Profiling Communication in Distributed Genetic Algorithms

To what extent is distr ibution beneficial to the search quali ty and computational resources used by a genetic algori thm execution? Most distr ibuted genetic algorithms rely on communicating genetic informat ion, in the form of individual solutions, between concurrently evolving populations. Another way of effectively using the additional information generated by the parallel executions is the profi l ing approach to communicat ion, where populations decide whether their own performance is satisfactory, relative to the global average improvement curve. Thus, communicat ion between populations takes the form of improvement histories. This is shown to improve on the tradi t ional communication approach, in terms of both solution quality and execution performance.