Novel Field-Support Vector Regression-Based Soft Sensor for Accurate Estimation of Solar Irradiance

An accurate measurement of the solar irradiance is of significance for evaluating and developing of solar renewable energy systems. Soft sensors are used to provide feasible and economical alternatives to costly physical measurement instruments (e.g., pyranometers and pyrheliometers). Conventional soft-sensing methods assume that input data are identically and independently distributed (i.i.d.) and calculate an estimate of the solar irradiance via a regression model. However, different ambient temperatures result in various current-voltage characteristics, meaning that the i.i.d. assumption is violated. To improve the estimation accuracy, a field-support vector regression soft sensor is proposed to estimate the irradiance levels from photovoltaic (PV) electrical characteristics. The soft sensing system groups its input data into several fields in accordance with ambient temperatures. By transforming the original data into a style-free and i.i.d. space, the soft sensing model achieves better estimation performance. The proposed soft sensor can be easily implemented through a PV module, a thermometer, a current sensor, and a DSP development board. It is validated by simulations and experimental prototyping using real outdoor measurements.

Duke Scholars

Author Kaizhu Huang DKU Faculty