LSTM Based 24 hours Ahead Forecasting of Solar PV System for Standalone Household System
S U Sabareesh, K S N Aravind, Kandru Bhargav Chowdary, S Syama, Kirthika Devi V S
Abstract
A rapid expansion in the technology of solar PV energy in recent years has paved the way for PV market to grow resulting in a cost reduction in material. Hence, technological improvements are eminent to maintain the stable working of the system. In order to create a system many techniques and modules are used like, MPPT algorithms to track the power which increases real-time efficiency, and a battery management system to efficiently manage the stored energy from the battery. This paper aims to design a forecasting model to predict the weather and load of the standalone system to prepare the battery for future use. The forecasting is done using Machine learning and Deep learning tools like RNN, LSTM, and GRU and the results are fed into the system in MATLAB Simulink simulation platform.