.png){kind=icon}
Return
Simulation-based Bayesian optimization for large-scale dynamic lane allocation
.png){kind=icon}
OA
AI
DOI：10.1016/j.tre.2026.105256.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a Bayesian optimization for large-scale binary simulation-based optimization.
• A grouped ARD Hamming kernel captures spatial and temporal relevance.
• Dimension reduction and binary trust-region search improve sampling efficiency.
• The method solves dynamic lane allocation for virtual and Barcelona networks.
• Results show faster convergence and better feasible solutions than baselines.
Keywords:
Bayesian optimization
Simulation-based optimization
High-dimensional binary optimization
Dynamic lane allocation
Journal
IF:
8.8
Papers:
871
Citations:
2.0W
Organization
Cited Papers
No cited papers available