VINES: Track 1: Al-driven Design, Control, and Management of NextG Optical Networks

Internet traffic and bandwidth demand have grown dramatically over the past decade, driven by video-intensive services such as TikTok, bandwidth-hungry applications such as online gaming, and emerging virtual and augmented reality services. This growth has accelerated further with the rapid expansion of artificial intelligence (AI), particularly the massive data movement required to train and deploy AI models. For decades, fiber-optic networks have formed the backbone of the Internet because of the enormous capacity of optical fiber. However, today’s explosive bandwidth demands are pushing core networks toward their operational limits, requiring network operators to extract greater performance, efficiency, and resilience from already-deployed infrastructure. Historically, optical network control and resource allocation have relied largely on rule-based methods and heuristics. While machine learning and broader AI techniques have recently shown promise in improving network efficiency and adaptability, the field lacks a systematic framework for deeply integrating AI into optical network control, management, and failure recovery. This project addresses that gap by developing an AI-integrated architecture for next-generation optical networks, together with AI-driven algorithms for resource allocation, performance optimization, and failure management. The overarching goal is to harness AI and machine learning (ML) to make faster, more effective decisions that improve network performance, increase utilization, and enhance resilience under both normal and failure conditions. The project is organized around three research thrusts. First, it will develop a comprehensive AI-integrated architecture for optical network control and management. Second, it will investigate the fundamental capabilities and limits of AI for improving resource allocation and will design new algorithms that exploit these capabilities. Third, it will develop AI/ML models for detecting, predicting, and mitigating network failures. By advancing AI-driven optical networking, this project has significant societal and economic implications for critical infrastructure, smart cities, resilient communications, and digital sovereignty. It will train graduate and undergraduate students at the intersection of networking, optical communications, and AI, preparing a workforce equipped for the next generation of intelligent communications infrastructure. Broader impacts will be amplified through K–12 outreach, exposure to critical networking technologies, and the release of open-source tools and community datasets. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.