Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison

Gaboitaolelwe, Jwaone; Zungeru, Adamu Murtala; Yahya, Abid; Lebekwe, Caspar K.; Vinod, Dasari Naga; Salau, Ayodeji Olalekan

doi:10.1109/access.2023.3270041

Cited by 34 publications

(20 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the authors in [20] examined enduring techniques for predicting energy consumption, PV, and wind power production. Furthermore, in [21], cloud cover, humidity, and temperature impacts on PV generation predictions were evaluated by 175 time series. They were obtained measuring the production of an actual rooftop-mounted PV system installed in Utrecht (Netherlands).…”

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning and Weather Model Combination for PV Production Forecasting

Buonanno,

Caputo,

Balog

et al. 2024

Energies

View full text Add to dashboard Cite

Accurate predictions of photovoltaic generation are essential for effectively managing power system resources, particularly in the face of high variability in solar radiation. This is especially crucial in microgrids and grids, where the proper operation of generation, load, and storage resources is necessary to avoid grid imbalance conditions. Therefore, the availability of reliable prediction models is of utmost importance. Authors address this issue investigating the potential benefits of a machine learning approach in combination with photovoltaic power forecasts generated using weather models. Several machine learning methods have been tested for the combined approach (linear model, Long Short-Term Memory, eXtreme Gradient Boosting, and the Light Gradient Boosting Machine). Among them, the linear models were demonstrated to be the most effective with at least an RMSE improvement of 3.7% in photovoltaic production forecasting, with respect to two numerical weather prediction based baseline methods. The conducted analysis shows how machine learning models can be used to refine the prediction of an already established PV generation forecast model and highlights the efficacy of linear models, even in a low-data regime as in the case of recently established plants.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning and Weather Model Combination for PV Production Forecasting

Buonanno,

Caputo,

Balog

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…Environmental factors, as well as other factors, that affect the output voltage and efficiency of solar photovoltaic modules, are examined in [25]. The research [26] provides a thorough and comparative analysis of current Machine Learning (ML)-based methods for PV power forecasting with an emphasis on short-term time horizons.…”

Section: Introductionmentioning

confidence: 99%

Assessment of photovoltaic generation penetration effect on the maximum loadability of the system

Gupta,

Ranjan,

Kumar

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

This paper proposed a method to investigate the effect of increasing PV penetration on the voltage stability of an IEEE 14-bus test system considering maximum PV penetration and system loadability limit. The critical bus of the test system has been decided based on nose curve analysis. The solar PV system is deployed with the most critical bus of the system. The effect of increasing PV penetration on the improvement in the loading capacity of various power system components like transmission lines, transmission line transformers, and generators is investigated over the adopted test system. Based on solar PV penetration up to 100 MW, the maximum loadability limit of the IEEE 14-bus test system increases, as shown by the results. Bus 14 is found to be the most severe bus of the test system using the continuation power flow (CPF) method. However, in some cases, overloading situations develop after a certain limit of PV penetration in the power system. In this condition, the overloading of the power system equipment is improved by the use of a Static Synchronous Compensator (STATCOM) at bus number 14, a double circuit line in the critical line (9–14), and Static Synchronous Series Compensator (SSSC) in the most severe line (9–14) in the system. The maximum loadability of the system gets maximum enhanced from 4.0349 p.u. to 4.5602 p.u. under simultaneous use of solar PV generation, SSSC, and STATCOM at the most critical bus and in most severe line of the system. As evidence, the enhancement in maximum loadability of the system found using the proposed method has been also compared with the existing research. The maximum system loadability has been also enhanced under normal and (N-1) contingency conditions by the use of PV penetration in the system. PSAT/MATLAB software is used for simulation and maximum loadability has been investigated by continuation power flow (CPF) method.

show abstract

“…This incident sun power can be harnessed via Photovoltaic (PV) cells to supply power for further use. Solar energy is the term for the energy that is harvested from the sun, and it is thought to be the most trustworthy renewable energy source due to large parts of the countryside receive sufficient solar radiation throughout the year [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

MPPT efficiency enhancement of a grid connected solar PV system using Finite Control set model predictive controller

Salau,

Alitasb

2024

Heliyon

Self Cite

View full text Add to dashboard Cite

Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison

Cited by 34 publications

References 81 publications

Machine Learning and Weather Model Combination for PV Production Forecasting

Machine Learning and Weather Model Combination for PV Production Forecasting

Assessment of photovoltaic generation penetration effect on the maximum loadability of the system

MPPT efficiency enhancement of a grid connected solar PV system using Finite Control set model predictive controller

Contact Info

Product

Resources

About