# Real-Time Predictive Control Strategy Optimization

## TL;DR

This paper introduces a real-time optimization framework for traffic control strategies that predicts network states to improve traffic flow, demonstrating up to 9% travel time reduction using a scalable genetic algorithm in Singapore.

## Contribution

It presents a novel real-time control optimization framework integrating prediction and decision-making for dynamic traffic management.

## Key findings

- Up to 9% reduction in network-wide travel times.
- Efficient genetic algorithm exploits parallel computing.
- Framework tested on large-scale Singapore road network.

## Abstract

Traffic congestion has lead to an increasing emphasis on management measures for a more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with guidance generation using predicted network states for Dynamic Traffic Assignment systems. The efficacy of the framework is demonstrated through a fixed demand dynamic toll optimization problem which is formulated as a non-linear program to minimize predicted network travel times. A scalable efficient genetic algorithm is applied to solve this problem that exploits parallel computing. Experiments using a closed-loop approach are conducted on a large scale road network in Singapore to investigate the performance of the proposed methodology. The results indicate significant improvements in network wide travel time of up to 9% with real-time computational performance.