Multiple simultaneous solution representations in a population based evolutionary algorithm

Abstract

The representation used for solutions in optimization can have a significant impact on the performance of the optimization method. Traditional population based evolutionary methods have homogeneous populations where all solutions use the same representation. If different representations are to be considered, different runs are required to investigate the relative performance. In this paper, we illustrate the use of a population based evolutionary method, Fresa, inspired by the propagation of Strawberry plants, which allows for multiple representations to co-exist in the population. Fresa is implemented in the Julia language. Julia provides dynamic typing and multiple dispatch. In multiple dispatch, the function invoked is determined, dynamically at run time, by the types of the arguments passed to it. This enables a generic implementation of key steps in the plant propagation algorithm which allows for a heterogeneous population. The search procedure then leads to a competition between representations automatically. A simple case study from the design of operating conditions for a batch reactor system is used to illustrate heterogeneous population based search.