Training and testing of a single-layer LSTM network for near-future solar forecasting

Abstract

Increasing integration of renewable energy sources, like solar photovoltaic (PV), necessitates the development of power forecasting tools to predict power fluctuations caused by weather. With trustworthy and accurate solar power forecasting models, grid operators could easily determine when other dispatchable sources of backup power may be needed to account for fluctuations in PV power plants. Additionally, PV customers and designers would feel secure knowing how much energy to expect from their PV systems on an hourly, daily, monthly, or yearly basis. The PROGNOSIS project, based at the Cyprus University of Technology, is developing a tool for intra-hour solar irradiance forecasting. This article presents the design, training, and testing of a single-layer long-short-term-memory (LSTM) artificial neural network for intra-hour power forecasting of a single PV system in Cyprus. Four years of PV data were used for training and testing the model (80% for training and 20% for testing). With a normalized root mean squared error (nRMSE) of 10.7%, the single-layer network performed similarly to a more complex 5-layer LSTM network trained and tested using the same data. Overall, these results suggest that simple LSTM networks can be just as effective as more complicated ones.