scholarly journals Deep Learning Neural Networks Trained with MODIS Satellite-Derived Predictors for Long-Term Global Solar Radiation Prediction

Energies ◽  
2019 ◽  
Vol 12 (12) ◽  
pp. 2407 ◽  
Author(s):  
Ghimire ◽  
Deo ◽  
Raj ◽  
Mi
Keyword(s):  
Neural Networks ◽  
Feature Selection ◽  
Renewable Energy ◽  
Deep Learning ◽  
Solar Radiation ◽  
Solar Energy ◽  
Deep Neural Networks ◽  
Global Solar Radiation ◽  
Hidden Layer

Solar energy predictive models designed to emulate the long-term (e.g., monthly) global solar radiation (GSR) trained with satellite-derived predictors can be employed as decision tenets in the exploration, installation and management of solar energy production systems in remote and inaccessible solar-powered sites. In spite of a plethora of models designed for GSR prediction, deep learning, representing a state-of-the-art intelligent tool, remains an attractive approach for renewable energy exploration, monitoring and forecasting. In this paper, algorithms based on deep belief networks and deep neural networks are designed to predict long-term GSR. Deep learning algorithms trained with publicly-accessible Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data are tested in Australia’s solar cities to predict the monthly GSR: single hidden layer and ensemble models. The monthly-scale MODIS-derived predictors (2003–2018) are adopted, with 15 diverse feature selection approaches including a Gaussian Emulation Machine for sensitivity analysis used to select optimal MODIS-predictor variables to simulate GSR against ground-truth values. Several statistical score metrics are adopted to comprehensively verify surface GSR simulations to ascertain the practicality of deep belief and deep neural networks. In the testing phase, deep learning models generate significantly lower absolute percentage bias (≤3%) and high Kling–Gupta efficiency (≥97.5%) values compared to the single hidden layer and ensemble model. This study ascertains that the optimal MODIS input variables employed in GSR prediction for solar energy applications can be relatively different for diverse sites, advocating a need for feature selection prior to the modelling of GSR. The proposed deep learning approach can be adopted to identify solar energy potential proactively in locations where it is impossible to install an environmental monitoring data acquisition instrument. Hence, MODIS and other related satellite-derived predictors can be incorporated for solar energy prediction as a strategy for long-term renewable energy exploration.

scholarly journals A Modified Method to Generate Typical Meteorological Years from the Long-Term Weather Database

2012 ◽  
Vol 2012 ◽  
pp. 1-9 ◽  
Author(s):  
Haixiang Zang ◽  
Qingshan Xu ◽  
Pengwei Du ◽  
Katsuhiro Ichiyanagi
Keyword(s):  
Relative Humidity ◽  
Solar Radiation ◽  
Solar Energy ◽  
Atmospheric Pressure ◽  
Energy Systems ◽  
Global Solar Radiation ◽  
Weather Data ◽  
Radiation Data ◽  
Modified Method

A modified typical meteorological year (TMY) method is proposed for generating TMY from practical measured weather data. A total of eleven weather indices and novel assigned weighting factors are applied in the processing of forming the TMY database. TMYs of 35 cities in China are generated based on the latest and accurate measured weather data (dry bulb temperature, relative humidity, wind velocity, atmospheric pressure, and daily global solar radiation) in the period of 1994–2010. The TMY data and typical solar radiation data are also investigated and analyzed in this paper, which are important in the utilizations of solar energy systems.

scholarly journals A Review of Solar Radiation Models—Part I

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
A. K. Katiyar ◽  
C. K. Pandey
Keyword(s):  
Renewable Energy ◽  
Solar Radiation ◽  
Solar Energy ◽  
Energy Demand ◽  
Socioeconomic Development ◽  
Global Solar Radiation ◽  
Point Of View ◽  
Climate Conditions ◽  
Energy Devices ◽  
The World

