Abstract
In spite of the vast set of measurements provided by current mobile networks, cellular operators have problems pinpointing problematic locations because the origin of such measurements (i.e., user location) is usually not registered. At the same time, social networks generate a huge amount of data that can be used to infer population density. In this work, a data-driven model is proposed to deduce the statistical distribution of connections, exploiting the knowledge of network layout and population density in the scenario. Due to the absence of GPS measurements, the proposed method combines data from radio connection traces stored in the network management system and geolocated posts from social networks. This information is enriched with user context information inferred from data traffic attributes. The method is tested with a large trace dataset from a live Long Term Evolution (LTE) network and a database of geotagged posts from social networks collected in real-time.
Highlights
IntroductionThe constant development of new, cheaper, more accessible, and powerful equipment has democratized access to cellular networks, triggering requests for new and already established services, causing both the generation of network traffic and the number of devices connected and transmitting simultaneously to grow exponentially, with an increase of almost eight times the current traffic and a total of 31.4 billion active mobile devices expected by 2023 [1]
Based on Social Information.It is a fact that, in recent years, the evolution and growth of mobile networks have been an unstoppable force
The model receives 4 inputs: (a) the information recorded in the radio connection traces, (b) data of land uses in the scenario, (c) information on the location and orientation of the cells in the scenario and (d) posts obtained from social networks that have associated geopositioning metadata
Summary
The constant development of new, cheaper, more accessible, and powerful equipment has democratized access to cellular networks, triggering requests for new and already established services, causing both the generation of network traffic and the number of devices connected and transmitting simultaneously to grow exponentially, with an increase of almost eight times the current traffic and a total of 31.4 billion active mobile devices expected by 2023 [1] This exponential growth phenomenon has resulted in complex and extensive cellular networks making it impossible to manually perform management tasks, a fact that will be increased with the solutions implemented in 5G. Network organizing tasks often have to be performed based on measurements only positioned by cell identifier and Timing Advance (TA) statistics This approach leads to large localization errors, even more in areas with high TA, where the combination of cell identifier and TA produces a large area location ring, which prevents estimating the user context.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
