CAREER: CatFly: Towards Resilience-Native Wireless Networks through Learning, Twinning, and Reconfiguring Co-Design
-
Project Information
- Award numbers: NSF CNS-2440756
- Project period: 07/01/2025 – 06/30/2030
- Principal investigator: Dr. Yuchen Liu (PI)
- Graduate students: Xuanhao Luo, Jiayuan Huang
-
Project Overview
- The evolution of mobile and wireless networks is being driven by three major technological advances: 1) a move to higher carrier frequencies (e.g. mmWave/THz), 2) the increased density of task-oriented network entities, and 3) the higher level of intelligence. To guarantee the delivery of consistently high-quality services for users with the above technological evolution, network resilience and self-reconfigurabilities are crucial. This necessitates a heightened level of intelligence and timely situational awareness in the face of various challenges like network or access point failures. To tackle these challenges, this project pursues a novel resilience-native network paradigm called CatFly, inspired by the way a cat behaves during a crash landing. For instance, in a long drop, falling cats can survive because they have time to relax and stretch out their legs like flying squirrels, which increases their air-resistance and reduces the shock of impact when they hit the ground. Inspired by this fact, if the network system is co-designed with such analogous ability - 1) predicting disturbances or failures with sufficient time ahead, 2) automating prepared countermeasures, and 3) reconfiguring physical structure to prevent potential losses - it can also become a well-trained ‘‘paratrooper’’ like a cat, increasing self-resilience to sustain performance in disruptive situations. To this end, this project explores hybrid digital-physical (HDP) intelligence that utilizes an evolutional digital replica of the network with sufficient what-if details to uncover multi-dimensional physical reconfigurability.
Back to Homepage