BANYAN will bring data-driven solutions at the mobile network radio access

The European project involves three partners including IMDEA Networks. It aims to train a new generation of creative, entrepreneurial and innovative early-stage researchers

22 February 2021

IMDEA Networks is since April 2020 part of the Innovative Training Networks (ITN) project “BANYAN: Big dAta aNalYtics for radio Access Networks”, financed by the European Union H2020-ICT-2019 call on Information and Communication Technology. Our Research Associate Professor Marco Fiore leads it at IMDEA Networks. One of its main objectives is forming five doctors in the telecommunication area, with a strong interdisciplinary background that mixes competences in data science and networking. Therefore, it pursues to make them been able to face current and future challenges and to convert knowledge and ideas into products and services for economic and social benefit.

Developing tools for data-driven 5G RAN is the key to BANYAN. The deployment of 5G has boosted the market of intelligent radio access networks. As mobile services consumed by people and machines become increasingly diversified and heterogeneous, 4G/5G networks are asked to meet a growing variety of Quality of Service (QoS) requirements. Network slicing, enabled by Network Function Virtualization (NFV), is a promising paradigm to increase the agility and elasticity of the mobile network via logical slices that can be formed and composed dynamically, so as to adapt to the fluctuations in the demands for different mobile services.

Precisely, a key enabler for network slicing is accurate data-driven models and the prediction of the spatio-temporal dynamics of the mobile service traffic, which allow discovering knowledge relevant to the orchestration of slices and anticipating the need for their reconfiguration. The need for effective data-driven slice management is especially critical in proximity of indoor Radio Access Network (RAN), which must accommodate most of the volume and variations in the demand associated to each mobile service and whose performance is crucial to user QoS.

BANYAN attempts to solve the following open issues, according to Fiore:

1. Develop models of the demands generated by mobile users for mobile services at macroscopic (e.g., metropolitan, regional) scales;
2. Develop predictors capable of forecasting such demands with high accuracy and low computational complexity, and in real time;
3. Develop radio access network (RAN) slicing strategies and policies based on the macroscopic and microscopic traffic analysis;
4. Develop algorithms for the orchestration of network slices at the mobile network edge;
5. Develop algorithms to proactively optimize and coordinate both outdoor and indoor networks; and
6. Develop algorithms to proactively optimize and coordinate in-building multi-RAT networks.

As beneficiary of the project, IMDEA Networks will hire and train two Early-Stage Researchers. “The students Aristide Akem, graduated from the Africa branch of Carnegie Mellon University, and André Zanella, graduated from Universidade Federal do Paraná in Brazil and with significant work experience as data analyst, will join IMDEA in early 2021”, says Fiore. It will also host a third ESR from one of the partners (Consiglio Nazionale delle Ricerche and Ranplan Wireless Networks Design LTD) during a whole year, and organize one of the two summer schools of the ITN.