Review of Different Error Metrics: A Case of Solar Forecasting

Abstract

Renewable energy systems (RES) are no longer confined to being used as a stand-alone entity in the modern era. These RES, especially solar panels are also used with the grid power systems to supply electricity. However, precise forecasting of solar irradiance is necessary to ensure that the grid operates in a balanced and planned manner. Various solar forecasting models (SFM) are presented in the literature to produce an accurate solar forecast. Nevertheless, each model has gone through the step of evaluation of its accuracy using some error measures. Many error measures are discussed in the literature for deterministic as well as probabilistic solar forecasting. But, each study has its own selected error measure which sometimes landed on a wrong interpretation of results if not selected appropriately. As a result, this paper offers a critical assessment of several common error metrics with the goal of discussing alternative error metrics and establishing a viable set of error metrics for deterministic and probabilistic solar forecasting. Based on highly cited research from the last three years (2019-2021), error measures for both types of forecasting are presented with their basic functionalities, advantages & limitations which equipped the reader to pick the required compatible metrics

Optimization and prediction of the cotton fabric dyeing process using Taguchi design-integrated machine learning approach

“…The results of the previously described machine-learning models for E%, F%, T%, and K/S, respectively, are summarized in Tables 2 , 3 , 4 , and 5 for convenience. In this work, a model's performance was quantified using three widely used error metrics, including RMSE, MAE, and R2, to exclude any possibility of bias in the evaluation of the model's performance 44 . Tables 2 , 3 , 4 , and 5 show that the training data's error metrics are RMSE 1 , MAE 1 , , whereas the testing data's error metrics are RMSE 1 , MAE 1 , and .…”

Sustainable fashion: Design of the experiment assisted machine learning for the environmental-friendly resin finishing of cotton fabric

“…For convenience, Tables 2 – 4 compile the findings of the aforementioned machine-learning models for CRA, TE and WI, respectively. In this study, three popular error metrics, including RMSE , MAE, and R 2, were used to quantify a model's performance to avoid bias in assessing the model performance [ 36 ]. As can be noticed in Tables 2 – 4 , the error metrics for the training data are RMSE 1 , MAE 1 , , while RMSE 1 , MAE 1 , are the error metrics denoted for the testing data.…”