COSC 4F90 Presentation - Nik Unger

Printer-friendly version

Mr. Nik Unger presents his papaer "COOPERATIVE PARTICLE SWARM OPTIMIZATION FOR DYNAMIC ENVIRONMENTS". 

When: Monday, Novermber 12, 2012

Time: 11:00 am - 12:00 pm

Room:  MCJ 328

Most optimization algorithms are designed to solve static, unchanging problems. However,many real-world problems exhibit dynamic behavior. Particle swarm optimization (PSO) is a successful metaheuristic methodology which has been adapted for locating and tracking optima in dynamic environments.

Recently, a powerful new class of PSO strategies using cooperative principles was shown to improve PSO performance in static environments. While there exist many PSO algorithms designed for dynamic optimization problems, only one cooperative PSO strategy has been introduced for this purpose.

This study proposes four new cooperative PSO strategies designed for dynamic environments, including the first cooperative PSO variant designed to locate and track multiple optima simultaneously. The new algorithms are shown to achieve significantly lower error rates when compared to well-known algorithms across problems with varying dimensionalities, temporal change severities, and spatial change severities.

This presentation presents our findings based on the four newly proposed algorithms. Challenges for PSO presented by dynamic environments and well-known strategies to overcome these challenges are also surveyed.

 

 

optima in dynamic environments.