Mismatching and partial shading identification in photovoltaic arrays by an artificial neural network ensemble (ONLY DATASET)

Mismatching and partial shading identification in photovoltaic arrays by an artificial neural network ensemble

Michel Piliougine ([e-mail]) and Giovanni Spagnuolo ([e-mail])

UNIVERSITA DEGLI STUDI DI SALERNO
DIEM – Via Giovanni Paolo II 132. 84084 Fisciano (SA), Italy

Date: May 22nd, 2021
Version: 1.0

Filename: dataset.mat
Description:

This file contains the dataset related to the article titled
Mismatching and partial shading identification in photovoltaic arrays by an artificial neural network ensemble

This file has been stored using the native Matlab format for its workspace (*.mat)

Now, the variables stored in  the file are described:

Variables:
    (*) full_curvesOk_simulated
        Cell array with 5000 full IV curves simulated using the SDM, assuming uniform conditions
        Each IV curve is a 300 x 2 matrix (double), with column 1= voltage (V), column 2 = current (A)
              (all the points of the simulated IV curve, not only those around MPP) 

        From this variable, the following splitting has been made:
        TRAINING => from index 1 to 3500
        VALIDATION => from index 3501 to 4000
        TEST  => from index 4001 to 5000 (referred as TEST#1 in the paper)

    (*) full_curvesSh_simulated
        Cell array with 5000 full IV curves simulated using the SDM, assuming FAULTY conditions (steeped curve)
        Each IV curve is a 300 x 2 matrix (double), with column 1= voltage (V), column 2 = current (A)
              (all the points of the simulated IV curve, not only those around MPP) 

        From this variable, the following splitting has been made:
        TRAINING => from index 1 to 3500
        VALIDATION => from index 3501 to 4000
        TEST  => from index 4001 to 5000 (referred as TEST#1 in the paper)

    (*) full_curvesOk_experimental
        Cell array with 1000 full IV curves measured of a real PV module, assigned to be measured under
        normal operating conditions, and assumed to be classified as HEALTHY

        Each IV curve is a n  x 2 matrix (double), with column 1= voltage (V), column 2 = current (A)
              (all the points of the simulated IV curve, not only those around MPP)
        where n is the number of experimental points of each IV curve, although it is around 100, but it could
        be different for each measured IV curve.

        All these curves has been used for testing
        TEST  => from index 1 to 1000 (referred as TEST#2 in the paper)

    (*) full_curvesSh_experimental
        Cell array with 1000 full IV curves measured of a real PV module, assigned to be measured under
        mismatched operating conditions, and assumed to be classified as FAULTY

        Each IV curve is a n  x 2 matrix (double), with column 1= voltage (V), column 2 = current (A)
              (all the points of the simulated IV curve, not only those around MPP)
        where n is the number of experimental points of each IV curve, although it is around 100, but it could
        be different for each measured IV curve.

        All these curves has been used for testing
        TEST  => from index 1 to 1000 (referred as TEST#2 in the paper)