Towards Multi-Model Big Data Road Traffic Forecast at Different Time Aggregations and Forecast Horizons

Authors

  • Riccardo Martoglia FIM - University of Modena and Reggio Emilia, Italy
  • Gabriele Savoia FIM - University of Modena and Reggio Emilia, Italy

DOI:

https://doi.org/10.4108/ew.v9i39.1187

Keywords:

Big Data Analytics, Time Series, Traffic Forecast, Time Aggregation, ARIMA, Apache Spark, Machine Learning

Abstract

Due to its usefulness in various social contexts, from Intelligent Transportation Systems (ITSs) to the reduction of urban pollution, road traffic prediction represents an active research area in the scientific community, with strong potential impact on citizens’ well-being. Already considered a non-trivial problem, in many real applications an additional level of complexity is given by the large amount of data requiring Big Data domain technologies. In this paper, we present the first steps of a novel approach integrating both classic and machine learning models in the Spark-based big data architecture of the H2020 CLASS project, and we perform preliminary tests to see how usually little-considered variables (different data aggregation levels, time horizons and traffic density levels) influence the error of the different models.

Downloads

Download data is not yet available.

Downloads

Published

25-05-2022

How to Cite

1.
Martoglia R, Savoia G. Towards Multi-Model Big Data Road Traffic Forecast at Different Time Aggregations and Forecast Horizons. EAI Endorsed Trans Energy Web [Internet]. 2022 May 25 [cited 2022 Oct. 6];9(39):e1. Available from: https://publications.eai.eu/index.php/ew/article/view/1187