Utilizing the Vector Autoregression Model (VAR) for Short-Term Solar Irradiance Forecasting

Abstract

Forecasting solar irradiance is a critical task in the renewable energy sector, as it provides essential information regarding the potential energy production from solar panels. This study aims to utilize the Vector Autoregression (VAR) model to forecast solar irradiance levels and weather characteristics in the San Francisco Bay Area. The results demonstrate a correlation between predicted and actual solar irradiance, indicating the effectiveness of the VAR model for this task. However, the model may not be sufficient for this region due to the requirement of additional weather features to reduce disparities between predictions and actual observations. Additionally, the current lag order in the model is relatively low, limiting its ability to capture all relevant information from past observations. As a result, the model's forecasting capability is limited to short-term horizons, with a maximum horizon of four hours.

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

“…This method achieved Root-Mean-Square Error (RMSE) of 0.893 and 0.659 for temperature and wind speed, respectively, showing a good fit with actual data. Najdawi et al [48] adopted a Vector Autoregression (VAR) model for forecasting short-term solar irradiance, using weather conditions (atmospheric pressure, temperature, and relative humidity) and solar irradiance, but faced limitations due to the model's low lag order, capping the forecast at four hours. Zhang et al [49] developed an Autoregressive Dynamic Adaptive (ARDA) model with no exogenous inputs, for real-time wind power forecasting, which, when compared with ARIMA and Long Short-Term Memory (LSTM) models, showed superior performance in accuracy, speed, and adaptability to wind data fluctuations.…”