Energy is considered as a key source for the future and plays a pivotal role in its socioeconomic development by raising the standard of living and the quality of life, not only for India but also for the world. In view of the scarce fossil fuel reserves, solar energy is one of the important sources of renewable energy used in India because of the suitable climate conditions. It receives about 5485.17 Wh/m2day of solar insolation with an annual total of about 19, 74, 661.2 Wh/m2. Except for the monsoon months, solar radiation incidence is very encouraging, from the application point of view. For the efficient functioning and better performance of solar energy device, the information of solar radiation and its components at particular location is very essential for designing the solar energy devices. Therefore, over the years, several empirical correlations have been developed in order to estimate the more appropriate solar radiation in India as well as around the world. Here we present a review of different solar radiation models which predict global solar radiation and discussed the long-term plan to meet future energy demand with renewable energy due to economy growth.

scholarly journals Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness

2019 ◽  
Author(s):  
NhatHai Phan ◽  
Minh N. Vu ◽  
Yang Liu ◽  
Ruoming Jin ◽  
Dejing Dou ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Theoretical Analysis ◽  
Gaussian Noise ◽  
Deep Neural Networks ◽  
Differential Privacy ◽  
Trade Off ◽  
Adversarial Examples ◽  
Hidden Layer ◽  
Privacy Budget

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in the traditional Gaussian Mechanism from (0, 1] to (0, infty), with a new bound of the noise scale to preserve differential privacy. The noise in our mechanism can be arbitrarily redistributed, offering a distinctive ability to address the trade-off between model utility and privacy loss. To derive provable robustness, our HGM is applied to inject Gaussian noise into the first hidden layer. Then, a tighter robustness bound is proposed. Theoretical analysis and thorough evaluations show that our mechanism notably improves the robustness of differentially private deep neural networks, compared with baseline approaches, under a variety of model attacks.

scholarly journals Evaluation of distributional solar radiation parameters of Cacak using long-term measured global solar radiation data

2007 ◽  
Vol 11 (4) ◽  
pp. 125-134 ◽  
Author(s):  
Snezana Dragicevic ◽  
Nikola Vuckovic
Keyword(s):  
Solar Radiation ◽  
Solar Energy ◽  
Energy Demand ◽  
Energy Production ◽  
Global Solar Radiation ◽  
Primary Energy ◽  
Horizontal Surface ◽  
Energy Potential ◽  
Radiation Data

Serbia is becoming more dependent on imported primary energy to meet its increasing energy demand. The ratio of indigenous primary energy production to primary energy consumption is decreasing. Therefore, it is of great importance for Serbia to make use of its indigenous energy resources more effectively, including its solar energy potential. Knowledge of global solar radiation is essential in the prediction, study, and design of the economic viability of systems which use solar energy. In this paper, the solar radiation data on Cacak (lat 43.87?N, long 20.33?E) are analyzed based on 4 years of global solar radiation data measured on a horizontal surface. The distributional solar radiation parameters are derived from the available data and analyzed. The available solar radiation data on a horizontal surface are converted to that of various tilt angles and the yearly and monthly optimum tilt angles are determined.

scholarly journals Towards Interpretable Deep Learning: A Feature Selection Framework for Prognostics and Health Management Using Deep Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5888
Author(s):  
Joaquín Figueroa Barraza ◽  
Enrique López Droguett ◽  
Marcelo Ramos Martins
Keyword(s):  
Neural Networks ◽  
Feature Selection ◽  
Deep Learning ◽  
High Performance ◽  
Deep Neural Networks ◽  
Health Management ◽  
Remaining Useful Life ◽  
Health State ◽  
Prognostics And Health Management ◽  
Selection Framework

