Predictive model for PV power generation using RNN (LSTM)

Park, Min Kyeong; Lee, Jong Man; Kang, Woo‐Hyoung; Choi, Jong Min

doi:10.1007/s12206-021-0140-0

Cited by 37 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM represents an extended version of RNN that is able to learn short-term as well as long-term time dependencies, this characteristic making it suitable for our task. Moreover, the decision of using the LSTM neural network in our work is supported by the results obtained in [9], [10], [11], and [12], where the PV power is predicted also using this neural network, proving its performance in the PV forecasting problem.…”

Section: Literature Reviewsupporting

confidence: 60%

See 1 more Smart Citation

Prediction of Power Generation of a Photovoltaic Power Plant Based on Neural Networks

et al. 2023

View full text Add to dashboard Cite

Photovoltaic energy production is an important factor for increasing the electricity supply. The ability to predict the electric power production (EPP) of a photovoltaic (PV) farm supports from the management process of the power grid to the trade in the energy market and much more. Also, by predicting the production of PV power (PVP), it is possible to monitor the lifetime of the solar cells that form the backbone of any solar PV system. As a critical result, sudden failures of the PV plant can be avoided. Using a long short-term memory recurrent neural network (LSTM-RNN) model, this work evaluates the prediction accuracy of two forecasting strategies: the recursive strategy and the non-recursive Multiple-Input and Multiple-Output, respectively. The dataset consists of 5-years in-filed production data measurements collected from the CETATEA photovoltaic power plant, a research site facility for renewable energies located in Cluj-Napoca, Romania. The high granularity of the electric power production dataset values recorded each 1 hour guarantees the overall prediction accuracy of the system. The impact of the dataset size, the number of previous observations, and the forecast horizon on the neural network prediction accuracy is evaluated for each strategy. The performance metrics used to evaluate the prediction accuracy are the root mean square error, the mean bias error, and the mean average error. The results analysis demonstrates the ability of the implemented machine learning models to predict electric power production, as well as their importance in the energy loss management process.

show abstract

Section: Literature Reviewsupporting

confidence: 60%

“…PV power forecasting is a topic widely investigated due to its economic and ecologic impact [2], [9], [10], [11], [12], [13], [14], [15], [16], [17]. Research by Wan et.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Power Generation of a Photovoltaic Power Plant Based on Neural Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In this study, both the encoder and decoder adopt LSTM Networks. LSTM is a special subtype of deep learning neural network that has the capability to handle sequential data, such as forecasting time-series building energy demand [ 45 ], indoor air temperature [ 46 ] and PV power generation [ 47 ]. It learns long- and short-term impacts from past time series and outperforms traditional non-linear machine learning algorithms by introducing three special gates, namely forget gate, input gate and output gate.…”

Section: Methodsmentioning

confidence: 99%

Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks

Zhuang

Choudhary

Mavrogianni

2022

Building and Environment

View full text Add to dashboard Cite

“…Support vector regression (SVR) and neural networks are the most widely used statistical methods for the PV power predictions [3]. In recent literature on the PV production forecasts, most of the papers implemented the deep-learning neural networks, including feed-forward neural network [4], recurrent neural network (RNN) [5], RNN with long short-term memory (LSTM) [6], and hybrid LSTM-CNN (convolutional neural network) [7], to name a few.…”

Section: Introductionmentioning

confidence: 99%

Error analysis of multi-step day-ahead PV production forecasting with chained regressors

Sarajčev

Meglic

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This paper presents a comprehensive error analysis of the day-ahead photovoltaic (PV) production multi-step forecasting model that uses a chained support vector regression (SVR). A principal component analysis (PCA) is also implemented to investigate possible improvements of the SVR prediction accuracy. Special attention was given to the hyper-parameter tuning of the chained SVR and PCA+SVR models; specifically, the dispersion of the prediction errors when fine-tuning the model with an experimental halving random search algorithm implemented within scikit-learn, i.e. the HalvingRandomSearchCV (HRSCV). The obtained results were compared with the traditional randomized search technique, i.e. the RandomizedSearchCV (RSCV). The chained SVR model prediction errors were analysed for several different parameter distribution settings. After doing repetitive fine-tuning and predictions, it was observed that the HRSCV tends to choose sub-optimal hyper-parameters for certain scenarios, as will be elaborated in the paper. Moreover, when analysing prediction errors of the same model fine-tuned repetitively with the HRSCV and RSCV, it was found that HRSCV creates larger errors and more inconsistency (variability) in the prediction results. The introduction of the PCA to the chained SVR model, at the same time, reduces the influence of exogenous variables and, on average, increases its performance and decreases prediction errors regardless of the optimization technique used.

show abstract

Predictive model for PV power generation using RNN (LSTM)

Cited by 37 publications

References 19 publications

Prediction of Power Generation of a Photovoltaic Power Plant Based on Neural Networks

Prediction of Power Generation of a Photovoltaic Power Plant Based on Neural Networks

Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks

Error analysis of multi-step day-ahead PV production forecasting with chained regressors

Contact Info

Product

Resources

About