Predefined-time distributed non-convex optimization via a time-base generator

TL;DR

This paper introduces innovative time-base generators for multi-agent systems to achieve predefined-time convergence in non-convex resource allocation and optimization problems, outperforming existing methods.

Contribution

The paper presents a novel approach using time-base generators for predefined-time convergence in non-convex distributed optimization, extending applicability beyond convex functions.

Findings

Achieves predefined-time approximate convergence for non-convex functions.

Converges to the optimal solution for generalized smoothness functions.

Demonstrates faster convergence and CPU efficiency in simulations.

Abstract

In this paper, we propose two novel multi-agent systems for the resource allocation problems (RAPs) and consensus-based distributed optimization problems. Different from existing distributed optimal approaches, we propose the new time-base generators (TBGs) for predefined-time non-convex optimization. Leveraging the proposed time-base generator, we study the roughness and boundedness of Lyapunov function based on TBGs. We prove that our approach achieves predefined-time approximate convergence to the optimal solution if the cost functions exhibit non-strongly convex or even non-convex characteristics. Furthermore, we prove that our approaches converge to the optimal solution if cost functions are generalized smoothness, and exhibit faster convergence rate and CPU speed. Finally, we present numerous numerical simulation examples to confirm the effectiveness of our approaches.