scholarly journals Sun Position Identification in Sky Images for Nowcasting Application

Forecasting ◽  
2020 ◽  
Vol 2 (4) ◽  
pp. 488-504
Author(s):  
Alessandro Niccolai ◽  
Alfredo Nespoli
Keyword(s):  
Neural Network ◽  
Renewable Energy Sources ◽  
Computational Effort ◽  
The Sun ◽  
Short Term ◽  
Energy Management Systems ◽  
The Neural Network ◽  
Stability Issues ◽  
Microgrid Energy Management ◽  
Solar Angle

Very-short-term photovoltaic power forecast, namely nowcasting, is gaining increasing attention to face grid stability issues and to optimize microgrid energy management systems in the presence of large penetration of renewable energy sources. In order to identify local phenomena as sharp ramps in photovoltaic production, whole sky images can be used effectively. The first step in the implementation of new and effective nowcasting algorithms is the identification of Sun positions. In this paper, three different techniques (solar angle-based, image processing-based, and neural network-based techniques) are proposed, described, and compared. These techniques are tested on real images obtained with a camera installed at SolarTechLab at Politecnico di Milano, Milan, Italy. Finally, the three techniques are compared by introducing some performance parameters aiming to evaluate of their reliability, accuracy, and computational effort. The neural network-based technique obtains the best performance: in fact, this method is able to identify accurately the Sun position and to estimate it when the Sun is covered by clouds.

scholarly journals Performance Evaluation of Neural Network-Based Short-Term Solar Irradiation Forecasts

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3030
Author(s):  
Simon Liebermann ◽  
Jung-Sup Um ◽  
YoungSeok Hwang ◽  
Stephan Schlüter
Keyword(s):  
Neural Network ◽  
Goodness Of Fit ◽  
Renewable Energy Sources ◽  
Weather Conditions ◽  
Solar Irradiation ◽  
Weather Data ◽  
Short Term ◽  
Climate Conditions ◽  
Lstm Network ◽  
The Time Domain

Due to the globally increasing share of renewable energy sources like wind and solar power, precise forecasts for weather data are becoming more and more important. To compute such forecasts numerous authors apply neural networks (NN), whereby models became ever more complex recently. Using solar irradiation as an example, we verify if this additional complexity is required in terms of forecasting precision. Different NN models, namely the long-short term (LSTM) neural network, a convolutional neural network (CNN), and combinations of both are benchmarked against each other. The naive forecast is included as a baseline. Various locations across Europe are tested to analyze the models’ performance under different climate conditions. Forecasts up to 24 h in advance are generated and compared using different goodness of fit (GoF) measures. Besides, errors are analyzed in the time domain. As expected, the error of all models increases with rising forecasting horizon. Over all test stations it shows that combining an LSTM network with a CNN yields the best performance. However, regarding the chosen GoF measures, differences to the alternative approaches are fairly small. The hybrid model’s advantage lies not in the improved GoF but in its versatility: contrary to an LSTM or a CNN, it produces good results under all tested weather conditions.

scholarly journals A Novel Neural Network-Based SINS/DVL Integrated Navigation Approach to Deal with DVL Malfunction for Underwater Vehicles

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Wanli Li ◽  
Mingjian Chen ◽  
Chao Zhang ◽  
Lundong Zhang ◽  
Rui Chen
Keyword(s):  
Neural Network ◽  
Autonomous Navigation ◽  
Underwater Vehicles ◽  
The Body ◽  
Doppler Velocity ◽  
Integrated Navigation ◽  
Body Frame ◽  
Short Term ◽  
The Neural Network ◽  
Nonlinear Autoregressive

A navigation grade Strapdown Inertial Navigation System (SINS) combined with a Doppler Velocity Log (DVL) is widely used for autonomous navigation of underwater vehicles. Whether the DVL is able to provide continuous velocity measurements is of crucial importance to the integrated navigation precision. Considering that the DVL may fail during the missions, a novel neural network-based SINS/DVL integrated navigation approach is proposed. The nonlinear autoregressive exogenous (NARX) neural network, which is able to provide reliable predictions, is employed. While the DVL is available, the neural network is trained by the body frame velocity and its increment from the SINS and the DVL measurements. Once the DVL fails, the well trained network is able to forecast the velocity which can be used for the subsequent navigation. From the experimental results, it is clearly shown that the neural network is able to provide reliable velocity predictions for about 200 s–300 s during DVL malfunction and hence maintain the short-term accuracy of the integrated navigation.

