Constrained real parameter optimization with an ecologically inspired algorithm

Most optimization problems have constraints of different types (e.g., physical, time, geometric, etc.), which modify the shape of the search space. We propose an ecologically inspired invasive weed optimization (IWO) algorithm to solve the constrained real-parameter optimization problems. Central to our approach is a parameter-free penalty function that we introduce. The adaptive nature of the penalty function makes the results of the algorithm mostly insensitive to low values of the penalty parameter. The proposed approach is compared with a state-of-the-art variant of particle swarm optimization (PSO) over 20 carefully chosen benchmarks from the test-suite of CEC 2006 competition on constrained real parameter optimization. The results indicate that in majority of the cases our approach was able to meet or beat the PSO-variant in a statistically meaningful way.