Proc. SPIE. 11126, Wide Bandgap Materials, Devices, and Applications IV
KEYWORDS: Photovoltaics, Solar energy, Data modeling, Solar cells, Neural networks, Artificial intelligence, Modulation transfer functions, Autoregressive models, Network architectures, Systems modeling
Solar energy is an intermittent source and purely Photo-voltaic (PV) based, or PV and storage based microgrids require characterization and modelling of PV resources for an effective planning and effective operations. In this research work long-short term memory (LSTM) as a recurrent neural network model is created for forecasting the PV solar resources, in which can assist in quantifying PV generation in various time intervals (hourly, daily, weekly). PV based microgrids often experience expensive or inaccurate resources planning due to the lack of accurate forecasting tools. The proposed LSTM model is simulated based on a real-time basis and the results are analyzed for its impact on planning and operations, and compared with conventional models such as Support Vector Machines - Regression (SVR). Hence, this model can be integrated further with existing energy management (demand side) and monitoring systems to streamline microgrid operations in its entirety.
Conference Committee Involvement (2)
Wide Bandgap Materials, Devices, and Applications IV
15 August 2019 | San Diego, California, United States
Wide Bandgap Power and Energy Devices and Applications III
21 August 2018 | San Diego, California, United States