A stochastic optimization framework for road traffic controls based on evolutionary algorithms and traffic simulation
DOI: 10.1016/j.advengsoft.2017.08.005
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of optimizing road traffic controls, specifically traffic light settings, within a stochastic and nonlinear environment. The authors identify a gap in existing research: while nature-inspired optimization techniques like genetic algorithms (GAs) are commonly used, there is a lack of general, model-based scientific computing frameworks that facilitate efficient real-world planning and management applications. The study aims to propose a generalized optimization framework that integrates traffic simulation models with advanced evolutionary algorithms to determine optimal control parameters for improving mobility efficiency, energy usage, and environmental sustainability. The proposed framework consists of three essential components: an evolutionary optimizer, a software-in-the-loop simulation module, and a performance estimator. The optimization engine employs an Archived Genetic Algorithm (AGA), which enhances standard GA performance by using a small population size combined with a large external archive to store globally elite solutions. This approach reduces the number of fitness function evaluations required for convergence. The framework utilizes Latin Hypercube sampling for initial population generation and adaptive crossover and mutation probabilities to balance exploration and exploitation. To handle the computational burden of microscopic traffic simulations, the system employs parallel processing and an inventory database to avoid redundant evaluations of identical control parameters. The framework is designed to be compatible with various traffic simulators, with the study specifically implementing the open-source SUMO simulator. To validate the framework, the authors conducted a case study optimizing traffic light controls for a simple road network of two intersections in Stockholm, Sweden. The application focused on a group-based vehicle-actuated control scheme known as LHOVRA. The performance estimator evaluated system efficiency using two primary metrics: average travel delay and fuel consumption. Travel delay was calculated based on instantaneous vehicle states from the microscopic simulation, while fuel consumption was estimated using the Comprehensive Modal Emission Model (CMEM) based on vehicle trajectories. The optimization process iteratively updated signal parameters, including green durations and phase configurations, until termination criteria were met. The results demonstrate that the Archived Genetic Algorithm achieves superior performance compared to ordinary genetic algorithms by significantly reducing the number of fitness function evaluations, thereby lowering computational time. The framework successfully optimized the traffic light settings for the Stockholm network, validating its capability to handle stochastic traffic processes and complex control schemes. The study concludes that this model-based optimization framework provides a robust, efficient, and generalizable tool for traffic engineers and planners. It facilitates the integration of high-fidelity microscopic simulations with advanced optimization algorithms, enabling more effective management of urban traffic congestion and environmental impacts.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | OpenAlex-citations | — | — | 1 | 2026-06-18 |
| archive | success | unpaywall | — | — | 2 | 2026-06-25 |
| extract | success | pdftotext | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | failed | — | — | — | 4 | 2026-06-25 |
| promote | success | — | — | — | 1 | 2026-06-18 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Theoretical Contribution: computational model