A Comprehensive Review on Ensemble Solar Power Forecasting Algorithms

Abstract

With increasing demand for energy, the penetration of alternative sources such as renewable energy in power grids has increased. Solar energy is one of the most common and well-known sources of energy in existing networks. But because of its non-stationary and non-linear characteristics, it needs to predict solar irradiance to provide more reliable Photovoltaic (PV) plants and manage the power of supply and demand. Although there are various methods to predict the solar irradiance. This paper gives the overview of recent studies with focus on solar irradiance forecasting with ensemble methods which are divided into two main categories: competitive and cooperative ensemble forecasting. In addition, parameter diversity and data diversity are considered as competitive ensemble forecasting and also preprocessing and post-processing are as cooperative ensemble forecasting. All these ensemble forecasting methods are investigated in this study. In the end, the conclusion has been drawn and the recommendations for future studies have been discussed.

High Precision Modeling of Power Demand for Electricity Distribution Companies with frequent load shedding

“…Nonetheless, Random Forest and support vector machine have the highest performance among the classical models, yet computational resources and time required for support vector machine computation are more than Random Forest even with lower performance. This result agrees with [9,27]. In conclusion, the distribution that utilizes load shedding for meeting different region power needs should consider ANN models for regional short-term horizon power forecast when high computational resources are available but Random forest with low computational resources instead of Support Vector Machine.…”

Analysis of variables to determine their influence on renewable energy forecasting using ensemble methods

“… Pombo, Bacher, Ziras, Bindner, Spataru, & Sørensen [ 25 ] Ensemble models for solar power prediction Ensemble models based on random forests and gradient boosting algorithms showed high performance in predicting power output. Raj et al [ 26 ]; Debani et al [ 27 ]; Rahimi et al [ 28 ] …”

The Prediction of Low-Rise Building Construction Cost Estimation Using Extreme Learning Machine

“…Bagging, the abbreviation for bootstrap aggregating, is a widely deployed ensemble learning technique to improve the accuracy and robustness of ML models, including those used for predicting low-rise building prices. It involves creating multiple diverse copies of the same base model, training each copy on a different random subset of the training data, and then combining their predictions to make the final prediction [28], as depicted in Fig. 6.…”

“…Boosting is another potent ensemble learning technique for improving ML models' predictive performance, including those used for predicting low-rise building prices. Unlike bagging focusing on training multiple models independently and combining their predictions, boosting builds a concatenation of models sequentially, where each model tries to correct the errors made by its predecessors [28], as depicted in Fig. 7.…”