Population size influence on the energy consumption of genetic programming

Evolutionary Algorithms (EAs) are routinely applied to solve a large set of optimization problems. Traditionally, their performance in solving those problems is analyzed using the fitness quality and computing time, effect evolutionary operators on both metrics used compare different versions EAs. Nevertheless, scientists face nowadays challenge considering energy efficiency addition computational which requires studying consumption algorithms. This paper discusses interest introducing power as new metric analyze standard genetic programming (GP). Two well-studied benchmark addressed three platforms, two approaches measure have been tested. Analyzing population size, results demonstrates its influence consumed: non-linear relationship was found between size required complete an experiment. analysis extended cache memory show exponential growth number misses increases, affects consumed. study shows that not only time or solution must be analyzed, but also find solution. Summarizing, this when GP applied, specific considerations how select parameter values taken into account if goal obtain solutions while searching for efficiency. Although has performed GP, we foresee it could similarly