Self-Regulated Particle Swarm Multi-Task Optimization.

Xiaolong Zheng,Yu Lei,Jiao Shi,Na Li,Tao Wu,Deyun Zhou

doi:10.3390/s21227499

Xiaolong Zheng, Yu Lei + Show 4 more

Open Access

https://doi.org/10.3390/s21227499

Copy DOI

Abstract

Population based search techniques have been developed and applied to wide applications for their good performance, such as the optimization of the unmanned aerial vehicle (UAV) path planning problems. However, the search for optimal solutions for an optimization problem is usually expensive. For example, the UAV problem is a large-scale optimization problem with many constraints, which makes it hard to get exact solutions. Especially, it will be time-consuming when multiple UAV problems are waiting to be optimized at the same time. Evolutionary multi-task optimization (EMTO) studies the problem of utilizing the population-based characteristics of evolutionary computation techniques to optimize multiple optimization problems simultaneously, for the purpose of further improving the overall performance of resolving all these problems. EMTO has great potential in solving real-world problems more efficiently. Therefore, in this paper, we develop a novel EMTO algorithm using a classical PSO algorithm, in which the developed knowledge transfer strategy achieves knowledge transfer between task by synthesizing the transferred knowledges from a selected set of component tasks during the updating of the velocities of population. Two knowledge transfer strategies are developed along with two versions of the proposed algorithm. The proposed algorithm is compared with the multifactorial PSO algorithm, the SREMTO algorithm, the popular multifactorial evolutionary algorithm and a classical PSO algorithm on nine popular single-objective MTO problems and six five-task MTO problems, which demonstrates its superiority.

Highlights

Two novel versions of knowledge transfer strategy are proposed in this paper, which are employed in the two versions of the proposed Self-Regulated Particle Swarm MTO (SRPSMTO) respectively
To validate the effectiveness of knowledge transfer in the SRPSMTO, this experiment is conducted on the nine Multi-task optimization (MTO) problems from Table 1 in comparison with a traditional Particle swarm optimization (PSO) algorithm
As the PSO employs same parameter settings as the SRPSMTO, the difference between them will demonstrate the effectiveness of knowledge transfer in the proposed SRPSMTO

Summary

Introduction

MTO is very promising in improving the optimization performance of multiple real-world problems, such as the path planning for multiple UAVs. Note that, UAV path planning problem aims at finding a satisfactory path within moderate computation resources and affordable time [8]. Over the past few decades, population-based evolutionary computation techniques (ECs) have been established, and have shown promising results in handling nonlinear, multimodal and NP-hard problems [31,32,33,34]. Most of these techniques can only solve a single optimization problem. Evolutionary multi-task optimization (EMTO) [2]

Methods

Results

Conclusion