Deep Learning based Models for Solar Energy Prediction

Jebli, Imane; Belouadha, Fatima-Zahra; Kabbaj, Mohammed Issam; Tilioua, Amine

doi:10.25046/aj060140

Cited by 32 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Time series one-dimensional data are the focus of RNN-based prediction. Numerous studies have been performed for the purpose of using RNN structures to forecast meteorological variables [ 7 , 8 , 9 , 10 , 11 ]. Recent studies have also incorporated both spatial and temporal data into models, facilitating the usage of more diverse and abundant meteorological data as inputs [ 24 , 30 , 31 , 32 ].…”

Section: Deep-learning-based Temperature Prediction Methodsmentioning

confidence: 99%

“…Before forwarding the input to the encoder and decoder, embedding was performed for the uniform input representation. The pointwise self-attention technique used by the vanilla Transformer [ 8 ] employs time stamps to provide the local positional context. However, the capacity to represent long-range independence in the long-range dependency problem necessitates the use of global data such as hierarchical time stamps (week, month, and year) and agnostic time stamps (holidays and events).…”

Section: Proposed Temperature Prediction Modelmentioning

confidence: 99%

“…As a response, the authors of many studies have examined the use of deep-learning-based predictions and forecasts for various meteorological variables [3][4][5][6]. Recurrent neural networks (RNNs), with their ability to predict current or future states based on past information, have been utilized in numerous studies to predict future time step variables [7][8][9][10][11]. However, with increasing network depths, RNNs often experience Sensors 2023, 23, 7047 2 of 17 gradient vanishing during the learning process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data

Jun

Kim

2023

Sensors

View full text Add to dashboard Cite

This paper proposes an Informer-based temperature prediction model to leverage data from an automatic weather station (AWS) and a local data assimilation and prediction system (LDAPS), where the Informer as a variant of a Transformer was developed to better deal with time series data. Recently, deep-learning-based temperature prediction models have been proposed, demonstrating successful performances, such as conventional neural network (CNN)-based models, bi-directional long short-term memory (BLSTM)-based models, and a combination of both neural networks, CNN–BLSTM. However, these models have encountered issues due to the lack of time data integration during the training phase, which also lead to the persistence of a long-term dependency problem in the LSTM models. These limitations have culminated in a performance deterioration when the prediction time length was extended. To overcome these issues, the proposed model first incorporates time-periodic information into the learning process by generating time-periodic information and inputting it into the model. Second, the proposed model replaces the LSTM with an Informer as an alternative to mitigating the long-term dependency problem. Third, a series of fusion operations between AWS and LDAPS data are executed to examine the effect of each dataset on the temperature prediction performance. The performance of the proposed temperature prediction model is evaluated via objective measures, including the root-mean-square error (RMSE) and mean absolute error (MAE) over different timeframes, ranging from 6 to 336 h. The experiments showed that the proposed model relatively reduced the average RMSE and MAE by 0.25 °C and 0.203 °C, respectively, compared with the results of the CNN–BLSTM-based model.

show abstract

Section: Deep-learning-based Temperature Prediction Methodsmentioning

confidence: 99%

Section: Proposed Temperature Prediction Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data

Jun

Kim

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…RNNs are largely used when there is a need to remember past information to predict future behaviour [84]. Moreover, RNNs can process sequential data of different lengths [92].…”

Section: Recursive Neural Network (Rnns)mentioning

confidence: 99%

A Review on Machine/Deep Learning Techniques Applied to Building Energy Simulation, Optimization and Management

Villano,

Mauro,

Pedace

2024

Thermo

View full text Add to dashboard Cite

Given the climate change in recent decades and the ever-increasing energy consumption in the building sector, research is widely focused on the green revolution and ecological transition of buildings. In this regard, artificial intelligence can be a precious tool to simulate and optimize building energy performance, as shown by a plethora of recent studies. Accordingly, this paper provides a review of more than 70 articles from recent years, i.e., mostly from 2018 to 2023, about the applications of machine/deep learning (ML/DL) in forecasting the energy performance of buildings and their simulation/control/optimization. This review was conducted using the SCOPUS database with the keywords “buildings”, “energy”, “machine learning” and “deep learning” and by selecting recent papers addressing the following applications: energy design/retrofit optimization, prediction, control/management of heating/cooling systems and of renewable source systems, and/or fault detection. Notably, this paper discusses the main differences between ML and DL techniques, showing examples of their use in building energy simulation/control/optimization. The main aim is to group the most frequent ML/DL techniques used in the field of building energy performance, highlighting the potentiality and limitations of each one, both fundamental aspects for future studies. The ML approaches considered are decision trees/random forest, naive Bayes, support vector machines, the Kriging method and artificial neural networks. The DL techniques investigated are convolutional and recursive neural networks, long short-term memory and gated recurrent units. Firstly, various ML/DL techniques are explained and divided based on their methodology. Secondly, grouping by the aforementioned applications occurs. It emerges that ML is mostly used in energy efficiency issues while DL in the management of renewable source systems.

show abstract

“…The utilization of Deep Learning approaches for Photovoltaic forecasting, namely Recurrent Neural Networks, Long Short-Term Memory, and Gated Recurrent Units, was investigated in this article [75]. The suggested prediction algorithms are based on accurate Errachidia provincial meteorological data from 2016 to 2018.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

Wind, Solar, and Photovoltaic Renewable Energy Systems with and without Energy Storage Optimization: A Survey of Advanced Machine Learning and Deep Learning Techniques

et al. 2022

View full text Add to dashboard Cite

Nowadays, learning-based modeling methods are utilized to build a precise forecast model for renewable power sources. Computational Intelligence (CI) techniques have been recognized as effective methods in generating and optimizing renewable tools. The complexity of this variety of energy depends on its coverage of large sizes of data and parameters, which have to be investigated thoroughly. This paper covered the most resent and important researchers in the domain of renewable problems using the learning-based methods. Various types of Deep Learning (DL) and Machine Learning (ML) algorithms employed in Solar and Wind energy supplies are given. The performance of the given methods in the literature is assessed by a new taxonomy. This paper focus on conducting comprehensive state-of-the-art methods heading to performance evaluation of the given techniques and discusses vital difficulties and possibilities for extensive research. Based on the results, variations in efficiency, robustness, accuracy values, and generalization capability are the most obvious difficulties for using the learning techniques. In the case of the big dataset, the effectiveness of the learning techniques is significantly better than the other computational methods. However, applying and producing hybrid learning techniques with other optimization methods to develop and optimize the construction of the techniques is optionally indicated. In all cases, hybrid learning methods have better achievement than a single method due to the fact that hybrid methods gain the benefit of two or more techniques for providing an accurate forecast. Therefore, it is suggested to utilize hybrid learning techniques in the future to deal with energy generation problems.

show abstract

Deep Learning based Models for Solar Energy Prediction

Cited by 32 publications

References 33 publications

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data

A Review on Machine/Deep Learning Techniques Applied to Building Energy Simulation, Optimization and Management

Wind, Solar, and Photovoltaic Renewable Energy Systems with and without Energy Storage Optimization: A Survey of Advanced Machine Learning and Deep Learning Techniques

Contact Info

Product

Resources

About