Sustainable and multifunctional wireless networks: the role of ML
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
The future global cellular infrastructure will underpin a variety of applications, such as smart city solutions, urban security, infrastructure monitoring, and smart mobility, among others. These emerging applications require new network functionalities that go beyond traditional communication. Key network KPIs for 6G include Gb/s data rates, cm-level localization, μs-level latency, and Tb/Joule energy efficiency. Additionally, future networks must support the UN’s Sustainable Development Goals to ensure sustainability, net-zero emissions, resilience, and inclusivity.
The multifunctionality and net-zero emissions agenda call for a redesign of intelligent signals and waveforms for 6G and beyond. In this talk, I will first discuss a recent research direction involving symbol-level precoding (SLP) approaches, which treat interference as a useful resource in multi-antenna communication systems. These approaches have demonstrated significant power consumption savings across various communication scenarios.
The second part of the talk will focus on enabling multifunctionality in signals and wireless transmissions as a means of reducing hardware redundancy and minimizing carbon footprint. We will explore the emerging field of integrated sensing and communications (ISAC), which represents a paradigm shift towards combining sensing and communication functionalities within a single transmission, utilizing a single spectrum and ultimately sharing a common infrastructure.
Throughout the talk, I will emphasize the potential of machine learning (ML) as an enabling solution and explore possible applications of ML in the domains discussed.