A review on physical and data-driven based nowcasting methods using sky images
Amongst all the renewable energy resources (RES), solar is the most popular form of energy source and is of particular interest for its widely integration into the power grid. However, due to the intermittent nature of solar source, it is of the greatest significance to forecast solar irradiance to ensure uninterrupted and reliable power supply to serve the energy demand. There are several approaches to perform solar irradiance forecasting, for instance satellite-based methods, sky image-based methods, machine learning-based methods, and numerical weather prediction-based methods. In this paper, we present a review on short-term intra-hour solar prediction techniques known as nowcasting methods using sky images. Along with this, we also report and discuss which sky image features are significant for the nowcasting methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Solar Irradiance ForecastingSimilar Papers 제목 키워드 기반
Improving deep learning precipitation nowcasting by using prior knowledge
Deep learning methods dominate short-term high-resolution precipitation nowcasting in terms of prediction error. However, their operational usability is limited by difficulties explaining dynamics behind the predictions,…
Deep LearningPredictionSkilful nowcasting of extreme precipitation with NowcastNet
Extreme precipitation is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through skilful nowcasting that has high resolution, long lead times and loc…
Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting
Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smoothed, spectrally decaying predictions that blur convective details an…
A review of radar-based nowcasting of precipitation and applicable machine learning techniques
A 'nowcast' is a type of weather forecast which makes predictions in the very short term, typically less than two hours - a period in which traditional numerical weather prediction can be limited. This type of weather pr…
BIG-bench Machine LearningPhysical Scales Matter: The Role of Receptive Fields and Advection in Satellite-Based Thunderstorm Nowcasting with Convolutional Neural Networks
The focus of nowcasting development is transitioning from physically motivated advection methods to purely data-driven Machine Learning (ML) approaches. Nevertheless, recent work indicates that incorporating advection in…