Network utility maximization by updating individual transmission rates

TL;DR

This paper presents novel algorithms for maximizing network utility by updating individual transmission rates, employing fast gradient and stochastic methods suitable for distributed network environments.

Contribution

It introduces two new optimization approaches for network utility maximization, accommodating non-strongly concave utilities and distributed information constraints.

Findings

Fast gradient method effectively optimizes the utility function.

Stochastic oracles enable distributed implementation in real networks.

Numerical experiments demonstrate the approaches' efficiency.

Abstract

This paper discusses the problem of maximizing the total data transmission utility of the computer network. The total utility is defined as the sum of the individual (corresponding to each node in the network) utilities that are concave functions of the data transmission rate. For the case of non-strongly concave utilities, we propose an approach based on the use of a fast gradient method to optimize a dually smoothed objective function. As an alternative approach, we introduce stochastic oracles for the problem under consideration and interpret them as the messages on the state of some individual node to use randomized switching mirror descent to solve the problem above. We propose interpretations of both described approaches allowing the effective implementation of the protocols of their operation in the real-life computer networks environment, taking into account the distributed information storage and the restricted communication capabilities. The numerical experiments were carried out to compare the proposed approaches on sythetic examples of network architectures.