Adventures of a multidimensional freak

This is Juan Julián Merelo Guervós English-language blog. He teaches computer science at the University of Granada, in southern Spain. Come back here to read about politics, technology, with a new twist

Latest comments

  • alex en Ants and roaches at Deneubourg's lab
  • jnyandrss en About conference poster design and defense
  • top 10 protein shakes en Riddles in Kafka on the shore
  • alex en Field guide to genetic programming
  • dubai five palm hotel en Äppärätti in Super Sad True Love Story
  • sjaden en Ants and roaches at Deneubourg's lab
  • Micah en About conference poster design and defense
  • jnyandrss en About conference poster design and defense
  • tffnysrys en About conference poster design and defense
  • alexender en Ants and roaches at Deneubourg's lab
  • Blogs Out There

    Nelson Minar's Blog
    Jeremy Zawodny's Blog
    Complexes, Carlos Gershenson's blog
    IlliGAL, Genetic Algorithms blog
    Blogging in the wind, Víctor R. Ruiz's blog

    Atalaya, my Spanish language blog
    Geneura@Wordpress, our research group's blog.
    My home page

    Old stories

    Creative Commons License
    This work is licensed under a Creative Commons License.

    Inicio > Historias > Browser-based distibuted evolutionary computation

    Browser-based distibuted evolutionary computation

    I have just uploaded to ArXiV preprints our paper Browser-based distributed evolutionary computation: performance and scaling behavior. The blurb:
    The challenge of ad-hoc computing is to find the way of taking advantage of spare cycles in an efficient way that takes into account all capabilities of the devices and interconnections available to them. In this paper we explore distributed evolutionary computation based on the Ruby on Rails framework, which overlays a Model-View-Controller on evolutionary computation. It allows anybody with a web browser (that is, mostly everybody connected to the Internet) to participate in an evolutionary computation experiment. Using a straightforward farming model, we consider different factors, such as the size of the population used. We are mostly interested in how they impact on performance, but also the scaling behavior when a non-trivial number of computers is applied to the problem. Experiments show the impact of different packet sizes on performance, as well as a quite limited scaling behavior, due to the characteristics of the server. Several solutions for that problem are proposed.

    We have also sent it to a conference; let's expect we get lucky. Basically, the paper is about a Ruby on Rails-based distributed evolutionary computation system that offloads to the browser the fitnesss evaluation, with some success (but not complete success). Suggestions and questions are always welcome.

    2007-01-18 10:47 | 2 Comment(s) | Filed in

    Referencias (TrackBacks)

    URL de trackback de esta historia


    De: Praveen Fecha: 2007-03-18 20:04

    We this work seems to be quite interesting. I was in a discussion recently on how implement different distrubuted computing architectures for our problems, which involve large amounts of computational resources. BOINC was one of the options, but currently we will be working with Beowulf. There are ethical issues involved with BOINC, for example the user may not be happy to install softwares provided by by somebody. You may want to put up an online demo or provide code so that more users will get interested in it.

    De: JJ Fecha: 2007-03-18 20:27

    The code is indeed available in RubyForge. It's not exactly what I would call production quality, but, well, we will happily accept volunteers. This paper was flunked rejected by GECCO, BTW... and for all the wrong reasons.
    Ethical problems are not totally solved, anyways. You only traslate your trust to your browser, since the experiments can't escape it, but you would still be providing CPU time on a volunteer basis.

    Dirección IP: (04eea2403e)
    ¿Cuánto es: mil + uno?

    © 2002 - 2008 jmerelo
    Powered by Blogalia