Implementation of a Genetic Algorithm for Real Valued, Multi-Objective Non-Linear Optimization
Nathan Denny
December 9, 1999




Abstract: I present a simple genetic algorithm for optimizing a sum of objective functions, subject to a set of constraints.  I detail the specifics of the genetic algorithm implementation and the results of some very small test cases.  I will briefly discuss the parallelizability of genetic algorithms, and illustrate a few features implemented to support distributed evolution.
 

  1. Introduction
  2. The General Genetic Algorithm
  3. Project Specifics
  4. Distributed Computing Features
  5. Conclusions

Source code for the project may be downloaded.
Please visit the Python web site to obtain an interpreter*.
(*Note: The ga_serv.py file requires a multi-threaded interpreter.)