Photovoltaic Power Forecasting: Assessment of the Impact of Multiple Sources of Spatio-Temporal Data on Forecast Accuracy

Abstract

The efficient integration of photovoltaic (PV) production in energy systems is conditioned by the capacity to anticipate its variability, that is, the capacity to provide accurate forecasts. From the classical forecasting methods in the state of the art dealing with a single power plant, the focus has moved in recent years to spatio-temporal approaches, where geographically dispersed data are used as input to improve forecasts of a site for the horizons up to 6 h ahead. These spatio-temporal approaches provide different performances according to the data sources available but the question of the impact of each source on the actual forecasting performance is still not evaluated. In this paper, we propose a flexible spatio-temporal model to generate PV production forecasts for horizons up to 6 h ahead and we use this model to evaluate the effect of different spatial and temporal data sources on the accuracy of the forecasts. The sources considered are measurements from neighboring PV plants, local meteorological stations, Numerical Weather Predictions, and satellite images. The evaluation of the performance is carried out using a real-world test case featuring a high number of 136 PV plants. The forecasting error has been evaluated for each data source using the Mean Absolute Error and Root Mean Square Error. The results show that neighboring PV plants help to achieve around 10% reduction in forecasting error for the first three hours, followed by satellite images which help to gain an additional 3% all over the horizons up to 6 h ahead. The NWP data show no improvement for horizons up to 6 h but is essential for greater horizons.

Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations

“…(vi) Make prediction interval from error distribution and deterministic forecasting The PIs comprise upper and lower boundaries. In this study, these boundaries are obtained by taking confidence intervals from set in (6). The set is not guaranteed to be distributed as a normal distribution; thus, how to make PIs should be investigated further in future work.…”

“…Ref. [6] proposed a model to forecast six hours based on 136 PV installations in France. Irradiance forecasting for 11 PVs distributed in a certain region is performed as accumulated generations [8].…”

Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations

“…The PIs comprise upper and lower boundaries. In this study, these boundaries are obtained by taking confidence intervals from set D t in (6). The set D t is not guaranteed to be distributed as a normal distribution; thus, making PIs should be investigated further in future work.…”

“…PVs are distributed within a specific area connected to the same distribution network. Thus, a spatiotemporal model is required to extract and use spatial and temporal data from multiple PVs to improve PI reliability [5][6][7]. The authors of [5] proposed a deep learning framework that can generate PV forecasts for multiple regions and horizons with 56 locations in the US, while [6] proposed a model to forecast six hours based on 136 PV installations in France.…”

“…Thus, a spatiotemporal model is required to extract and use spatial and temporal data from multiple PVs to improve PI reliability [5][6][7]. The authors of [5] proposed a deep learning framework that can generate PV forecasts for multiple regions and horizons with 56 locations in the US, while [6] proposed a model to forecast six hours based on 136 PV installations in France. Irradiance forecasting for 11 PVs distributed in a specific region is performed as accumulated generations [8].…”