A Novel Ramp Metering Approach Based on Machine Learning and Historical Data

TL;DR

This paper introduces a machine learning-based real-time ramp metering model that leverages historical data to improve freeway traffic flow management, demonstrating promising results over traditional methods.

Contribution

It presents a novel ramp metering algorithm that combines machine learning and historical data for improved traffic flow control.

Findings

The ML-based model outperforms baseline algorithms in traffic flow efficiency.

The approach effectively predicts traffic conditions in real-time.

Results show significant reduction in congestion and delays.

Abstract

The random nature of traffic conditions on freeways can cause excessive congestions and irregularities in the traffic flow. Ramp metering is a proven effective method to maintain freeway efficiency under various traffic conditions. Creating a reliable and practical ramp metering algorithm that considers both critical traffic measures and historical data is still a challenging problem. In this study we use machine learning approaches to develop a novel real-time prediction model for ramp metering. We evaluate the potentials of our approach in providing promising results by comparing it with a baseline traffic-responsive ramp metering algorithm.