The massive adoption of eXtended Reality (XR) in most of our daily activities regarding education, work, health, entertainment and
personal life will heavily transform our society in the following years. Those XR applications will mostly reach the final user - to both
consume and create XR contents - through wireless networks, and Wi-Fi in particular, due to their flexibility, mobility support and ease of use. The success of such an XR-enabled society will depend to a great extent on the ability of the wireless networks to support their stringent performance requirements. Real-time, and interactive XR applications - which mainly consist of exchanging high quality video along with metadata - require both high throughput (hundreds of Mbps per user) and low-latency (ms, or even sub-ms), which generally are opposed performance metrics.
Current wireless networks are not yet ready to cope with a massive use of XR applications in an efficient way, and so both academia and industry are pushing to find innovative solutions. The target is to have them ready by 2030. By then, Wi-Fi will likely continue being the preferred wireless access solution in unlicensed bands, and so the most used technology to consume XR experiences. However, although current Wi-Fi technologies are extremely advanced, reaching speeds of several dozens of Gbps, they are far from being ready to efficiently offer low-latency guarantees.
To support XR needs in future Wi-Fi networks a paradigm change is required from throughput-centered to latency-aware networking. This paradigm change can be supported by allowing Wi-Fi to opportunistically use different spectrum bands in a coordinated way, enable cooperation between different Access Points, implement sub-frame resource allocation schemes, exchange control information with other layers, and support the use of Machine Learning for a seamless adaptation to diverse and rapidly evolving scenarios.
This project aims to build on the aforementioned points to offer innovative and practical solutions for next-generation Wi-Fi networks, so they can successfully offer both high-throughput and low-latency guarantees to interactive streaming applications including video contents, cloud gaming, and immersive XR applications, among others. By considering new principles such as multi Access Point cooperation and opportunistic multi-channel/band access, we will be able to design particular solutions able to satisfy the needs of XR applications in dense and dynamic wireless network deployments. Moreover, we will go beyond traditional protocol/mechanism design: motivated by the need to find/learn specific functionalities that suit each unique scenario, we will focus on the design of intelligent protocols/mechanisms by embedding Machine Learning techniques in the different Wi-Fi functionalities.
The generated results will extend our knowledge in wireless networking, Wi-Fi technologies, real-time and interactive video applications (cloud gaming, and XR), and in the design of intelligent protocols. It will also contribute to developing the required new mathematical, simulation and experimental frameworks to be able to characterize the performance gains of the upcoming latency-aware Wi-Fi networks. All in all, this project will help to build a better future society by contributing to enable the use of interactive and real-time XR applications and services.