Prediction of energy photovoltaic power generation based on artificial intelligence algorithm

Zhang, Shuhua; Wang, Jinsong; Li, Haibo; Tong, Jie; Sun, Zaihong

doi:10.1007/s00521-020-05249-z

Cited by 64 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the PV power is impacted not only by the environmental factors, but also the internal features of PV panels. Both internal and external factors interact to create a multi-variable, extremely nonlinear relationship that influences photovoltaic output power [4]. Thus, machine learning within Artificial intelligence appears as a promising advantage for renewable-energy predictions thanks to the countless possibilities and perspectives that it offers especially with the increase in computer processing power and the important volume of data generated in real-time by the internet of things activators.…”

Section: State Of the Artmentioning

confidence: 99%

Novel Comparison of Machine Learning Techniques for Predicting Photovoltaic Output Power

Chahboun

Maâroufi

2021

IJRER

View full text Add to dashboard Cite

With the tremendous advancements in the sector of renewable energy, power generation sources have diversified, and the grid has become complex to manage. Therefore, enhanced prediction of power sources has become paramount to efficiently manage power systems. In the context of the fourth industrial revolution, artificial intelligence appears as an emerging solution to address this challenging issue. Supported by other developing technologies such as big data and connected objects, artificial intelligence can provide accurate forecasts. Therefore, a performance comparison of several up-to-date machine learning algorithms is conducted in this paper for the hourly prediction of the resulting Photovoltaic power. The methods employed include bayesian regularized neural networks, k-nearest neighbors, gradient boosting, random forest, support vector regression, and multivariate adaptive regression splines. Moreover, this paper investigates the prevailing meteorological and irradiation data affecting the Photovoltaic power through using a correlation analysis. Although there are various existing surveys on photovoltaic power forecasts, current researches usually employ a single approach and compare it to basic algorithms without providing a thorough performance comparison. Furthermore, the datasets used in general depend on a certain period of the year, making it hard to assess the final results. The key contribution of this research is the comprehensive assessment of six complex machine learning techniques, using two years of input data, the most popular error metrics: R-squared, Root Mean Square Error, Mean Absolute Error and a consistent set of black box model's explainers. The results revealed precisely that Bayesian regularized neural networks achieved the best prediction accuracy with R²=99,99%.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Novel Comparison of Machine Learning Techniques for Predicting Photovoltaic Output Power

Chahboun

Maâroufi

2021

IJRER

View full text Add to dashboard Cite

show abstract

“…Atmospheric variables, such as solar irradiance, temperature, humidity and cloud properties, can directly and indirectly influence PV power generation. The dependence of the electrical energy generated in a photovoltaic farm on weather conditions, and the high variability of these conditions, make the problem of predicting the energy generated in a photovoltaic farm a complex task [2].…”

Section: Introductionmentioning

confidence: 99%

Photovoltaic generation prediction using the deep learning long short term memory model

Casanova

Viltres

2022

ITEGAM JETIA

View full text Add to dashboard Cite

Solar photovoltaic energy is a renewable, clean and safe energy source that is currently used worldwide. However, it presents a dynamic and intermittent behavior, caused by the variation of climatic conditions. Due to this, it has been necessary to develop different methods for the prediction of the energy generated in photovoltaic systems. The present work is focused on analyzing the prediction of the power generated in a photovoltaic plant connected to the grid, by means of the Long Short-Term Memory (LSTM) deep learning model. In order to carry out the study, a database obtained from the photovoltaic plant of the Central University "Marta Abreu" of Las Villas (UCLV) with a nominal installed power of 1.1 MW is used. Initially, the correlation between the different variables with respect to the photovoltaic power generated is analyzed, then the LSTM model is implemented to make the prediction. The results obtained show that the predictions made for different time horizons and for days with different behavior are adequate, which demonstrates the effectiveness of this prediction method.

show abstract

“…These features have good generalization ability. It has achieved remarkable results in computer vision, target detection, speech recognition, and so on [13,14]. The three-phase current of the feeder on the low-voltage side of the main transformer, the three-phase voltage, and the zero-sequence voltage signal of the bus bar can comprehensively reflect the working state of the feeder.…”

Section: Introductionmentioning

confidence: 99%

Fault identification method for distribution network based on parameter optimized variational mode decomposition and convolutional neural network

Hou

Guo

2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

In order to extract the fault characteristics of the distribution power system automatically, a new method for fault identification based on parameter optimized variational mode decomposition (VMD) and convolutional neural network (CNN) is proposed. First, the VMD is used to decompose electric signals of the main transformer, including the current of the low-voltage inlet line, bus voltage, and so on. The obtained intrinsic mode functions should be arranged in sequence from low to high according to the central frequency. The VMD can obtain the time-frequency matrices. In order to decide the decomposition layers of the VMD adaptively, the partial mean of multi-scale permutation entropy is used to optimize it. Then, the time-frequency matrixes can be converted into pixel matrices by pseudo-colour coding. The pixel matrices which are appropriately compressed can be used as input of CNN. The CNN can autonomously extract the eigenvectors of fault. Finally, the classification algorithms of support vector machine (SVM), naive Bayesian classifier (NBC), extreme learning machine (ELM), and random forest (RF) are used to train and test the feature vectors extracted by CNN to verify the effectiveness of the method. The experiments show that the proposed method has excellent stability, fast convergence speed, and high precision. The technique can effectively complete the fault identification of the distribution network.

show abstract

Prediction of energy photovoltaic power generation based on artificial intelligence algorithm

Cited by 64 publications

References 12 publications

Novel Comparison of Machine Learning Techniques for Predicting Photovoltaic Output Power

Novel Comparison of Machine Learning Techniques for Predicting Photovoltaic Output Power

Photovoltaic generation prediction using the deep learning long short term memory model

Fault identification method for distribution network based on parameter optimized variational mode decomposition and convolutional neural network

Contact Info

Product

Resources

About