Smart Grids Challenge: A competitive variant for Single Objective Numerical Optimization
In this work, we present a new algorithm (AJSO) for high-dimensional single objective problems. It is well known that nding high quality solutions is still a challenge for complex problems like those found in the literature as well as in real world concerning Smart Grids scenarios. Our proposal AJS...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/114206 |
| Aporte de: |
| Sumario: | In this work, we present a new algorithm (AJSO) for high-dimensional single objective problems. It is well known that nding high quality solutions is still a challenge for complex problems like those found in the literature as well as in real world concerning Smart Grids scenarios. Our proposal AJSO is an improvement on a state-of-the-art differential Evolution (DE) based algorithm known as SHADE. More speci cally, AJSO implements two novel mutation strategies and also incorporates a mechanism for mantaining and taking good solutions from a special archive when a particular condition during the exploration process is de- tected. To compare the performance of AJSO, the benchmark given in the WCCI/GECCO 2020 is used. This challenge consisted of opti- mization problems represented in two testbeds of Smart Grids problems. In this paper we adopted the guidelines given in the WCCI/GECCO 2020 competition. Experimental results show that AJSO outperforms SHADE in the two studied testbeds. |
|---|