In the last five years, the inclusion of Deep Learning algorithms in prognostics and health management (PHM) has led to a performance increase in diagnostics, prognostics, and anomaly detection. However, the lack of interpretability of these models results in resistance towards their deployment. Deep Learning-based models fall within the accuracy/interpretability tradeoff, which means that their complexity leads to high performance levels but lacks interpretability. This work aims at addressing this tradeoff by proposing a technique for feature selection embedded in deep neural networks that uses a feature selection (FS) layer trained with the rest of the network to evaluate the input features’ importance. The importance values are used to determine which will be considered for deployment of a PHM model. For comparison with other techniques, this paper introduces a new metric called ranking quality score (RQS), that measures how performance evolves while following the corresponding ranking. The proposed framework is exemplified with three case studies involving health state diagnostics and prognostics and remaining useful life prediction. Results show that the proposed technique achieves higher RQS than the compared techniques, while maintaining the same performance level when compared to the same model but without an FS layer.

scholarly journals Artificial Neural Networks and Deep Learning for Genomic Prediction of Continuous Outcomes

2022 ◽  
pp. 427-476
Author(s):  
Osval Antonio Montesinos López ◽  
Abelardo Montesinos López ◽  
Jose Crossa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Learning Rate ◽  
Continuous Outcomes ◽  
General Guide ◽  
Tuning Process ◽  
Hidden Layer ◽  
Learning Frameworks

AbstractThis chapter provides elements for implementing deep neural networks (deep learning) for continuous outcomes. We give details of the hyperparameters to be tuned in deep neural networks and provide a general guide for doing this task with more probability of success. Then we explain the most popular deep learning frameworks that can be used to implement these models as well as the most popular optimizers available in many software programs for deep learning. Several practical examples with plant breeding data for implementing deep neural networks in the Keras library are outlined. These examples take into account many components in the predictor as well many hyperparameters (hidden layer, number of neurons, learning rate, optimizers, penalization, etc.) for which we also illustrate how the tuning process can be done to increase the probability of a successful application.

scholarly journals A Linear Regression Model for Global Solar Radiation on Horizontal Surfaces at Warri, Nigeria

2013 ◽  
Vol 2 (3) ◽  
pp. 121-126 ◽  
Author(s):  
Michael S. Okundamiya ◽  
Israel E. Okpamen
Keyword(s):  
Renewable Energy ◽  
Linear Regression ◽  
Solar Radiation ◽  
Solar Energy ◽  
Regression Model ◽  
Linear Regression Model ◽  
Global Solar Radiation ◽  
Mean Bias Error ◽  
Accurate Estimation ◽  
Radiation Data

The growing anxiety on the negative effects of fossil fuels on the environment and the global emission reduction targets call for a more extensive use of renewable energy alternatives. Efficient solar energy utilization is an essential solution to the high atmospheric pollution caused by fossil fuel combustion. Global solar radiation (GSR) data, which are useful for the design and evaluation of solar energy conversion system, are not measured at the forty-five meteorological stations in Nigeria. The dearth of the measured solar radiation data calls for accurate estimation. This study proposed a temperature-based linear regression, for predicting the monthly average daily GSR on horizontal surfaces, at Warri (latitude 5.020N and longitude 7.880E) an oil city located in the south-south geopolitical zone, in Nigeria. The proposed model is analyzed based on five statistical indicators (coefficient of correlation, coefficient of determination, mean bias error, root mean square error, and t-statistic), and compared with the existing sunshine-based model for the same study. The results indicate that the proposed temperature-based linear regression model could replace the existing sunshine-based model for generating global solar radiation data. Keywords: air temperature; empirical model; global solar radiation; regression analysis; renewable energy; Warri

Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks

2019 ◽  
Vol 12 (3) ◽  
pp. 156-161 ◽  
Author(s):  
Aman Dureja ◽  
Payal Pahwa
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Primary Objective ◽  
Experimental Comparison ◽  
Activation Functions ◽  
Practical Applications ◽  
Network Activation ◽  
Non Linear ◽  
Hidden Layer

