Big-Data Inspired, Proximity-Aware 4G/5G Service Supporting Urban Social Interactions

Unlike virtual sociality, in their daily social behavior individuals are used to communicate with a limited number of persons and periodically meet their inner social circle in specific city locations to perform common social activities. Physical encounters among a restricted number of people interestingly give rise to a significant amount of in-proximity voice/data traffic on the cellular network and advocate the provisioning of a new class of services supporting it. This paper gives empirical evidence of the role played by these location-centered social interactions through the extensive analysis of a large anonymized dataset of Call Detail Records (CDR) relying on the phone activities of nearly 1 million people in the city of Milano. The analysis and understanding of these human interactions have inspired the design of a new mobile service that detects, after user's consent, proximity with a person in my inner social circle and autonomously deploys the mobile social network supporting proximity interactions. The approach we propose brings together a few important contributions: first, it concretely shows that the current NFV-enabled trend of placing cloud services at the edge of the operator's network has a payoff in terms of traffic offloading and improved user's experience; secondly, it demonstrates for the first time that a few typical cloud-based services can actually be directly performed by the mobile network operator by simply leveraging the rich amount of data they possess and never exploit.