Improved A* search: A bandwidth allocation algorithm for Linux traffic control based on Hierarchical Token Bucket

Abstract

Efficient bandwidth allocation is crucial for network performance. HTB (Hierarchical Token Bucket), a widely-used queue discipline in Linux traffic control, lacks theoretical guidance for parameter configuration. To address this, we formalize the bandwidth allocation problem under HTB as a Bandwidth Satisfaction Optimization (BSO) problem, proving its NP-hardness. We propose an improved A* algorithm that constructs a solution space tree, skips irrelevant parameters, and accelerates search through constraint relaxation and breadth limitation. Extensive evaluations show that our algorithm outperforms existing methods, achieving at least 90% of Gurobi’s effectiveness with significantly shorter execution time. Implementation on a real machine confirms that actual bandwidth usage matches the model’s calculated results, demonstrating the algorithm’s effectiveness and reliability in practical applications.