MLOps-Assisted Anomalous Reflector Metasurfaces Design Based on Red Hat OpenShift AI

TL;DR

This paper presents an AI-driven MLOps framework using Red Hat OpenShift for designing anomalous reflector metasurfaces, enabling automated, resource-efficient, and high-quality metasurface design with deep learning models.

Contribution

It introduces a novel MLOps architecture leveraging Red Hat OpenShift AI for metasurface design, integrating cGANs and surrogate models for efficient and automated physical-layer metasurface optimization.

Findings

High training accuracy of the proposed model.

Feasibility of deploying in containerized Red Hat OpenShift environment.

Improved design efficiency over traditional methods.

Abstract

The integration of artificial intelligence as a design tool for metasurfaces, and the implementation of a deep-learning model pose a challenge in the development of an automated solution due to high resources requirements. The presented work introduces a network-layer solution to configure such environment for end user objectives, and for an underlying physical-layer technology. An architecture is developed to design an anomalous reflector by employing the Redhat Openshift AI (RHOAI) technology to support an automated machine learning operations (MLOps) framework in smart radio environments. This entails the design of lossless impenetrable metasurfaces characterized by a scalar surface impedance for an optimal anomalous reflection, achieved by optimizing the number of the Floquet modes through the utilization of a local power conservation constraint qualified as a fitness function. The metasurfaces design process is implemented by using a conditional generative adversarial network (cGAN). An extended cGAN with a surrogate model assists in a high-quality freeform metasurfaces design, where it introduces a swift simulation tool for the metasurfaces design process and analysis of the far-field model. The paper focuses on the challenges of building such a system, and potential abstraction layers. The training accuracy value of the proposed model demonstrates the feasibility and benefits of deploying in containerized environment of Red Hat Openshift in comparison with other deployments of ResNet-50 reported in literature.