scholarly journals NEURAL NETWORK FORECASTING OF ENERGY CONSUMPTION OF A METALLURGICAL ENTERPRISE

2021 ◽  
pp. 14-22
Author(s):  
Anna Bakurova ◽  
Olesia Yuskiv ◽  
Dima Shyrokorad ◽  
Anton Riabenko ◽  
Elina Tereschenko
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Energy Consumption ◽  
Short Term ◽  
Metallurgical Enterprise ◽  
Input Information ◽  
The Neural Network ◽  
Artificial Neural

The subject of the research is the methods of constructing and training neural networks as a nonlinear modeling apparatus for solving the problem of predicting the energy consumption of metallurgical enterprises. The purpose of this work is to develop a model for forecasting the consumption of the power system of a metallurgical enterprise and its experimental testing on the data available for research of PJSC "Dneprospetsstal". The following tasks have been solved: analysis of the time series of power consumption; building a model with the help of which data on electricity consumption for a historical period is processed; building the most accurate forecast of the actual amount of electricity for the day ahead; assessment of the forecast quality. Methods used: time series analysis, neural network modeling, short-term forecasting of energy consumption in the metallurgical industry. The results obtained: to develop a model for predicting the energy consumption of a metallurgical enterprise based on artificial neural networks, the MATLAB complex with the Neural Network Toolbox was chosen. When conducting experiments, based on the available statistical data of a metallurgical enterprise, a selection of architectures and algorithms for learning neural networks was carried out. The best results were shown by the feedforward and backpropagation network, architecture with nonlinear autoregressive and learning algorithms: Levenberg-Marquard nonlinear optimization, Bayesian Regularization method and conjugate gradient method. Another approach, deep learning, is also considered, namely the neural network with long short-term memory LSTM and the adam learning algorithm. Such a deep neural network allows you to process large amounts of input information in a short time and build dependencies with uninformative input information. The LSTM network turned out to be the most effective among the considered neural networks, for which the indicator of the maximum prediction error had the minimum value. Conclusions: analysis of forecasting results using the developed models showed that the chosen approach with experimentally selected architectures and learning algorithms meets the necessary requirements for forecast accuracy when developing a forecasting model based on artificial neural networks. The use of models will allow automating high-precision operational hourly forecasting of energy consumption in market conditions. Keywords: energy consumption; forecasting; artificial neural network; time series.

scholarly journals Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network

2019 ◽  
Vol 9 (16) ◽  
pp. 3355 ◽  
Author(s):  
Min Seop Lee ◽  
Yun Kyu Lee ◽  
Dong Sung Pae ◽  
Myo Taeg Lim ◽  
Dong Won Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Emotion Recognition ◽  
Binary Classification ◽  
Single Pulse ◽  
Signal Pulse ◽  
Short Term ◽  
Signal Features ◽  
The Neural Network ◽  
Valence And Arousal

Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3% and 76.2% valence and arousal accuracies, respectively, on the DEAP data.

Neural Network Forecasting of Tourism Demand

2005 ◽  
Vol 11 (3) ◽  
pp. 301-328 ◽  
Author(s):  
Sen Cheong Kon ◽  
Lindsay W. Turner
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Accurate Method ◽  
Future Research ◽  
Data Series ◽  
Structural Method ◽  
Short Term ◽  
Neural Network Models ◽  
The Neural Network ◽  
Short Term Forecasting

In times of tourism uncertainty, practitioners need short-term forecasting methods. This study compares the forecasting accuracy of the basic structural method (BSM) and the neural network method to find the best structure for neural network models. Data for arrivals to Singapore are used to test the analysis while the naïve and Holt-Winters methods are used for base comparison of simpler models. The results confirm that the BSM remains a highly accurate method and that correctly structured neural models can outperform BSM and the simpler methods in the short term, and can also use short data series. These findings make neural methods significant candidates for future research.

