Parallel Genetic Programming: Component Object-based Distributed Collaborative Approach

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Tanev:2001:ICOIN,

• author = "Ivan Tanev and Takashi Uozumi and Koichi Ono",
• title = "Parallel Genetic Programming: Component Object-based Distributed Collaborative Approach",
• booktitle = "Proceedings of the 15th International Conference on Information Networking (ICOIN-15)",
• year = "2001",
• pages = "129--136",
• keywords = "genetic algorithms, genetic programming, DCOM, DCPGP, Internet, autonomous subpopulations, centralized manager, coarse grained inherent parallelism, communicating entities, communication network, communication paradigm, component object based distributed collaborative approach, computational performance, cost-efficient clusters, distributed collaborative approach, distributed collaborative parallel GP, distributed component object model, dynamic scaling-up features, generic support, global migration broker, globally fittest individuals, linear speedup characteristics, parallel genetic programming, performance demands, semi-isolated subpopulations, true system model, Internet, distributed object management, groupware, parallel programming, workstation clusters",
• DOI = "doi:10.1109/ICOIN.2001.905345",
• size = "8 pages",
• abstract = "We discuss the feasibility of applying the distributed collaborative approach for improving the computational performance of genetic programming (GP), implemented on cost-efficient clusters or the Internet. Proposed approach exploits the coarse grained inherent parallelism in GP among relatively autonomous subpopulations. Developed architecture of distributed collaborative parallel GP (DCPGP) features single, global migration broker and centralised manager of the semi-isolated subpopulations, which contribute to quick propagation of the globally fittest individuals among the subpopulations, reducing the performance demands to the underlying communication network, and achieving dynamic scaling-up features. DCPGP exploits the distributed component object model (DCOM) as a communication paradigm, which as a true system model offers generic support for the issues of naming, locating and security of communicating entities of developed architecture. Experimentally obtained speedup results show that close to linear speedup characteristics of the prototype of DCPGP are achieved on network of 8 workstations.",

}

Genetic Programming entries for Ivan T Tanev Takashi Uozumi Koichi Ono

Citations