A novel game approach to integrating traffic assignment and signal control for enhanced efficiency and environmental performance in mixed networks

•A centralized optimal control framework, which involves the combined traffic assignment and signal control (CAC) in the mixed network with expressways and surface streets is established.•The proposed Level-Change-MPC (Model Predictive Control)-VT-Meso-Emission Model (LCMVTM) enables the leader/foll...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Transportation research. Part C, Emerging technologies Jg. 171; S. 105017
Hauptverfasser: Yang, Hang, Ma, Wanjing, Cheng, Rongjun, Wu, Bing, Wang, Yibing, Zheng, Pengjun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.02.2025
Schlagworte:
Integrated Traffic Control
Novel Stackelberg Games Model
Reinforcement Learning Algorithm
Signal Control
Traffic Assignment
Urban Mixed Network
Signal Control
Integrated Traffic Control
Reinforcement Learning Algorithm
Novel Stackelberg Games Model
Traffic Assignment
Urban Mixed Network
ISSN:0968-090X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A centralized optimal control framework, which involves the combined traffic assignment and signal control (CAC) in the mixed network with expressways and surface streets is established.•The proposed Level-Change-MPC (Model Predictive Control)-VT-Meso-Emission Model (LCMVTM) enables the leader/follower level transfer dynamically through users’ compliance rate, which gives more flexibility when the single games-based control method fails to enhance the network performance in the peak hour.•The stability test verifies that the role-change in leader-follower will not bring the extra flow fluctuation referring to the least number of stop&go per vehicle. The combined traffic assignment and signal control (CAC) has proven to be effective in enhancing the wholistic performance of mixed networks, which includes both expressways and surface streets. This study focuses on addressing the limitations of traditional Stackelberg game-based CAC models, particularly the rigid leader–follower dynamic. We propose an integrated Level-Change-MPC (Model Predictive Control)-VT-Meso-Emission Model (LCMVTM), which incorporates a dynamic role-change function triggered by the compliance rate of users to variable message signs (VMS). This role-change mechanism offers greater flexibility under varying road conditions and simplifies the authority’s task of predicting user routing behavior. Additionally, a Q-learning-based algorithm is developed to balance travel costs and emissions by managing the rate of emission accumulation across control horizons. The results demonstrate a reduction in total travel costs by 11% to over 30%, while emissions decrease by 16.98% to approximately 40% compared to the other different combination of control strategies and MAS/non MAS structured network. The emission accumulation rate also drops by 20% to 43.69%. LCMVTM outperformed the other benchmarks by reducing the number of stop&go per vehicle, resulting in improved efficiency and environmental outcomes.
ISSN:0968-090X
DOI:10.1016/j.trc.2025.105017