Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks

Gensler, André; Henze, Janosch; Sick, Bernhard; Raabe, Nils

doi:10.1109/smc.2016.7844673

Cited by 434 publications

(252 citation statements)

References 22 publications

Supporting

Mentioning

242

Contrasting

Unclassified

Order By: Relevance

“…The study found that the proposed ELM model has higher predictive accuracy and a lower arithmetic time than the output power generated by the photoelectric system. Gensler et al 29 used a group consisted of deep learning algorithms such as MLP, deep belief networks, AutoEncoder, and LSTM to predict and use them in the renewable energy field. The study aimed to show the strength of these approaches compared with the physical prediction model.…”

Section: Introductionmentioning

confidence: 99%

Experimental and deep learning artificial neural network approach for evaluating grid-connected photovoltaic systems

et al. 2019

View full text Add to dashboard Cite

Summary This article evaluates a 1.4‐kW building integrated grid‐connected photovoltaic plant. The PV plant was installed in the Faculty of Engineering solar energy lab, Sohar University, Oman, and the system data have been collected for a year from July 2017 to June 2018. The grid‐connected system was evaluated in terms of power, energy, specific yield, capacity factor, and cost of energy, and payback period. The measured diffuse and global solar irradiations are 3289 and 6182 Wh/m2, respectively. Four predictive models (TLRN, FRNN‐1, FRNN‐2, and FRNN‐3) using deep learning approach based on RNN and TLRN were proposed to predict the PV current performance through data input of temperature (T) and solar irradiance (G). The experiment results found that the highest energy production, array, reference, and final yields are 245.8 kWh, 3.43 to 5.65 kWh/kWp‐day, 4.61 to 7.33 kWh/kWp‐day, and 3.24 to 4.82 kWh/kWp‐day, respectively. Meanwhile, CF, CoE, and PBP were found to be 21.7%, 0.045 USD/kWh and 11.17 years, respectively. The highest performance for prediction models were found for FRNN‐2 and FRNN‐3 due to they exhibit lower MSE which means being tightly fitted to experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Experimental and deep learning artificial neural network approach for evaluating grid-connected photovoltaic systems

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Long short-term memory (LSTM) 17 which is a kind of DL method is chosen in this paper, since it is widely used in presenting many aspects of the economy 18 and energy. 19,20 Selecting variables before performing regression is also an important problem. Some traditional methods such as principal components analysis (PCA), 21 Kernel principal components analysis (KPCA), 22 or Bayes 23 are widely used in the field of energy economics.…”

mentioning

confidence: 99%

Prediction of energy consumption: Variable regression or time series? A case in China

2019

Energy Science & Engineering

View full text Add to dashboard Cite

Energy consumption is closely related to industrial structure, economic prosperity, and population. Because of the Granger causal relationship between GDP and energy consumption, many researchers consider the regression method to predict energy consumption using economic variables. However, some other researchers regard the time series method (forecast) to estimate for energy consumption. To address the advantages and disadvantages of two methods in energy consumption prediction, we performed the deep learning (DL) based on the case of China. The experiment results show that the accuracy of time series forecast is much higher than regression methods. In addition, we also explored the relationship between industry, economy, population, and energy consumption. We found that GDP, population, secondary sector, and tertiary sector were significant to energy consumption. A tertiary sector can help to reduce energy consumption to some extent. This could give suggestions about changing industry structure. More and more attention has been paid to energy intensity. The strategic approach to sustainable development requires reducing energy intensity while developing the economy. Since China is committed to achieving carbon emission peak by 2030, this paper predicts the energy intensity of China in the next decade based on a DL algorithm. The prediction results show that energy intensity would slightly decrease in the next decade. Different types of energy represent the industrial structure behind economic growth. Therefore, this paper was conducted using ridge regression (RR) to explore the relationship between different types of energy and energy intensity. In addition, the effect (positive or negative) of different energy sources in reducing energy intensity has also been explored. We found that the best way of developing the economy and reducing energy consumption is to use natural gas and hydroelectric instead of coal. This can guide policy development about changing energy source structure.

show abstract

“…We can conclude that GRU neural networks do better in both convergence speed and training time, which depends on the improved single structure of GRU units. We also performed the experiments to compare with current methods such as back-propagation neural networks (BPNNs) [7,8], stacked autoencoders (SAEs) [17], RNNs [24,25], and LSTM [29][30][31]. Their parameters and structures are set as described in Section 3.2.…”

Section: Comparison Of Results Of Proposed Methodsmentioning

confidence: 99%

Short-Term Load Forecasting with Multi-Source Data Using Gated Recurrent Unit Neural Networks

et al. 2018

View full text Add to dashboard Cite

Short-term load forecasting is an important task for the planning and reliable operation of power grids. High-accuracy forecasting for individual customers helps to make arrangements for generation and reduce electricity costs. Artificial intelligent methods have been applied to short-term load forecasting in past research, but most did not consider electricity use characteristics, efficiency, and more influential factors. In this paper, a method for short-term load forecasting with multi-source data using gated recurrent unit neural networks is proposed. The load data of customers are preprocessed by clustering to reduce the interference of electricity use characteristics. The environmental factors including date, weather and temperature are quantified to extend the input of the whole network so that multi-source information is considered. Gated recurrent unit neural networks are used for extracting temporal features with simpler architecture and less convergence time in the hidden layers. The detailed results of the real-world experiments are shown by the forecasting curve and mean absolute percentage error to prove the availability and superiority of the proposed method compared to the current forecasting methods.

show abstract

Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks

Cited by 434 publications

References 22 publications

Experimental and deep learning artificial neural network approach for evaluating grid-connected photovoltaic systems

Experimental and deep learning artificial neural network approach for evaluating grid-connected photovoltaic systems

Prediction of energy consumption: Variable regression or time series? A case in China

Short-Term Load Forecasting with Multi-Source Data Using Gated Recurrent Unit Neural Networks

Contact Info

Product

Resources

About