Photovoltaic Power Generation Forecasting for Regional Assessment Using Machine Learning

Borunda, Mónica; Ramírez, Adrián; Garduño, Raul; Ruíz, Gerardo; Hernández, S.; Jaramillo, O.A.

doi:10.3390/en15238895

Cited by 12 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power produced by a photovoltaic module (P MOD ) is calculated according to Equation (7). This equation considers the nominal power of the photovoltaic module (P N ), the irradiance under standard measurement conditions (G STC ), and the temperature coefficient of the photovoltaic panel (γ), which was considered to have a value of 0.35%•K −1 [33,34].…”

Section: Resultsmentioning

confidence: 99%

“…The climatological values obtained make it possible to calculate the photovoltaic production and include hourly information on the average solar radiation on the photovoltaic plane (G M ) and ambient temperature (T A ). The temperature of the photovoltaic cell (T C ) is calculated using Equation ( 6), where NOCT is the nominal operating cell temperature of the photovoltaic cell [33,34], and it was considered to be 47…”

Section: Model Of the Pv-bessmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Photovoltaic Plants with Battery Energy Storage Systems (PV-BESS) for Monthly Constant Power Operation

Tejero-Gómez

Bayod-Rújula

2023

Energies

View full text Add to dashboard Cite

Photovoltaic generation is one of the key technologies in the production of electricity from renewable sources. However, the intermittent nature of solar radiation poses a challenge to effectively integrate this renewable resource into the electrical power system. The price reduction of battery storage systems in the coming years presents an opportunity for their practical combination with utility-scale photovoltaic plants. The integration of properly sized photovoltaic and battery energy storage systems (PV-BESS) for the delivery of constant power not only guarantees high energy availability, but also enables a possible increase in the number of PV installations and the PV penetration. A massive data analysis with long-term simulations is carried out and indicators of energy unavailability of the combined system are identified to assess the reliability of power production. The proposed indicators allow to determine the appropriate sizing of the battery energy storage system for a utility-scale photovoltaic plant in a planning stage, as well as suggest the recommended operating points made for each month through a set of graphs and indicators. The presence of an inflection zone has been observed, beyond which any increase in storage does not generate significant reductions in the unavailability of energy. This critical zone is considered the sweet spot for the size of the storage, beyond which it is not sensible to increase its size. Identifying the critical point is crucial to determining the optimal storage size. The system is capable of providing reliable supply of constant power in monthly periods while ensuring capacity credit levels above 95%, which increases the penetration of this renewable resource. Despite the fact that the study focuses exclusively on the analysis from an energy perspective, it is important to consider the constraints associated to real storage systems and limit their oversizing.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Model Of the Pv-bessmentioning

confidence: 99%

Analysis of Photovoltaic Plants with Battery Energy Storage Systems (PV-BESS) for Monthly Constant Power Operation

Tejero-Gómez

Bayod-Rújula

2023

Energies

View full text Add to dashboard Cite

show abstract

“…As for machine learning models, Support Vector Regression (SVR) [12], Gradient Boost Decision Tree [21], Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) [22,23], and generally Artificial Neural Networks (ANN) [24][25][26] have been widely explored. Recent advancements also include hybrid combinations of ML approaches, such as the combination of GRU and CNN proposed by Sabri et al [23], or the combination of CNN and LSTM as explored by Almaghrabi et al [27].…”

Section: State Of the Artmentioning

confidence: 99%

Machine Learning Models for Regional Photovoltaic Power Generation Forecasting with Limited Plant-Specific Data

Tucci,

Piazzi,

Thomopulos

2024

Energies

View full text Add to dashboard Cite

Predicting electricity production from renewable energy sources, such as solar photovoltaic installations, is crucial for effective grid management and energy planning in the transition towards a sustainable future. This study proposes machine learning approaches for predicting electricity production from solar photovoltaic installations at a regional level in Italy, not using data on individual installations. Addressing the challenge of diverse data availability between pinpoint meteorological inputs and aggregated power data for entire regions, we propose leveraging meteorological data from the centroid of each Italian province within each region. Particular attention is given to the selection of the best input features, which leads to augmenting the input with 1-hour-lagged meteorological data and previous-hour power data. Several ML approaches were compared and examined, optimizing the hyperparameters through five-fold cross-validation. The hourly predictions encompass a time horizon ranging from 1 to 24 h. Among tested methods, Kernel Ridge Regression and Random Forest Regression emerge as the most effective models for our specific application. We also performed experiments to assess how frequently the models should be retrained and how frequently the hyperparameters should be optimized in order to comprise between accuracy and computational costs. Our results indicate that once trained, the model can provide accurate predictions for extended periods without frequent retraining, highlighting its long-term reliability.

show abstract

“…The research carried out in [25] proposes an approach for clustering regions and forecasting photovoltaic generation, which lists locations with better viability for the installation of photovoltaic panels. A probabilistic method combined with machine learning models for forecasting photovoltaic generation is considered to be more suitable for the study horizon and data discretization, which is monthly.…”

Section: Literature Reviewmentioning

confidence: 99%

Multivariate Strategy Using Artificial Neural Networks for Seasonal Photovoltaic Generation Forecasting

et al. 2022

View full text Add to dashboard Cite

Electric power systems have experienced the rapid insertion of distributed renewable generating sources and, as a result, are facing planning and operational challenges as new grid connections are made. The complexity of this management and the degree of uncertainty increase significantly and need to be better estimated. Considering the high volatility of photovoltaic generation and its impacts on agents in the electricity sector, this work proposes a multivariate strategy based on design of experiments (DOE), principal component analysis (PCA), artificial neural networks (ANN) that combines the resulting outputs using Mixture DOE (MDOE) for photovoltaic generation prediction a day ahead. The approach separates the data into seasons of the year and considers multiple climatic variables for each period. Here, the dimensionality reduction of climate variables is performed through PCA. Through DOE, the possibilities of combining prediction parameters, such as those of ANN, were reduced, without compromising the statistical reliability of the results. Thus, 17 generation plants distributed in the Brazilian territory were tested. The one-day-ahead PV generation forecast has been considered for each generation plant in each season of the year, reaching mean percentage errors of 10.45% for summer, 9.29% for autumn, 9.11% for winter and 6.75% for spring. The versatility of the proposed approach allows the choice of parameters in a systematic way and reduces the computational cost, since there is a reduction in dimensionality and in the number of experimental simulations.

show abstract

Photovoltaic Power Generation Forecasting for Regional Assessment Using Machine Learning

Cited by 12 publications

References 42 publications

Analysis of Photovoltaic Plants with Battery Energy Storage Systems (PV-BESS) for Monthly Constant Power Operation

Analysis of Photovoltaic Plants with Battery Energy Storage Systems (PV-BESS) for Monthly Constant Power Operation

Machine Learning Models for Regional Photovoltaic Power Generation Forecasting with Limited Plant-Specific Data

Multivariate Strategy Using Artificial Neural Networks for Seasonal Photovoltaic Generation Forecasting

Contact Info

Product

Resources

About