Background: In making the deep neural network, activation functions play an important role. But the choice of activation functions also affects the network in term of optimization and to retrieve the better results. Several activation functions have been introduced in machine learning for many practical applications. But which activation function should use at hidden layer of deep neural networks was not identified. Objective: The primary objective of this analysis was to describe which activation function must be used at hidden layers for deep neural networks to solve complex non-linear problems. Methods: The configuration for this comparative model was used by using the datasets of 2 classes (Cat/Dog). The number of Convolutional layer used in this network was 3 and the pooling layer was also introduced after each layer of CNN layer. The total of the dataset was divided into the two parts. The first 8000 images were mainly used for training the network and the next 2000 images were used for testing the network. Results: The experimental comparison was done by analyzing the network by taking different activation functions on each layer of CNN network. The validation error and accuracy on Cat/Dog dataset were analyzed using activation functions (ReLU, Tanh, Selu, PRelu, Elu) at number of hidden layers. Overall the Relu gave best performance with the validation loss at 25th Epoch 0.3912 and validation accuracy at 25th Epoch 0.8320. Conclusion: It is found that a CNN model with ReLU hidden layers (3 hidden layers here) gives best results and improve overall performance better in term of accuracy and speed. These advantages of ReLU in CNN at number of hidden layers are helpful to effectively and fast retrieval of images from the databases.

scholarly journals Detrended Multiple Cross-Correlation Coefficient applied to solar radiation, air temperature and relative humidity

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Andrea de Almeida Brito ◽  
Heráclio Alves de Araújo ◽  
Gilney Figueira Zebende
Keyword(s):  
Relative Humidity ◽  
Solar Radiation ◽  
Solar Energy ◽  
Correlation Coefficient ◽  
Air Temperature ◽  
Cross Correlation ◽  
Global Solar Radiation ◽  
Meteorological Variables ◽  
Hourly Data ◽  
Cross Correlations

AbstractDue to the importance of generating energy sustainably, with the Sun being a large solar power plant for the Earth, we study the cross-correlations between the main meteorological variables (global solar radiation, air temperature, and relative air humidity) from a global cross-correlation perspective to efficiently capture solar energy. This is done initially between pairs of these variables, with the Detrended Cross-Correlation Coefficient, ρDCCA, and subsequently with the recently developed Multiple Detrended Cross-Correlation Coefficient, $${\boldsymbol{DM}}{{\boldsymbol{C}}}_{{\bf{x}}}^{{\bf{2}}}$$DMCx2. We use the hourly data from three meteorological stations of the Brazilian Institute of Meteorology located in the state of Bahia (Brazil). Initially, with the original data, we set up a color map for each variable to show the time dynamics. After, ρDCCA was calculated, thus obtaining a positive value between the global solar radiation and air temperature, and a negative value between the global solar radiation and air relative humidity, for all time scales. Finally, for the first time, was applied $${\boldsymbol{DM}}{{\boldsymbol{C}}}_{{\bf{x}}}^{{\bf{2}}}$$DMCx2 to analyze cross-correlations between three meteorological variables at the same time. On taking the global radiation as the dependent variable, and assuming that $${\boldsymbol{DM}}{{\boldsymbol{C}}}_{{\bf{x}}}^{{\bf{2}}}={\bf{1}}$$DMCx2=1 (which varies from 0 to 1) is the ideal value for the capture of solar energy, our analysis finds some patterns (differences) involving these meteorological stations with a high intensity of annual solar radiation.

scholarly journals Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1579
Author(s):  
Dongqi Wang ◽  
Qinghua Meng ◽  
Dongming Chen ◽  
Hupo Zhang ◽  
Lisheng Xu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Channel Model ◽  
Expert Knowledge ◽  
Automatic Detection ◽  
Data Representation ◽  
Learning Technology ◽  
Arrhythmia Detection ◽  
Automatic Feature Extraction

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition.

Sign in / Sign up

Export Citation Format

Share Document