In this study, a newly designed local model called locally weighted regression model is proposed for the regression problem. This model predicts the output for a newly submitted data point. In general, the local regression model focuses on an area of the input space specified by a certain kernel function (Gaussian function, in particular). The local area is defined as a region enclosed by a neighborhood of the given query point. The weights assigned to the local area are determined by the related entries of the partition matrix originating from the fuzzy C-means method. The local regression model related to the local area is constructed using a weighted estimation technique. The model exploits the concept of the nearest neighbor, and constructs the weighted least square estimation once a new query is provided given. We validate the modeling ability of the overall model based on several numeric experiments.

In the paper, a pattern analysis to decide whether the 1st local peak power point near open circuit voltage is the global peak power point or not, in case that the voltage and current at the 1st local peak power point are in a specific range, for Maximum Power Point Tracking on the photo voltaic power conversion system. When a solar cell panel array is shaded partially, multi-local peak power points can occur. That makes it hard to search the global peak power point. Through Tableau analysis using by piecewise linear solar cell model, V-I characteristic of a solar cell panel array circuit when partial shading problem happens, is simulated. The global peak power and the local peak power points is confirmed by simulations. Voltage and current values and patterns of V-I characteristic are analyzed. The generating efficiency of the solar cell panel array is improved, when the solar cell panel array circuit is operated at the power point estimated by setting up specific range.

No abstract