Neural Quantile Optimization for Edge-Cloud Networking

TL;DR

This paper introduces a neural network-based approach using Gumbel-softmax reparameterization to optimize traffic allocation in edge-cloud networks, achieving better feasibility and cost efficiency than random strategies.

Contribution

It develops a novel neural network framework that models traffic allocation as a continuous optimization problem, enabling efficient unsupervised learning for network optimization.

Findings

Outperforms random strategies in feasibility and cost.

Generalizes well with increased users and time steps.

Accelerates optimization with warm-starts from existing solvers.

Abstract

We seek the best traffic allocation scheme for the edge-cloud computing network that satisfies constraints and minimizes the cost based on burstable billing. First, for a fixed network topology, we formulate a family of integer programming problems with random parameters describing the various traffic demands. Then, to overcome the difficulty caused by the discrete feature of the problem, we generalize the Gumbel-softmax reparameterization method to induce an unconstrained continuous optimization problem as a regularized continuation of the discrete problem. Finally, we introduce the Gumbel-softmax sampling network to solve the optimization problems via unsupervised learning. The network structure reflects the edge-cloud computing topology and is trained to minimize the expectation of the cost function for unconstrained continuous optimization problems. The trained network works as an efficient traffic allocation scheme sampler, remarkably outperforming the random strategy in feasibility and cost function value. Besides testing the quality of the output allocation scheme, we examine the generalization property of the network by increasing the time steps and the number of users. We also feed the solution to existing integer optimization solvers as initial conditions and verify the warm-starts can accelerate the short-time iteration process. The framework is general with solid performance, and the decoupled feature of the random neural networks is adequate for practical implementations.