Study on encoding schemes in compact genetic algorithm for the continuous numerical problems

In this paper, we experimented how the performance of compact genetic algorithms (cGAs) become different according to two competitive encoding schemes: binary encoding and gray encoding scheme. We apply two encoding schemes to original cGA in various numerical problems including continuous and multimodal problems as well as unimodal problems. Experimental results unexpectedly show that the binary encoding is more effective in the almost the problems using an original cGA, unlike the case of using GA.