Validation of short and medium term operational solar radiation forecasts in the US

By Richard Perez, S. Kivalov, J. Schlemmer, Karl Hemker, D. Renné, T. Hoff. 2010

458 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Renewable Energy, Sustainability and the Environment

View Paper: https://www.semanticscholar.org/paper/449f476ddc4922d954cdf7123a7a1b9bdcfdfa4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Renewable Energy, Sustainability and the Environment

Citations in the corpus

The Economics of Solar Electricity (2013, background): “Less work has been done on solar forecasting than on wind forecasting, but an emerging literature should be useful for managing system operations as solar penetration increases (e.g., Perez et al., 2010; Mathiesen 4 & Kleissl, 2011; Marquez & Coimbra, 2011; Lorenz et al., 2011).”
Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database (2011, methodology): “As indicated by the RMSE and R2 values, Perez’s 2010 model (Perez et al., 2010) compares favorably with Model 1, which includes the same inputs (note that clear-sky GHI is approximated well by cosZ).”
Cloud-tracking methodology for intra-hour DNI forecasting (2014, methodology): “Different studies have been presented reaching spatial resolutions of 1 km2 (Schroedter-Homscheidt et al., 2009; Perez et al., 2010; Marquez and Coimbra, 2013b) and time horizons as short as 30 min (Hammer et al., 1999).”
Accurate photovoltaic power forecasting models using deep LSTM-RNN (2017, background): “Satellites, with their ability to monitor cloud movement over wide areas, have been employed for forecasting solar radiation [21, 36, 46].”
Comparison of numerical weather prediction solar irradiance forecasts in the US, Canada and Europe (2013, methodology): “Next, the concept of evaluation is introduced, and finally, we provide the results of the forecast comparison along with a short discussion and conclusions.”
Short-term irradiance variability: Preliminary estimation of station pair correlation as a function of distance (2012, methodology): “Further, as a planned next step of this work, we will analyze high resolution (1 km) satellite images and apply the cloud motion forecast algorithm (Perez et al., 2010b) to simulate high resolution, high frequency irradiance time series over any arbitrary extended area.”
Photovoltaic and solar power forecasting for smart grid energy management (2015, methodology): “Similar forecasts are obtained based on the images of the Geostationary Operational Environment Satellite in [18].”
Regional PV power prediction for improved grid integration (2011, background): “For forecast horizons from about 6 h onwards, forecasts based on numerical weather prediction (NWP) models typically out-perform the satellite based forecasts [10,11].”
Data-Driven Short-Term Solar Irradiance Forecasting Based on Information of Neighboring Sites (2019, methodology): “scores computed according to forecasting errors in [23] were 7.”
Proposed Metric for Evaluation of Solar Forecasting Models (2013, methodology): “This definition is related to the commonly used RMSE [4,6,8,9] where sometimes relative or normalized RMSE is used [4,6,9] with respect to the average irradiance.”
Intra-hour DNI forecasting based on cloud tracking image analysis (2013, methodology): “For 1-h ahead forecasting, Perez et al. (2010) obtained 8–10% improvement over persistence using cloud motion forecasts from satellite images; Marquez and Coimbra (2013) obtained 12–20% using a ANNs; and Martin et al. (2010) obtained 10–15% also using ANNs.”