Region Encoding Helps Evolutionary Computation Evolve Faster: A New Solution Encoding Scheme in Particle Swarm for Large-Scale Optimization

In the last decade, many evolutionary computation (EC) algorithms with diversity enhancement have been proposed to solve large-scale optimization problems in big data era. Among them, social learning particle swarm (SLPSO) has shown good performance. However, as SLPSO uses different guidance information for particles maintain diversity, it often results slow convergence speed. Therefore, this article proposes a new region encoding scheme (RES) extend solution representation from single point region, which can help EC evolve faster. The RES is generic and applied SLPSO. Based on RES, novel adaptive search (ARS) designed one hand keep of other accelerate speed, forming ARS (SLPSO-ARS). SLPSO-ARS, each encoded so that some best (e.g., top P) carry out better solutions near their current positions. strategy offers greater chance discover nearby optimal helps speed whole population. Moreover, radius adaptively controlled based information. Comprehensive experiments all both IEEE Congress Evolutionary Computation 2010 (CEC 2010) 2013 2013) competitions are conducted validate effectiveness efficiency SLPSO-ARS investigate its important parameters components. experimental show achieve generally performance than compared algorithms.