A Model Combining Stacked Auto Encoder and Back Propagation Algorithm for Short-Term Wind Power Forecasting

Jiao, Runhai; Huang, Xujian; Ma, Xin; Han, Liye; Tian, Wei

doi:10.1109/access.2018.2818108

Cited by 125 publications

(40 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Optimizing SAE parameters could create a favorable effect on the learning problem being handled. In [15], a forecasting algorithm was designed using SAE and back propagation. To increase the accuracy of forecasting, particle swarm optimization was adopted.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, optimizing various parameters creates a favorable effect on profiling methods by increasing the prediction accuracy. In recent years, deep learning methods have been applied on various fields such as wind power prediction [15], traffic data flow prediction [16], and image processing [8] without considering tuning parameters. Underlying motivation of selecting processors to perform the experiment is that they are easy to be exposed measure energy consumption.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tuning Stacked Auto-encoders for Energy Consumption Prediction: A Case Study

Öztürk¹

2019

IJITCS

View full text Add to dashboard Cite

Energy is a requirement for electronic devices. A processor is a substantial part of computer components in terms of energy consumption. A great concern has risen over recent years about computers with regard to the energy consumption. Taking accurate information about energy consumption of a processor allows us to predict energy flow features. However, using traditional classifiers may not enhance the accuracy of the prediction of energy consumption. Deep learning shows great promise for predicting energy consumption of a processor. Stacked auto-encoders has emerged a robust type of deep learning. This work investigates the effects of tuning stacked auto-encoder in computer processor with regard to the energy consumption. To search parameter space, a grid search based training method is adopted. To prepare data to prediction, a data preprocessing algorithm is also proposed. According to the obtained results, on average, the method provides 0.2% accuracy improvement along with a remarkable success in reducing parameter tuning error. Further, in receiver operating curve analysis, tuned stacked auto-encoder was able to increase value of are under the curve up to 0.5.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Tuning Stacked Auto-encoders for Energy Consumption Prediction: A Case Study

Öztürk¹

2019

IJITCS

View full text Add to dashboard Cite

show abstract

“…Particle swarm optimization is used to select the optimal number of neurons in the hidden layer and the learning rate. The results have shown that the proposed method yields better accuracy as compared to a SVM and neural network [27].…”

Section: Introductionmentioning

confidence: 97%

A New Hybrid Approach to Forecast Wind Power for Large Scale Wind Turbine Data Using Deep Learning with TensorFlow Framework and Principal Component Analysis

2019

View full text Add to dashboard Cite

Wind power forecasting plays a vital role in renewable energy production. Accurately forecasting wind energy is a significant challenge due to the uncertain and complex behavior of wind signals. For this purpose, accurate prediction methods are required. This paper presents a new hybrid approach of principal component analysis (PCA) and deep learning to uncover the hidden patterns from wind data and to forecast accurate wind power. PCA is applied to wind data to extract the hidden features from wind data and to identify meaningful information. It is also used to remove high correlation among the values. Further, an optimized deep learning algorithm with a TensorFlow framework is used to accurately forecast wind power from significant features. Finally, the deep learning algorithm is fine-tuned with learning error rate, optimizer function, dropout layer, activation and loss function. The algorithm uses a neural network and intelligent algorithm to predict the wind signals. The proposed idea is applied to three different datasets (hourly, monthly, yearly) gathered from the National Renewable Energy Laboratory (NREL) transforming energy database. The forecasting results show that the proposed research can accurately predict wind power using a span ranging from hours to years. A comparison is made with popular state of the art algorithms and it is demonstrated that the proposed research yields better predictions results.

show abstract

“…The relevance of the problem of efficient energy supply of objects from renewable sources of wind and solar energy is confirmed by the fact that individual territories have considerable uneven supply of this energy in different seasons of the calendar year, as well as with respect to their individual species [1][2][3][4][5][6][7][8][9][10][11]. In addition, the creation of energy systems for renewable energy sources and wind to meet consumer needs is a pressing issue, given the recent trends in fossil fuel prices.…”

Section: Introductionmentioning

confidence: 99%

“…Conducted scientific studies by Ukrainian and foreign scientists have made it possible to solve many problems of efficient use of non-traditional and renewable energy sources [5][6][7][8][9]. Among these are studies related to the creation of efficient energy systems based on the use of renewable wind and solar energy, operating in deterministic or stochastic conditions [10][11].…”

Section: Introductionmentioning

confidence: 99%

Research of the variable natural potential of the wind and energy energy in the northern strip of the ukrainian carpathians

et al. 2020

View full text Add to dashboard Cite

The expediency of studying the varying potential of wind and solar energy in the northern strip of the Ukrainian Carpathians is substantiated. The technique of conducting experiments to determine the natural potential of wind and solar energy is proposed and a model for determining the relative volumes of electricity generation by wind farms and solar electrical installations is developed. Based on the conducted research, according to the Drohobych meteorological station, an energy assessment of wind and solar energy resources in the northern strip of the Ukrainian Carpathians was performed. It is substantiated that the theoretical curves of distribution of wind velocity in separate quarters of the year in the territory of the northern strip of the Ukrainian Carpathians are described by the Weibull distributions. Based on the calculations, it is established that the highest total daily solar radiation is in the summer months. Daily graphs of the relative generation of electricity by wind farms and solar electric installations have been constructed. The expediency of formation of combined systems of energy supply of objects from wind and solar energy in the northern strip of the Ukrainian Carpathians has been established. The substantiated patterns of change in the natural potential of wind and solar energy, as well as the graphs of the relative generation of electricity from them, will significantly speed up managerial decisions and improve their quality.

show abstract

A Model Combining Stacked Auto Encoder and Back Propagation Algorithm for Short-Term Wind Power Forecasting

Cited by 125 publications

References 24 publications

Tuning Stacked Auto-encoders for Energy Consumption Prediction: A Case Study

Tuning Stacked Auto-encoders for Energy Consumption Prediction: A Case Study

A New Hybrid Approach to Forecast Wind Power for Large Scale Wind Turbine Data Using Deep Learning with TensorFlow Framework and Principal Component Analysis

Research of the variable natural potential of the wind and energy energy in the northern strip of the ukrainian carpathians

Contact Info

Product

Resources

About