Short-Term Traffic Flow Forecasting Using a Distributed Spatial-Temporal k Nearest Neighbors Model

摘要

Accurate and timely information on the current and predicted traffic flows is important for the successful deployment of intelligent transport systems. These data plays an essential role in traffic management and control. Using traffic flow information, travelers could plan the routes to avoid traffic congestion, reduce travel time, environmental pollution, and improve traffic operation efficiency in general. In this paper, we propose a distributed model for short-term traffic flow prediction based on the k nearest neighbors method, that takes into account spatial and temporal traffic flow distribution. The proposed model is implemented as a MapReduce based algorithm on an Apache Spark framework. An experimental study of the proposed model is carried out on a traffic flow data in transportation network of Samara, Russia.