Feature selection-based irradiance forecast for efficient operation of a stand-alone PV system

Abstract

Solar irradiance (SI) forecasting and determination of optimum tilt angle (OTA) of photovoltaic (PV) panels are the key strategies for improving the power output of PV systems. Precise SI forecasting offer valuable information regarding the predictable accessibility of solar energy, empowering PV system operators to make informed decisions for PV system optimization. This research uses a bi-directional long short-term memory (Bi-LSTM) hybrid network to forecast SI. Then, the OTA of the PV module is estimated by applying the forecasted SI data to the ASHRAE (American Society of Heating, Refrigerating and Air-conditioning Engineers) SI model. The performance of the Bi-LSTM hybrid network to estimate SI is compared with the observed data and the other existing forecasting models in the literature. The impact of OTA in improving PV power output is evaluated by comparing the solar irradiance received on both tilted and horizontal surfaces. This work has been experimentally implemented using the PV module setup at Thiagarajar College of Engineering, Madurai, Tamil Nadu, India. The OTA obtained by the proposed method yielded an increased output PV power compared to all other tilt angle approaches in the literature.