Equilibrium Optimizer (EO)

EO is inspired by control volume mass balance to estimate both dynamic and equilibrium state. In EO, search agents randomly update their concentration (Position) with respect to some talented particles called equilibrium candidates to finally reach to equilibrium state as optimal results.

EO’s performance is validated against 58 mathematical functions including unimodal, multimodal, hybrid and composition functions as well as 3 engineering benchmark problems and its performance is compared to three classes of optimization methods; GA and PSO as the most well-studied metaheuristics, GWO, GSA and SSA as recently developed algorithms and CMA-ES, SHADE and LSHADE-SPACMA as high performance optimizers. Comprehensive statistical analysis revealed that EO is able to significantly outperform PSO, GA, GWO, GSA, SSA and CMA-ES while its performance is statistically similar to SHADE and LSHADE-SPACMA.

Main paper: A. Faramarzi, M. Heidarinejad, B. Stephens, S. Mirjalili, Equilibrium optimizer: A novel optimization algorithm, Knowledge-Based Systems. DOI: https://doi.org/10.1016/j.knosys.2019.105190.

The source code of EO is also available at GitHub: https://github.com/afshinfaramarzi/Equilibrium-Optimizer

If you don’t have access to the paper, just leave me a message at afaramar@hawk.iit.edu or afshin.faramarzi@gmail.com and I will send you the paper.