Optimization of stochastic switching buffer network via DC programming

TL;DR

This paper presents a method to optimize stochastic switching buffer networks, modeled via Markov processes, using DC programming to handle nonconvexity, with validation through simulation experiments.

Contribution

It introduces a novel application of DC programming to optimize stochastic buffer networks governed by Markov switching laws.

Findings

Effective optimization of buffer networks achieved

DC programming reduces nonconvexity issues

Simulation confirms the method's effectiveness

Abstract

This letter deals with the optimization problems of stochastic switching buffer networks, where the switching law is governed by Markov process. The dynamical buffer network is introduced, and its application in modeling the car-sharing network is also presented. To address the nonconvexity for getting a solution as close-to-the-global-optimal as possible of the optimization problem, we adopt a succinct but effective nonconvex optimization method called \emph{ DC (difference of convex functions) programming}. By resorting to the log-log convexity of a class of nonlinear functions called posynomials, the optimization problems can be reduced to DC programming problems. Finally, we verify the effectiveness of our results by simulation experiments.