A brief history and critique of the developments in of particle swarm optimisation [Student Research Proposal]

Kenny, Ian (2008). A brief history and critique of the developments in of particle swarm optimisation [Student Research Proposal]. Technical Report 2008/12; Department of Computing, The Open University.

DOI: https://doi.org/10.21954/ou.ro.00016071


Swarm Computing1 is a relatively new optimisation paradigm. The basic premise is to model natural phenomena such as swarms, flocks and shoals, in order to solve nonlinear problems. There are currently two main heuristic techniques, Ant Colony Optimisation (ACO), developed by Dorigo[81], and Particle Swarm Optimisation (PSO) developed by Kennedy and Eberhart[187]. Ant Colony Optimisation attempts to model the pheromone trails of ants whilst they search for food. Particle Swarm Optimisation attempts to model bird flocks or swarms of bees by modelling their collective social influence. I have decided to concentrate on Particle Swarm Optimisation in my research. I consider it has greater unexplored potential, especially as it does not require the problem to be graphable. Much of the current research on particle swarm optimisation concerns the correct selection of the runtime parameters to ensure convergence. I therefore want to explore my conjecture that it is a more flexible approach to solving optimisation problems. In the vast majority of real-world applications, to which PSO has been applied, it is used as a data pre processor for a neural network or similar post processing system. Swarm Computing has not been applied to very many real-world applications. Whilst the travelling salesman problem and other similar standard optimisation problems all have applications, my intention is to explore an application of swarm computing, specifically, particle swarm optimisation to a real-world problem directly. Ideally I'd like to apply PSO to EMG or EEG data. My ideas centre on two Family or Cultural swarm questions: Can a hierarchy of swarms be introduced to PSO to increase diversity and encourage the spread of information across the solution space? Can that information be used effectively to guide the collective swarm to a better.1 Swarm Computing is often called Swarm Intelligence however, my preferred term is Swarm Computing.

Viewing alternatives


Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions
No digital document available to download for this item

Item Actions