Prediction in Photovoltaic Power by Neural Networks

Rosato, Antonello; Altilio, Rosa; Araneo, Rodolfo; Panella, Massimo

doi:10.3390/en10071003

Cited by 52 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior to deep learning and LSTM networks, the literature has been filled by statistical and data driven modeling tools where the univariate approach represented by (2) or (3) has been pursued by solving prediction through data regression. In machine learning, both recurrent and feed-forward models have been investigated by using shallow neural networks, possibly hybridized with fuzzy modeling and evolutionary computing for complex optimization [14], [37]. There are two main groups of forecasting approaches in the considered field: indirect and direct [38].…”

Section: Related Workmentioning

confidence: 99%

“…This is the reason why the prediction of power output has become a necessary tool for all the actors involved [14]: producers need predictions to prepare their respective offer strategies; consumers need predictions to maximize their profit; Transmission (TSO) and Distribution (DSO) System Operators need predictions to optimize short and medium term decisions for energy regulation and dispatching. Furthermore, an accurate prediction system, which is the key element within automatic modeling tools for data analytics and intelligent operation control, may enable prosumeroriented home energy management systems [15] and reduce both energy and operation costs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series

et al. 2020

Self Cite

View full text Add to dashboard Cite

The large-scale penetration of renewable energy sources is forcing the transition towards the future electricity networks modeled on the smart grid paradigm, where energy clusters call for new methodologies for the dynamic energy management of distributed energy resources and foster to form partnerships and overcome integration barriers. The prediction of energy production of renewable energy sources, in particular photovoltaic plants that suffer from being highly intermittent, is a fundamental tool in the modern management of electrical grids shifting from reactive to proactive, with also the help of advanced monitoring systems, data analytics and advanced demand side management programs. The gradual move towards a smart grid environment impacts not only the operating control/management of the grid, but also the electricity market. The focus of this paper is on advanced methods for predicting photovoltaic energy output that prove, through their accuracy and robustness, to be useful tools for an efficient system management, even at prosumer's level and for improving the resilience of smart grids. Four different deep neural models for the multivariate prediction of energy time series are proposed; all of them are based on the Long Short-Term Memory network, which is a type of recurrent neural network able to deal with long-term dependencies. Additionally, two of these models also use Convolutional Neural Networks to obtain higher levels of abstraction, since they allow to combine and filter different time series considering all the available information. The proposed models are applied to real-world energy problems to assess their performance and they are compared with respect to the classic univariate approach that is used as a reference benchmark. The significance of this work is to show that, once trained, the proposed deep neural networks ensure their applicability in real online scenarios characterized by high variability of data, without requiring retraining and end-user's tricks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Combining the two and introducing scaling factors and translation factors can improve the generalization ability and convergence speed of the network. It has a more flexible function fitting efficiency (Rosato et al 2017). However, the initial weights and wavelet factors of the wavelet neural network are randomly generated.…”

Section: Optimized Wnn By Cuckoo Search Algorithmmentioning

confidence: 99%

An Efficient Algorithm for Power Prediction in PV Generation System

Alsafasfeh

2020

Int. J. Renew. Energy Dev.

View full text Add to dashboard Cite

Aiming at the existing photovoltaic power generation prediction methods, the modeling is complicated, the prediction accuracy is low, and it is difficult to meet the actual needs. Based on the improvement of the traditional wavelet neural network, a dual-mode cuckoo search wavelet neural network algorithm combined prediction method is proposed, which takes into account the extraction of chaotic features of surface solar radiation and photovoltaic output power. The proposed algorithm first reconstructs the chaotic phase space of the hidden information of each influencing factor in the data history of PV generation and according to the correlation analysis, the solar radiation is utilized as additional input. Next, the proposed algorithm overcomes the limitations of the cuckoo search algorithm such as the sensitivity to the initial value and searchability and convergence speed by dual-mode cuckoo search wavelet neural network algorithm. Lastly, a prediction model of the proposed algorithm is proposed and the prediction analysis is performed under different weather conditions. Simulation results show that the proposed algorithm shows better performance than the existing algorithms under different weather conditions. Under various weather conditions, the mean values of TIC, EMAE and ENRMSE error indicators of the proposed forecasting algorithm were reduced by 43.70%, 45.75%, and 45.41%, respectively. Compared with the Chaos-WNN prediction method, the prediction performance has been further improved under various weather conditions and the mean values of TIC, EMAE and ENRMSE error indicators have been reduced by 25.55%, 27.26%, and 36.83%, respectively. ©2020. CBIORE-IJRED. All rights reserved

show abstract

“…Xu et al [21] developed a method for day-ahead prediction and shaping of the dynamic response of the demand at bulk supply points without field measurements, broadly based on the application of the artificial neural network, Monte Carlo simulations, and load modeling approaches. Rosato et al [22] proposed a new approach based on neural and fuzzy neural networks for PV power prediction, and the forecasting results in the training of neural networks confirm such a trend for which the performance decreases progressively as the length of the training set increases because the training process is more difficult. Dolara et al [23] proposed the hybrid method, combining an artificial intelligence technique with an analytical physical model, and the results showed that the length training set is critical to the dynamic characteristics of neural networks.…”

Section: Introductionmentioning

confidence: 98%

An Improved Forecasting Method for Photovoltaic Power Based on Adaptive BP Neural Network with a Scrolling Time Window

Zhu

Lian

et al. 2017

Energies

View full text Add to dashboard Cite

Due to the large scale of grid-connected photovoltaic (PV) power generation installations, accurate PV power forecasting is critical to the safe and economic operation of the electric power system. In the paper, by analyzing the influence of external ambient factors and the changing characteristics of PV modules with time, it is found that PV power generation is a nonlinear and time-varying process. This suggests that a certain single forecasting model is inadequate for representing actual generation characteristics, and it is difficult to obtain an accurate forecasting result. An adaptive back propagation (BP) neural network model adopting scrolling time window is proposed to solve the problem. Via an update of the training data of BP neural network with the scrolling time window, the forecasting model adapts to time and a changing external environment with the required modeling precision. Meanwhile, through evaluation of the forecasting performance in different time windows, an optimized time window can be determined to guarantee accuracy. Finally, using the actual operation data of a PV plant in Beijing, the approach is validated as being applicable for PV power forecasting and is able to effectively respond to the dynamic change of the PV power generation process. This improves the forecasting accuracy and also reduces computation complexity as compared with the conventional BP neural network algorithm.

show abstract

Prediction in Photovoltaic Power by Neural Networks

Cited by 52 publications

References 47 publications

Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series

Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series

An Efficient Algorithm for Power Prediction in PV Generation System

An Improved Forecasting Method for Photovoltaic Power Based on Adaptive BP Neural Network with a Scrolling Time Window

Contact Info

Product

Resources

About