History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining

Abstract

Text mining is an emerging topic that advances the review of academic literature. This paper presents a preliminary study on how to review solar irradiance and photovoltaic (PV) power forecasting (both topics combined as "solar forecasting" for short) using text mining, which serves as the first part of a forthcoming series of text mining applications in solar forecasting. This study contains three main contributions: (1) establishing the technological infrastructure (authors, journals & conferences, publications, and organizations) of solar forecasting via the top 1000 papers returned by a Google Scholar search; (2) consolidating the frequently-used abbreviations in solar forecasting by mining the full texts of 249 ScienceDirect publications; and (3) identifying key innovations in recent advances in solar forecasting (e.g., shadow camera, forecast reconciliation). As most of the steps involved in the above analysis are automated via an application programming interface, the presented method can be transferred to other solar engineering topics, or any other scientific domain, by means of changing the search word. The authors acknowledge that text mining, at its present stage, serves as a complement to, but not a replacement of, conventional review papers.

Text Mining in Big Data Analytics

“…Grubert [212] investigated the Life Cycle Assessment (LCA) literature by applying unsupervised topic modeling to more than 8200 environment-related LCA journal article titles and abstracts published between 1995 and 2014. Yang et al [213] mined 1000 abstracts from the Google Scholar database for search results for technology infrastructure of solar forecasting, classified the concepts of solar forecasting on the full texts of 249 papers from Science Direct, and also undertook the keyword analysis and topic modeling on six handpicked papers on emerging technologies related to the subject. Moro et al [214] performed text mining over the whole textual contents of papers, excluding only the references and authors' affiliations, published in a tourism-related journal from 1996 to 2016.…”

Forecasting short-term dynamics of shallow cumuli using dynamic mode decomposition

“…Recent research has suggested that partial differential equation (PDE) fluid models can aid in cloud forecasting [24]. While three-dimensional PDE simulations can be computationally burdensome, there may be promise in the discovery of a suitable two-dimensional PDE model that operates in the photographic image spatial domain, using the method of Sparse Identification of Nonlinear Dynamics (SINDy) [3].…”

Nowcasting solar irradiance using an analog method and geostationary satellite images

“…The combination of different forecast methods has been recently identified as an essential trend in solar forecasting (Yang et al, 2018). The downscaling procedure presented herein is a simple example of such a combination.…”

“…For intrahour forecasting, machine learning methods or on site cloud tracking methods have been developed, while for more than six hours ahead and day ahead forecasts, Numerical Weather Prediction (NWP) forecasts are generally used as the primary source of information (Mathiesen et al, 2013;Thorey et al, 2015). Using satellite images provides information on horizontal cloud structures and has proven to be efficient for the intraday horizon (see the recent review by Yang et al, 2018). The widely studied cloud motion vector methods (Hammer et al, 1999;Lorenz et al, 2004;Escrig et al, 2013) estimate a motion field from successive cloud satellite images and produce a forecast by advecting the clouds.…”