Probabilistic Forecasting of Solar Power: An Ensemble Learning Approach

Mohammed, Azhar Ahmed; Yaqub, Waheeb; Aung, Zeyar

doi:10.1007/978-3-319-19857-6_38

Cited by 45 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A preliminary version of this study has been presented as [8]. In this current paper, we have significantly extended our work by incorporating a more detailed description of our proposed method, as well as much more comprehensive experimental results.…”

Section: Our Contributionsmentioning

confidence: 98%

See 1 more Smart Citation

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

Mohammed¹,

Aung²

2016

Energies

Self Cite

View full text Add to dashboard Cite

Probabilistic forecasting accounts for the uncertainty in prediction that arises from inaccurate input data due to measurement errors, as well as the inherent inaccuracy of a prediction model. Because of the variable nature of renewable power generation depending on weather conditions, probabilistic forecasting is well suited to it. For a grid-tied solar farm, it is increasingly important to forecast the solar power generation several hours ahead. In this study, we propose three different methods for ensemble probabilistic forecasting, derived from seven individual machine learning models, to generate 24-h ahead solar power forecasts. We have shown that while all of the individual machine learning models are more accurate than the traditional benchmark models, like autoregressive integrated moving average (ARIMA), the ensemble models offer even more accurate results than any individual machine learning model alone does. Furthermore, it is observed that running separate models on the data belonging to the same hour of the day vastly improves the accuracy of the results. Getting more accurate forecasts will help the stakeholders come up with better decisions in resource planning and control when large-scale solar farms are integrated into the power grid.

show abstract

Section: Our Contributionsmentioning

confidence: 98%

“…In this current paper, we have significantly extended our work by incorporating a more detailed description of our proposed method, as well as much more comprehensive experimental results. It is a summary version of the master's thesis [9] written by the first author and advised by the second author.…”

Section: Our Contributionsmentioning

confidence: 99%

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

Mohammed¹,

Aung²

2016

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…A way to reduce the covariance between each tree is needed, which is accomplished by using random forests. The studies of using PV forecasting with a random forest can be found in references [31][32][33][34].…”

Section: Random Forestmentioning

confidence: 99%

An Ensemble Learner-Based Bagging Model Using Past Output Data for Photovoltaic Forecasting

Choi¹,

Hur

2020

Energies

View full text Add to dashboard Cite

As the world is aware, the trend of generating energy sources has been changing from conventional fossil fuels to sustainable energy. In order to reduce greenhouse gas emissions, the ratio of renewable energy sources should be increased, and solar and wind power, typically, are driving this energy change. However, renewable energy sources highly depend on weather conditions and have intermittent generation characteristics, thus embedding uncertainty and variability. As a result, it can cause variability and uncertainty in the power system, and accurate prediction of renewable energy output is essential to address this. To solve this issue, much research has studied prediction models, and machine learning is one of the typical methods. In this paper, we used a bagging model to predict solar energy output. Bagging generally uses a decision tree as a base learner. However, to improve forecasting accuracy, we proposed a bagging model using an ensemble model as a base learner and adding past output data as new features. We set base learners as ensemble models, such as random forest, XGBoost, and LightGBMs. Also, we used past output data as new features. Results showed that the ensemble learner-based bagging model using past data features performed more accurately than the bagging model using a single model learner with default features.

show abstract

“…Moreover, combinations of different learning methods have been used to improve predictive performance, since it is expected that ensemble learning for probabilistic forecasts is able to result in better accuracy, on average, than any individual prediction. The main advantage of ensemble learning is the flexibility and ease implementation, since the individual models can be replaced (or added) for any other point forecast, such as any FTS method [18]. In this paper we provide a new probabilistic forecasting approach using seasonal FTS, ensemble learning and kernel density estimation (KDE).…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Forecasting with Seasonal Ensemble Fuzzy Time-Series

Silva¹,

Alves²,

Severiano³

et al. 2018

Proceedings XIII Brazilian Congress on Computational Inteligence

View full text Add to dashboard Cite

The aim of this paper is to propose a method for probabilistic forecasting based on the aggregation of seasonal Fuzzy Time-Series techniques with ensemble learning. The proposed method generates different seasonal FTS models and the best ones are combined into an ensemble learning. The forecasting procedure consists in evaluating individual models and combining their outputs into a continuous probability distribution using Kernel density estimation. The method was applied to SONDA dataset considering three seasonal indexes on solar radiation data. The best Ensemble models were those with 15 minutes interval index and Entropy partitioning in their different parameters. The built ensemble forecasts were then compared with ARIMA and Quantile Auto-Regression models using Continuous Ranked Probability Score (CRPS) metric. The Ensemble FTS method presented a slightly larger CRPS, especially for the Epanechnikov, Tophat and Triangular kernels, which suggests a better model.

show abstract

Probabilistic Forecasting of Solar Power: An Ensemble Learning Approach

Cited by 45 publications

References 14 publications

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

An Ensemble Learner-Based Bagging Model Using Past Output Data for Photovoltaic Forecasting

Probabilistic Forecasting with Seasonal Ensemble Fuzzy Time-Series

Contact Info

Product

Resources

About