Very short term forecasting in global solar irradiance using linear and nonlinear models

Orjuela-Cañón, Álvaro David; Hernández, Johann; Rivero, Cristian Rodríguez

doi:10.1109/pepqa.2017.7981691

Cited by 17 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many proposals apply machine learning algorithms to predict both photovoltaic energy production and Solar Irradiance. Orjuela-Cañón et al [9] compare several machine learning algorithms, both linear and nonlinear, such as Regression Trees, Artificial Neural Networks, and a Seasonal Autoregressive model. Gagne et al [10] which compares Gradient Boosting and Random forests, both of which are combinations of simple models.…”

Section: Introductionmentioning

confidence: 99%

Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production

Huertas‐Tato

Brito

2018

Energies

View full text Add to dashboard Cite

Solar energy forecasting is an active research problem and a key issue to increase the competitiveness of solar power plants in the energy market. However, using meteorological, production, or irradiance data from the past is not enough to produce accurate forecasts. This article aims to integrate a prediction algorithm (Smart Persistence), irradiance, and past production data, using a state-of-the-art machine learning technique (Random Forests). Three years of data from six solar PV modules at Faro (Portugal) are analyzed. A set of features that combines past data, predictions, averages, and variances is proposed for training and validation. The experimental results show that using Smart Persistence as a Machine Learning input greatly improves the accuracy of short-term forecasts, achieving an NRMSE of 0.25 on the best panels at short horizons and 0.33 on a 6 h horizon.

show abstract

Section: Introductionmentioning

confidence: 99%

Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production

Huertas‐Tato

Brito

2018

Energies

View full text Add to dashboard Cite

show abstract

“…4, PV power will be measured twice in each control cycle at time instants and + 2. Based on these two measurements, the PV generation at time instant + 5 is estimated through a linear forecast model [22] as…”

Section: B Pv Power Prediction and Control Cycle Designmentioning

confidence: 99%

Real-Time Coordinated Voltage Control of PV Inverters and Energy Storage for Weak Networks With High PV Penetration

Wang

Bai

Yan

2018

IEEE Trans. Power Syst.

181

View full text Add to dashboard Cite

Abstract-There are more large-scale PV plants being established in rural areas due to availability of low priced land. However, distribution grids in such areas traditionally have feeders with low X/R ratios, which makes the independent reactive power compensation method less effective on voltage regulation. Consequently, upstream Step Voltage Regulator (SVR) may suffer from excessive tap operations with PV induced fast voltage fluctuations. Although a battery energy storage system (BESS) can successfully smooth PV generation, frequent charge/discharge will substantially affect its cost effectiveness. In this paper, a real-time method is designed to coordinate PV inverters and BESS for voltage regulation. To keep up with fast fluctuations of PV power, this method will be executed in each 5s control cycle. In addition, charging/discharging power of BESS is adaptively retuned by an active adjustment method in order to avoid BESS premature energy exhaustion in a long run. Finally, through a voltage margin control scheme, the upstream SVR and downstream PV inverters and BESS are coordinated for voltage regulation without any communication. This research is validated via an RTDS-MatLab co-simulation platform, and it will provide valuable insights and applicable strategies to both utilities and PV owners for large-scale PV farm integration into rural networks.Index Terms--Coordinated voltage control, photovoltaic (PV), battery energy storage system (BESS), real-time control, state of charge (SOC) regulation.

show abstract

“…The task consisted in composing the decision trees, which with great accuracy will determine the value of the new parameters y according to the relevant attributes ij x [4,5]; in other words, the task consisted in development of a model (function) f that, having received x on input, E3S Web of Conferences 51, 02004 (2018) https://doi.org/10.1051/e3scconf/20185102004 ICACER 2018 would predict the value of the response y . In this research, a gradient-boosting algorithm was used with decision trees.…”

Section: Sps Operational Forecasting Model 21 Problem Formulationmentioning

confidence: 99%

Machine learning techniques for short-term solar power stations operational mode planning

2018

View full text Add to dashboard Cite

The paper presents the operational model of very-short term solar power stations (SPS) generation forecasting developed by the authors, based on weather information and built into the existing software product as a separate module for SPS operational forecasting. It was revealed that one of the optimal mathematical methods for SPS generation operational forecasting is gradient boosting on decision trees. The paper describes the basic principles of operational forecasting based on the boosting of decision trees, the main advantages and disadvantages of implementing this algorithm. Moreover, this paper presents an example of this algorithm implementation being analyzed using the example of data analysis and forecasting the generation of the existing SPS.

show abstract

Very short term forecasting in global solar irradiance using linear and nonlinear models

Cited by 17 publications

References 18 publications

Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production

Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production

Real-Time Coordinated Voltage Control of PV Inverters and Energy Storage for Weak Networks With High PV Penetration

Machine learning techniques for short-term solar power stations operational mode planning

Contact Info

Product

Resources

About