Comparative Synthesis: Learning Near-Optimal Network Designs by Query

TL;DR

This paper introduces a novel interactive synthesis framework for designing near-optimal network configurations without predefined objectives, utilizing a learning algorithm and real-world case studies to demonstrate effectiveness.

Contribution

It presents the first comparative synthesis method for network design, a learning algorithm for query selection, and an implementation with real-world validation.

Findings

Effective in four real-world network case studies

Converges efficiently with theoretical guarantees

Engages network researchers and practitioners in pilot study

Abstract

When managing wide-area networks, network architects must decide how to balance multiple conflicting metrics, and ensure fair allocations to competing traffic while prioritizing critical traffic. The state of practice poses challenges since architects must precisely encode their intent into formal optimization models using abstract notions such as utility functions, and ad-hoc manually tuned knobs. In this paper, we present the first effort to synthesize optimal network designs with indeterminate objectives using an interactive program-synthesis-based approach. We make three contributions. First, we present comparative synthesis, an interactive synthesis framework which produces near-optimal programs (network designs) through two kinds of queries (Propose and Compare), without an objective explicitly given. Second, we develop the first learning algorithm for comparative synthesis in which a voting-guided learner picks the most informative query in each iteration. We present theoretical analysis of the convergence rate of the algorithm. Third, we implemented Net10Q, a system based on our approach, and demonstrate its effectiveness on four real-world network case studies using black-box oracles and simulation experiments, as well as a pilot user study comprising network researchers and practitioners. Both theoretical and experimental results show the promise of our approach.