Differential Evolution Implementation for Power Quality Disturbances Monitoring using OpenCL

• Main Authors: SOLIS-MUNOZ, F. J., OSORNIO-RIOS, R. A., ROMERO-TRONCOSO, R. J., JAEN-CUELLAR, A. Y.
• Format: Article
• Language: English
• Published: Stefan cel Mare University of Suceava 2019-05-01
• Series: Advances in Electrical and Computer Engineering
• Subjects: evolutionary computation; parallel programming; parallel processing; power quality; power system faults
• Online Access: http://dx.doi.org/10.4316/AECE.2019.02002

This article presents a new methodology to implement a computational parallel scheme based on Differential Evolution (DE) algorithm through the use of Graphical Processing Units (GPU). A system application in which it is possible to perform an online monitoring of Power Quality Disturbances (PQD) in electric grids is presented as a case study, where a fitting of the parameters of a mathematical model is performed through this technique. Hyper-parameter optimization of the parallel Differential Evolution algorithm is performed for the assigned fitting function. As a result of this parallel implementation, a speed-up of 37 times compared with the serial implementation is achieved by using a single low budget GPU. The work presented shows a significant speed and accuracy improvement compared with Micro-Genetic Algorithm for Power Quality Analysis (MGA-PQA) technique.