Spatial and Temporal Day-Ahead Total Daily Solar Irradiation Forecasting: Ensemble Forecasting Based on the Empirical Biasing

Abstract

Total daily solar irradiation for the next day is forecasted through an ensemble of multiple machine learning algorithms using forecasted weather scenarios from numerical weather prediction (NWP) models. The weather scenarios were predicted at grid points whose longitudes and latitudes are integers, but the total daily solar irradiation was measured at non-integer grid points. Therefore, six interpolation functions are used to interpolate weather scenarios at non-integer grid points, and their performances are compared. Furthermore, when the total daily solar irradiation for the next day is forecasted, many data trimming techniques, such as outlier detection, input data clustering, input data pre-processing, and output data post-processing techniques, are developed and compared. Finally, various combinations of these ensemble techniques, different NWP scenarios, and machine learning algorithms are compared. The best model is to combine multiple forecasting machines through weighted averaging and to use all NWP scenarios.

Review on Spatio-Temporal Solar Forecasting Methods Driven by In Situ Measurements or Their Combination with Satellite and Numerical Weather Prediction (NWP) Estimates

“…The most commonly used machine learning methods in the studies reviewed are Artificial Neural Networks (ANN) [11,[94][95][96][97][98], Random Forest (RF) [41,65,73,99], Gradient Boosted Trees (GBT) [29,100], and Support-Vector Machine (SVM) [65,79,101]. All studies that used machine learning methods were compiled in Table 3.…”

“…There are authors that use as input a sequence of irradiance maps [42], a matrix representation of the spatial-temporal relationship between the sites [107], a graph structure where the nodes are the measurements locations and the vertices are the distance [108] or the correlation relationship between them [34]. The works considered in this review study refer to spatially distributed ground sensors (e.g., [15,103,127]), complemented with gridded satellite estimates (e.g., [97]), or NWP forecasts (e.g., [29,32,65,99]), or a combination of these (e.g., [11,24,29]). The numbers of sites or pixels considered in a model can vary from less than 10 (e.g., [41,60,127]) to more than 100 (e.g., [23,30,34]).…”

“…The authors emphasized in their work's title a few spatial characteristics that were found to be referred differently. For instance, the most used was spatio-temporal, being found written differently as "spatial-temporal" [59][60][61], "spatiotemporal" [7,23,[62][63][64], and "spatial and temporal" [65,66]. To achieve a compilation as complete as possible, the spatio-temporal references of these works were also included.…”

A Novel Feature Selection and Short-Term Price Forecasting Based on a Decision Tree (J48) Model

“…Gonzalez et al [28] discussed regression tree-based models, like bagging and random forests, to identify the inputs dominating the marginal price and highlighted the effectiveness of the proposed ensemble of tree-based models. Baek et al [29] presented a next day forecasted for total daily solar irradiation through an ensemble of multiple machine learning algorithms using forecasted weather scenarios from numerical weather prediction (NWP) models. Many data trimming techniques, such as outlier detection, input data clustering, and input data pre-processing, are developed and compared.…”

ANFIS-Based Peak Power Shaving/Curtailment in Microgrids Including PV Units and BESSs

“…The concept of smart microgrids has emerged from high penetration of distributed generation (DG) and distributed/renewable energy resources (DERs/RERs) and energy storage systems (ESS) [1][2][3][4][5]. A microgrid is a small-scale, low-voltage power grid in the low voltage designed to solve energy issues locally and enhance flexibility.…”