Traffic Flow Estimation using LTE Radio Frequency Counters and Machine Learning
This addresses the problem of costly and slow traffic sensor deployment for municipalities and traffic authorities by offering a cheaper, scalable alternative, though it is incremental in applying existing ML methods to new data.
The paper tackles traffic flow estimation by using standardized LTE radio frequency counters and machine learning, achieving promising results with a privacy-preserving and scalable approach that benefits from transfer learning to generalize across time and space.
As the demand for vehicles continues to outpace construction of new roads, it becomes imperative we implement strategies that improve utilization of existing transport infrastructure. Traffic sensors form a crucial part of many such strategies, giving us valuable insights into road utilization. However, due to cost and lead time associated with installation and maintenance of traffic sensors, municipalities and traffic authorities look toward cheaper and more scalable alternatives. Due to their ubiquitous nature and wide global deployment, cellular networks offer one such alternative. In this paper we present a novel method for traffic flow estimation using standardized LTE/4G radio frequency performance measurement counters. The problem is cast as a supervised regression task using both classical and deep learning methods. We further apply transfer learning to compensate that many locations lack traffic sensor data that could be used for training. We show that our approach benefits from applying transfer learning to generalize the solution not only in time but also in space (i.e., various parts of the city). The results are very promising and, unlike competing solutions, our approach utilizes aggregate LTE radio frequency counter data that is inherently privacy-preserving, readily available, and scales globally without any additional network impact.