Benchmarks for solar radiation time series forecasting

• Published in: Renewable energy Vol. 191; pp. 747 - 762
• Main Authors: Voyant, Cyril, Notton, Gilles, Duchaud, Jean-Laurent, Gutiérrez, Luis Antonio García, Bright, Jamie M., Yang, Dazhi
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2022; Elsevier
• Subjects: Benchmark; Combination; Environmental Sciences; Exponential smoothing; Filtering; Forecast; Irradiation; Statistics; Exponential smoothing; Irradiation; Benchmark; Filtering; Combination; Forecast; Exponential Smoothing; Irradiation Filtering Exponential Smoothing Combination Benchmark Forecast
• ISSN: 0960-1481; 1879-0682
• DOI: 10.1016/j.renene.2022.04.065

With an ever-increasing share of intermittent renewable energy in the world's energy mix, there is an increasing need for advanced solar power forecasting models to optimize the operation and control of solar power plants. In order to justify the need for more elaborate forecast modeling, one must compare the performance of advanced models with naïve reference methods. On this point, a rigorous formalism using statistical tools, variational calculation and quantification of noise in the measurement is studied and five naïve reference forecasting methods are considered, among which there is a newly proposed approach called ARTU (a particular autoregressive model of order two). These methods do not require any training phase nor demand any (or almost no) historical data. Additionally, motivated by the well-known benefits of ensemble forecasting, a combination of these models is considered, and then validated using data from multiple sites with diverse climatological characteristics, based on various error metrics, among which some are rarely used in the field of solar energy. The most appropriate benchmarking method depends on the salient features of the variable being forecast (e.g., seasonality, cyclicity, or conditional heteoroscedasity) as well as the forecast horizon. Hence, to ensure a fair benchmarking, forecasters should endeavor to discover the most appropriate naïve reference method for their setup by testing all available options. Among the methods proposed in this paper, the combination and ARTU statistically offer the best results for the proposed study conditions. •Benchmark of six Statistical Reference Methods (SRM).•Direct multi-step forecast strategy without training phase.•Validation of results using data from multiple climates.•Theory mixing statistical tools, variational calculation and measurement error.•Combination of models and ARTU are the best performing models.