, with comparably or improved energy efficiency.
Kokoelmat
- Avoin saatavuus [38865]
Ellei muuten mainita, aineiston lisenssi on https://creativecommons.org/licenses/by/4.0/