Welcome to the Localized MPPT for PV Systems using Fuzzy-weighted ELM project Homepage!

The solar irradiance data classification is greatly helpful in identifying the perturbation sizes for perturb-and-observe (P&O) maximum power point tracking (MPPT) method. In this project, we observe the solar irrandiance variation in two location in the United States: Humboldt State University (HSU) and University of Nevada, Las Vegas (UNLV). The solar irradiance data is freely available at MIDC Homepage.

The solar irradiance patterns for the two locations are completely different:

The data can be easily categorized as coastal area patterns and desert area patterns. About 60% of the data collected in this project can be easily labeled manually; however, the rest can be hardly to tell due to the specific weather conditions.

In this study, a fuzzy weighted ELM framework is proposed to assign each ambiguous history graph a fuzzy weight, indicating the level of that particular graph belonging to the coastal area or desert area. The entire assignment part is automatic!

First, a traditional ELM is used to assign each downloaded sample a label together with a weight. The fuzzy weighted ELM is trained by those labeled samples and used to automatically classify the ambiguous samples with providing the confidence levels.

The source codes of traditional ELM and fuzzy weighted ELM are freely available.

 


Back to Yan Ke's Homepage.