The Conception of the New Agent-Based Platform for Modeling and Implementation of Parallel Evolutionary Algorithms
Author(s) -
Sara Sabba,
Salim Chıkhı
Publication year - 2014
Publication title -
international journal of intelligent systems and applications
Language(s) - English
Resource type - Journals
eISSN - 2074-9058
pISSN - 2074-904X
DOI - 10.5815/ijisa.2014.04.02
Subject(s) - computer science , computation , range (aeronautics) , evolutionary algorithm , quality (philosophy) , evolutionary computation , algorithm , mathematical optimization , artificial intelligence , mathematics , philosophy , materials science , epistemology , composite material
Evolutionary algorithms (EAs) are a range of problem-solving techniques based on mechanisms inspired by biological evolution. Nowadays, EAs have proven their ability and effectiveness to solve combinatorial problems. However, these methods require a considerable time of calculation. To overcome this problem, several parallelization strategies have been proposed in the literature. In this paper, we present a new parallel agent-based EC framework for solving numerical optimization problems in order to optimize computation time and solutions quality.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom