A Chained Neural Network Model for Photovoltaic Power Forecast

Photovoltaic (PV) power forecasting is an important task preceding the scheduling of dispatchable power plants for the day-ahead market. Commercially available methods rely on conventional meteorological data and parameters to produce reliable predictions. These costs increase linearly with a rising number of plants. Recently, publicly available sources of free meteorological data have become available which allows for forecasting models based on machine learning, albeit offering heterogeneous data quality. We investigate a chained neural network model for PV power forecasting that takes into account varying data quality and follows the business requirement of frequently introducing new plants. This two-step model allows for easier integration of new plants in terms of manual efforts and achieves high-quality forecasts comparable to those of raw forecasting models from meteorological data.