Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units

• Published in: Energies (Basel) Vol. 12; no. 21; p. 4055
• Main Authors: Wojtkiewicz, Jessica, Hosseini, Matin, Gottumukkala, Raju, Chambers, Terrence Lynn
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 24.10.2019
• Subjects: Artificial intelligence; Big Data; Cloud cover; Deep learning; Electricity; Electricity distribution; Forecasting; gated recurrent units; Humidity; International conferences; Irradiance; Machine learning; Model accuracy; multivariate; Multivariate analysis; Neural networks; Physics; Power plants; Short term; Solar energy; solar irradiance; Static models; Stochasticity; Time series; time series forecasting; Variables; Weather forecasting; Louisiana; United States > US
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12214055

Variation in solar irradiance causes power generation fluctuations in solar power plants. Power grid operators need accurate irradiance forecasts to manage this variability. Many factors affect irradiance, including the time of year, weather and time of day. Cloud cover is one of the most important variables that affects solar power generation, but is also characterized by a high degree of variability and uncertainty. Deep learning methods have the ability to learn long-term dependencies within sequential data. We investigate the application of Gated Recurrent Units (GRU) to forecast solar irradiance and present the results of applying multivariate GRU to forecast hourly solar irradiance in Phoenix, Arizona. We compare and evaluate the performance of GRU against Long Short-Term Memory (LSTM) using strictly historical solar irradiance data as well as the addition of exogenous weather variables and cloud cover data. Based on our results, we found that the addition of exogenous weather variables and cloud cover data in both GRU and LSTM significantly improved forecasting accuracy, performing better than univariate and statistical models.