Laboratory leader: Flor Ortiz
Laboratory technician: Suleima Brisenio
The TelecomAI-Lab is a research facility committed to advancing the convergence of artificial intelligence (AI) and telecommunications, with a particular emphasis on neuromorphic computing and AI-driven innovations for next-generation communication networks.
TelecomAI-Lab focuses on developing and validating AI-based solutions for telecommunications, particularly in wireless and satellite communication systems. Its research explores neuromorphic computing paradigms for energy-efficient and high-performance signal processing, as well as AI-driven enhancements for 5G/6G networks and non-terrestrial networks (NTN). The lab also investigates AI-based optimisations in physical layer communications, resource allocation, and interference management.
The TelecomAI-Lab is equipped with cutting-edge AI accelerators and neuromorphic processors to drive innovation in communication systems. Key hardware resources include:
Neuromorphic processors, such as Akida (BrainChip) and Loihi (Intel), designed for bio-inspired, low-power computation.
AI accelerators, including the Versal AI Core Series VCK family, optimised for AI-based signal processing and edge computing.
High-performance computing (HPC) resources for training and deploying deep learning models in communication networks.
Unlike traditional communication laboratories, TelecomAI-Lab focuses on AI-native solutions for signal processing and network optimisation.
We are happy to share our datasets with the community (for free).
Please note that the datasets CANNOT be used for commercial (for profit or non-profit organization) purposes, only for RESEARCH.
However, it took us time to prepare these. We kindly appreciate your citations. Please see: datasets
6G Communication Systems: Research on integrating AI-driven methodologies for future 6G satellite-terrestrial networks.
Satellite-Terrestrial Network Integration: Development of hybrid networks combining satellite and terrestrial infrastructures.
Beamforming and Precoding Optimization: Advanced signal processing techniques for multibeam satellites.
Interference Mitigation for NGSO and GSO Satellites: Techniques to minimize interference in multi-constellation satellite environments.
Energy-Efficient Communications: AI-based resource allocation for sustainable and low-power communication networks.
AI/ML for Satellite Communications: Application of AI techniques for satellite resource management, interference mitigation, and beamforming.
Generative AI for Telecommunications: Use of generative models to enhance satellite network adaptability and optimization.
Neuromorphic Computing for Communications: Development of neuromorphic processors and hardware for energy-efficient satellite and 6G systems.
AI for Non-Terrestrial Networks (NTN): Optimization of communication protocols and spectrum sharing for space-based networks.
Deep Learning for Signal Processing: Application of CNNs, RNNs, and reinforcement learning to optimize radio resource allocation.
Convex and Non-Convex Optimization for Wireless Networks: Optimization models for power and bandwidth management in VHTS and NGSO networks.
Radio Resource Management (RRM) for Space Communications: AI-enhanced spectrum allocation and adaptive power control.
Flexible Payload and Spectrum Management: Dynamic reallocation of satellite spectrum and onboard signal processing.
AI-Driven Digital Signal Processing (DSP): Novel AI-based approaches for adaptive coding, modulation, and channel estimation.