Trends and gaps in photovoltaic power forecasting with machine learning

Alcañiz, Alba; Grzebyk, Daniel; Ziar, Hesan; Isabella, Olindo

doi:10.1016/j.egyr.2022.11.208

Cited by 49 publications

(20 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study employed five techniques, namely RT, GPR, ET, SVM, and ANN, to establish prediction models. These algorithms have been previously documented in the literature [24,[26][27][28] and won't be extensively detailed in this report. The ML models were implemented using MATLAB R2023b software alongside the Statistics and ML Toolbox.…”

Section: K-fold (Fivefold In This Study) Crossvalidation and Ml-based...mentioning

confidence: 99%

Analysis and Selection of Optimal Perovskite/Silicon Tandem Configuration for Building Integrated Photovoltaics Based on Their Annual Outdoor Energy Yield Predicted by Machine Learning

Nguyen,

Asada,

Raifuku

et al. 2024

Solar RRL

View full text Add to dashboard Cite

Accurate estimation of annual output energy yield (Eout,annual) for perovskite/silicon (PSK/cSi) tandem solar cells is pivotal in assessing their suitability for building integrated photovoltaics (BIPV). This study pioneers five machine learning models of ensembles of trees, Gaussian process regression, regression tree, support vector machine, and artificial neural network (ANN) to predict output power density and compute Eout,annual for 2T, 3T, and 4T PSK/cSi tandem configurations in Japan’s outdoor conditions. Seven predictive inputs of visible‐light solar irradiance, near‐infrared‐light solar irradiance, incident solar spectrum angle, solar module temperature, perovskite thickness, perovskite bandgap, and terminal of tandem configuration (T) drive the ML models. These models optimize Eout,1−month predictions using k‐fold cross‐validation and Bayesian algorithms, showcasing superior precision in Eout,annual prediction compared to prior models. The ANN model emerges as the best model, displaying the minimal error in predicting Eout,1month, used to estimate Eout,annual across five Japanese locations (Gifu, Naganuma, Okinoerabu, Tosu, and Tsukuba). Results from these locations in blue‐rich solar spectrum zones identify the 4T PSK/cSi tandem configuration, featuring the most outstanding mean maximal Eout,annual (93.63, 263.02, 153.59, and 91.75 kWh/m2 for the east, rooftop, south, and west directions), as the prime candidate for BIPV applications.This article is protected by copyright. All rights reserved.

show abstract

Section: K-fold (Fivefold In This Study) Crossvalidation and Ml-based...mentioning

confidence: 99%

Analysis and Selection of Optimal Perovskite/Silicon Tandem Configuration for Building Integrated Photovoltaics Based on Their Annual Outdoor Energy Yield Predicted by Machine Learning

Nguyen,

Asada,

Raifuku

et al. 2024

Solar RRL

View full text Add to dashboard Cite

show abstract

“…PV production depends on the amount of solar radiation reaching the PV cells on panels. As solar radiance is affected by current weather conditions such as cloudiness, temperature and windiness, it becomes difficult to plan and manage the energy within the system [2]. As the share of solar energy rapidly increases, so does the need for reliable and accurate PV production forecasting.…”

Section: Introductionmentioning

confidence: 99%

Advances in Short-Term Solar Forecasting: A Review and Benchmark of Machine Learning Methods and Relevant Data Sources

Pandžić,

Capuder

2023

Energies

View full text Add to dashboard Cite

Solar forecasting is becoming increasingly important due to the exponential growth in total global solar capacity each year. More photovoltaic (PV) penetration in the grid poses problems for grid stability due to the inherent intermittent and variable nature of PV power production. Therefore, forecasting of solar quantities becomes increasingly important to grid operators and market participants. This review presents the most recent relevant studies focusing on short-term forecasting of solar irradiance and PV power production. Recent research has increasingly turned to machine learning to address this challenge. The paper provides a discussion about building a solar forecasting model, including evaluation measures and machine learning method selection through analysed literature. Given that machine learning is data-driven, the focus of this review has been placed on data sources referenced in the literature. Open-access data sources have been compiled and explored. The main contribution of this paper is the establishment of a benchmark for assessing the performance of solar forecasting models. This benchmark utilizes the mentioned open-source datasets, offering a standardized platform for future research. It serves the crucial purpose of streamlining investigations and facilitating direct comparisons among different forecasting methodologies in the field of solar forecasting.

show abstract

“…Photovoltaic power generation relies mainly on solar resources and is affected by weather, resulting in periodic, intermittent, and random characteristics that affect the overall scheduling and stable operation of the power grid. Accurate prediction of photovoltaic power generation is the key to addressing these issues [2], [3]. This paper will use a deep learning method to predict photovoltaic power generation.…”

Section: Introductionmentioning

confidence: 99%

Short-term PV Power Prediction Based on SAGA-FCM and XGBoost

Zhong

Zhou

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The stable and economic operation of the power grid cannot be achieved without accurate prediction of PV plant power. To address the problem of unstable clustering quality of the fuzzy c-mean clustering algorithm, this paper proposes to combine the genetic algorithm and simulated annealing algorithm to optimize the FCM clustering algorithm, and then combine it with XGBoost to construct a short-term PV power generation prediction model. Firstly, the robustness of the clustering algorithm is improved. Secondly, the differences in power generation characteristics under different weather types are considered, and the prediction models under three typical weather types are separately trained. Finally, to verify the improvement of the model on prediction accuracy, different clustering methods are used to compare the prediction results, and the results show that the algorithm proposed in this paper has higher accuracy compared with the other three methods.

show abstract

Trends and gaps in photovoltaic power forecasting with machine learning

Cited by 49 publications

References 121 publications

Analysis and Selection of Optimal Perovskite/Silicon Tandem Configuration for Building Integrated Photovoltaics Based on Their Annual Outdoor Energy Yield Predicted by Machine Learning

Analysis and Selection of Optimal Perovskite/Silicon Tandem Configuration for Building Integrated Photovoltaics Based on Their Annual Outdoor Energy Yield Predicted by Machine Learning

Advances in Short-Term Solar Forecasting: A Review and Benchmark of Machine Learning Methods and Relevant Data Sources

Short-term PV Power Prediction Based on SAGA-FCM and XGBoost

Contact Info

Product

Resources

About