“The research conducted at BANYAN has been groundbreaking in several respects. For one, the project has revealed previously unknown aspects of mobile service demand in various contexts, such as urban areas, indoor environments, and during special events,” explains Dr. Fiore. These findings have enabled the creation of accurate models of user behavior and mobile traffic, essential tools for improving the planning and management of modern radio access networks. “As representative examples, we were able to reveal how the introduction of 5G has fostered an increase in the consumption of certain mobile applications (particularly those related to video games), and we demonstrated how large public protests generate dramatic increases in traffic for only certain types of services (notably, browsing and messaging).”.

Another key achievement of BANYAN has been the development of an artificial intelligence (AI)-based solution for modeling signal propagation in dense radio access environments. This technique not only enables precise planning of wireless network infrastructure but also reduces the computational time required to design indoor wireless networks compared to traditional tools. This represents a significant advancement for efficiently designing networks in smart cities and large indoor spaces such as shopping malls or airports.

Commercialization:
The project's results have not only remained within the academic sphere but have also found commercial applications. "Some of the tools developed during BANYAN have been integrated into the radio planning software marketed by Ranplan Wireless, one of the project partners," Fiore points out.
At the academic level, the work has been presented at top-tier conferences such as ACM IMC, IEEE INFOCOM, and the IEEE JSAC journal, further emphasizing BANYAN's contribution to scientific knowledge in the field of radio access networks.

Challenges
The BANYAN project addressed several complex challenges, including:

• Measure, characterize, and model traffic demand for individual mobile services at large scale (e.g., entire cities or countries) in both indoor and outdoor environments.
• Develop AI-based tools to generate realistic radio frequency propagation in indoor and outdoor scenarios with high accuracy and low complexity.
• Create optimization models for automated network planning.
• Design AI solutions for autonomous mobile network management, tested on experimental platforms.