A residual ensemble learning approach for solar irradiance forecasting

Brahma, Banalaxmi; Wadhvani, Rajesh

doi:10.1007/s11042-023-14616-6

Cited by 2 publications

(1 citation statement)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study also suggests that Gumbel probabilistic (GP) and ARIMA-GP models are more effective for separating beam (Hb) and diffuse (Hd) from global solar radiation (H) than empirical or machine learning models. Brahma & Wadhvani propose a new residual ensemble learning approach that uses advanced base models, Deep Neural Networks (DNNs) and Recurrent Neural Networks (RNNs), for solar irradiance forecasting, which is essential for efficient solar energy systems and sustainable power demand management [11]. The proposed approach consists of three modules that focus on data collection and analysis, feature selection, and the development of an accurate and robust forecast model.…”

Section: Introductionmentioning

confidence: 99%

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

Najdawi,

Villarreal

2023

EPE

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%