HUMAN ROBOT INTERACTIVE INTENTION PREDICTION USING DEEP LEARNING TECHNIQUES

2021 ◽  
pp. 1-12
Author(s):  
Thang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
The Neural Network ◽  
Learning Techniques ◽  
Long Short Term Memory ◽  
Deep Learning Neural Network

In this research, we propose a method of human robot interactive intention prediction. The proposed algorithm makes use of a OpenPose library and a Long-short term memory deep learning neural network. The neural network observes the human posture in a time series, then predicts the human interactive intention. We train the deep neural network using dataset generated by us. The experimental results show that, our proposed method is able to predict the human robot interactive intention, providing 92% the accuracy on the testing set.

scholarly journals Short Term Electric Load Forecasting of Kathmandu Valley of Nepal using Artificial Neural Network

2018 ◽  
Vol 1 (1) ◽  
pp. 43-48
Author(s):  
Binod Bhandari ◽  
Shree Raj Shakya ◽  
Ajay Kumar Jha
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Load Flow ◽  
Kathmandu Valley ◽  
Electric Load ◽  
Short Term ◽  
Load Demand ◽  
The Neural Network ◽  
Artificial Neural

Decision making in the energy sector has to be based on accurate forecasts of the load demand. Short-term forecasting, which forms the focus of this paper, gives a day ahead hourly forecast of electric load. This forecast can help to make important decisions in the field of scheduling, contingency analysis, load flow analysis, preventing imbalance in the power generation and load demand, load switching strategies, thus leading to greater network reliability and power quality. A method called Artificial Neural Network is used to anticipate the future load of Kathmandu Valley of Nepal. The Neural Network is build, trained with historical data along with seven different input variables and used for prediction of day ahead 24 hours load. The output is validated with the real Load collected from NEA. In addition, forecasting is performed by some other time series methods as well, and whose output are compared with that of neural network. The range of Mean Absolute Deviation for four different time series models lied between 1.50-2.59. When the errors were calculated in terms of MSE and MAPE the range of these values were found to be in between 2.59-7.78, and 1.61- 5.07 respectively. The Artificial Neural Network proved to be the more accurate forecast method when the results are compared in terms of error measurements with a MAD having 1.23, MSE having 1.79 and MAPE having 1.17. The Neural Network proved to be more accurate method comparatively with satisfactory minimum error.

scholarly journals Deep Learning for Subtyping and Prediction of Diseases: Long-Short Term Memory

2021 ◽  
Author(s):  
Hayrettin Okut
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Short Term ◽  
Time Step ◽  
Term Memory ◽  
The Neural Network ◽  
Long Short Term Memory ◽  
Sequential Information ◽  
Hidden Layer

The long short-term memory neural network (LSTM) is a type of recurrent neural network (RNN). During the training of RNN architecture, sequential information is used and travels through the neural network from input vector to the output neurons, while the error is calculated and propagated back through the network to update the network parameters. Information in these networks incorporates loops into the hidden layer. Loops allow information to flow multi-directionally so that the hidden state signifies past information held at a given time step. Consequently, the output is dependent on the previous predictions which are already known. However, RNNs have limited capacity to bridge more than a certain number of steps. Mainly this is due to the vanishing of gradients which causes the predictions to capture the short-term dependencies as information from earlier steps decays. As more layers in RNN containing activation functions are added, the gradient of the loss function approaches zero. The LSTM neural networks (LSTM-ANNs) enable learning long-term dependencies. LSTM introduces a memory unit and gate mechanism to enable capture of the long dependencies in a sequence. Therefore, LSTM networks can selectively remember or forget information and are capable of learn thousands timesteps by structures called cell states and three gates.

scholarly journals A neural network model for short term prediction of surface ozone at Pone

MAUSAM ◽  
2021 ◽  
Vol 50 (1) ◽  
pp. 91-98
Author(s):  
P. GUHATHAKURTA
Keyword(s):  
Neural Network ◽  
Air Pollution ◽  
Network Model ◽  
Neural Network Model ◽  
Surface Ozone ◽  
Anthropogenic Activity ◽  
Short Term ◽  
Term Prediction ◽  
The Neural Network ◽  
Short Term Prediction

A new method for short term prediction of air pollution is presented using the neural network technique, Due to increase in industrial and anthropogenic activity, air pollution is a serious subject of concern today, Surface ozone can be considered as a representative of total atmospheric oxidants and of air pollution, A three layer neural network model using the technique of adaptive pattern recognition is developed, The model can predict the mean surface ozone between 12 and 13 hours (hour of maximum concentration), The model can perform well both in training and independent periods, The classical methods of short term modelling are not reliable enough, The method can also be used for short term prediction of other air pollutants.

Sign in / Sign up

Export Citation Format

Share Document