Deep Belief Network with Seasonal Decomposition for Solar Power Output Forecasting

Solar power is a type of renewable energy system that uses solar energy to produce electricity, and is regarded as one of the most important power sources in Taiwan. Since sunshine duration affects the amount of energy that can be generated by a solar power, the seasons of the year are important factors that should be considered for accurate solar power prediction. In the last decade, the use of artificial intelligence for forecasting systems have been quite popular, and the deep belief network (DBN) models started getting more attention. In this study, a seasonal deep belief network (SDBN) was developed to forecast monthly solar power output data. The SDBN was constructed by combining seasonal decomposition method and DBN. Further, this study used monthly solar power output data from the Taiwan Power Company. The results indicated that the proposed forecasting system demonstrated a superior performance in terms of forecasting accuracy. Also, the performance of autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), and DBN obtained from a separate study were compared to the performance of the proposed SDBN model and showed that the latter was better than the other three models. Thus, the SDBN model can be used as an alternative method for monthly solar power output data forecasting.

Download Full-text

Integrating Gray Data Preprocessor and Deep Belief Network for Day-Ahead PV Power Output Forecast

IEEE Transactions on Sustainable Energy ◽

10.1109/tste.2018.2888548 ◽

2020 ◽

Vol 11 (1) ◽

pp. 185-194 ◽

Cited By ~ 7

Author(s):

Gary W. Chang ◽

Heng-Jiu Lu

Keyword(s):

Power Output ◽

Deep Belief Network ◽

Belief Network

Download Full-text

Self-Organizing Traffic Flow Prediction with an Optimized Deep Belief Network for Internet of Vehicles

Sensors ◽

10.3390/s18103459 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3459 ◽

Cited By ~ 19

Author(s):

Shidrokh Goudarzi ◽

Mohd Kama ◽

Mohammad Anisi ◽

Seyed Soleymani ◽

Faiyaz Doctor

Keyword(s):

Traffic Flow ◽

Traffic Congestion ◽

Deep Belief Network ◽

Fine Tuning ◽

Superior Performance ◽

Traffic Information ◽

Series Data ◽

Internet Of Vehicles ◽

Belief Network ◽

Self Organizing

To assist in the broadcasting of time-critical traffic information in an Internet of Vehicles (IoV) and vehicular sensor networks (VSN), fast network connectivity is needed. Accurate traffic information prediction can improve traffic congestion and operation efficiency, which helps to reduce commute times, noise and carbon emissions. In this study, we present a novel approach for predicting the traffic flow volume by using traffic data in self-organizing vehicular networks. The proposed method is based on using a probabilistic generative neural network techniques called deep belief network (DBN) that includes multiple layers of restricted Boltzmann machine (RBM) auto-encoders. Time series data generated from the roadside units (RSUs) for five highway links are used by a three layer DBN to extract and learn key input features for constructing a model to predict traffic flow. Back-propagation is utilized as a general learning algorithm for fine-tuning the weight parameters among the visible and hidden layers of RBMs. During the training process the firefly algorithm (FFA) is applied for optimizing the DBN topology and learning rate parameter. Monte Carlo simulations are used to assess the accuracy of the prediction model. The results show that the proposed model achieves superior performance accuracy for predicting traffic flow in comparison with other approaches applied in the literature. The proposed approach can help to solve the problem of traffic congestion, and provide guidance and advice for road users and traffic regulators.

Download Full-text

Solar power output forecasting using evolutionary seasonal decomposition least-square support vector regression

Journal of Cleaner Production ◽

10.1016/j.jclepro.2015.08.099 ◽

2016 ◽

Vol 134 ◽

pp. 456-462 ◽

Cited By ~ 45

Author(s):

Kuo-Ping Lin ◽

Ping-Feng Pai

Keyword(s):

Support Vector Regression ◽

Power Output ◽

Solar Power ◽

Least Square ◽

Support Vector ◽

Seasonal Decomposition

Download Full-text

A Precise Diagnosis Method of Structural Faults of Rotating Machinery based on Combination of Empirical Mode Decomposition, Sample Entropy, and Deep Belief Network

Sensors ◽

10.3390/s19030591 ◽

2019 ◽

Vol 19 (3) ◽

pp. 591 ◽

Cited By ~ 7

Author(s):

Zhaoyi Guan ◽

Zhiqiang Liao ◽

Ke Li ◽

Peng Chen

Keyword(s):

Empirical Mode Decomposition ◽

Sample Entropy ◽

Rotating Machinery ◽

Deep Belief Network ◽

Superior Performance ◽

Intrinsic Mode Functions ◽

Belief Network ◽

Mode Decomposition ◽

Reconstructed Signal ◽

Fault Information

To precisely diagnose the rotating machinery structural faults, especially structural faults under low rotating speeds, a novel scheme based on combination of empirical mode decomposition (EMD), sample entropy, and deep belief network (DBN) is proposed in this paper. EMD can decompose a signal into several intrinsic mode functions (IMFs) with different signal-to-noise ratios (SNRs) and sample entropy is performed to extract the signals that carry fault information with high SNR. The extracted fault signal is reconstructed into a new vibration signal that will carry abundant fault information. DBN has strong feature extraction and classification performance. It is suitably performed to build the diagnosis model based on the reconstructed signal. The effectiveness of the proposed method is validated by structural faults signal and the comparative experiments (BPNN, CNN, time-domain signal only, frequency-domain signal only). The results show that the diagnosis accuracy of the proposed method is between 99% and 100%, the BPNN is less than 25%, and the CNN is between 70% and 95%, which means the verified, proposed method has a superior performance to diagnose the structural fault.

Download Full-text

Roundness and positioning deviation prediction in single point incremental forming using deep learning approaches

Advances in Mechanical Engineering ◽

10.1177/1687814019864465 ◽

2019 ◽

Vol 11 (7) ◽

pp. 168781401986446

Author(s):

Sofien Akrichi ◽

Amira Abbassi ◽

Sabeur Abid ◽

Noureddine Ben yahia

Keyword(s):

Deep Learning ◽

Incremental Forming ◽

Single Point ◽

Deep Belief Network ◽

Superior Performance ◽

Single Point Incremental Forming ◽

Learning Approaches ◽

Geometric Accuracy ◽

Forming Process ◽

Belief Network

This article proposes a deep learning technique for the prevision of the geometric accuracy in single point incremental forming. Moreover, predicting geometric accuracy is one of the most crucial measures of part quality. Accordingly, roundness and positioning deviation are two indicators for measuring geometric accuracy and presenting two output variables. Two types of artificial intelligence learning approaches, that is, shallow learning and deep learning, are investigated and compared for forecasting geometrical accuracy in the single point incremental forming process. Therefore, the back-propagation neural network with one hidden layer is selected as the representative for shallow learning and deep belief network and stack autoencoder are chosen as the representatives for deep learning. Accurate prediction is closely related to the feature learning of single point incremental forming process parameters. The following six parameters were considered as input variables: sheet thickness, tool path direction, step depth, speed rate, feed rate, and wall angle. The results of these studies indicate that deep learning could be a powerful tool in the current search for geometric accuracy prediction in single point incremental forming. Otherwise, the deep learning approach shows the best performance prediction with shallow learning. In addition, the deep belief network model achieves superior performance accuracy for the prediction of roundness and position deviation in comparison with the stack autoencoder approach.

Download Full-text