Complex Disturbances Identification: A Novel PQDs Decomposition and Modeling Method

In the context of unprecedented attention to renewable energy, wind and photovoltaic power generations are widely used. However, this process introduces a large number of solid-state switching and nonlinear loads, which makes power quality disturbances (PQDs) complex and brings unknown challenges to power-pollution control. As a prerequisite for power-pollution control, this article proposes an automatic PQDs classification approach, which is suitable for complicated phenomena. First, an ensemble intrinsic timescale decomposition (EITD) method is proposed to decompose the PQDs, which overcomes the decomposition level's endpoint effect and frequency aliasing by adding Gaussian noise and integrating multiple subcomponents. Then, utilizing the global depthwise convolution layer and parameter rectified linear unit, a global depthwise shuffle CNN (GSCNN) is proposed to improve the performance and reduce the number of parameters. Based on EITD and GSCNN, an automatic framework is proposed to identify and classify complex PQDs. Simulation experiments and hardware platform tests show that the proposed framework has superior performance for complex and even nonlinear disturbances under different noise.

Automated summary

In this article, an automatic approach for power quality disturbances (PQDs) classification is proposed, which is suitable for complex phenomena. The proposed method includes ensemble intrinsic timescale decomposition (EITD) for decomposing PQDs and a global depthwise shuffle CNN (GSCNN) for improving performance and reducing parameters. Based on EITD and GSCNN, an automatic framework is created to identify and classify complex PQDs.