scholarly journals Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model

2016 ◽  
Vol 2 (3) ◽  
pp. 131 ◽  
Author(s):  
Winita Sulandari ◽  
Subanar Subanar ◽  
Suhartono Suhartono ◽  
Herni Utami
Keyword(s):  
Neural Network ◽  
Hybrid Model ◽  
Network Model ◽  
Neural Network Model ◽  
Exponential Smoothing ◽  
Series Data ◽  
Demand Forecast ◽  
Forecast Performance ◽  
Load Demand ◽  
Electricity Load

Short-term electricity load demand forecast is a vital requirements for power systems. This research considers the combination of exponential smoothing for double seasonal patterns and neural network model. The linear version of Holt-Winter method is extended to accommodate a second seasonal component. In this work, the Fourier with time varying coefficient is presented as a means of seasonal extraction. The methodological contribution of this paper is to demonstrate how these methods can be adapted to model the time series data with multiple seasonal pattern, correlated non stationary error and nonlinearity components together. The proposed hybrid model is started by implementing exponential smoothing state space model to obtain the level, trend, seasonal and irregular components and then use them as inputs of neural network. Forecasts of future values are then can be obtained by using the hybrid model. The forecast performance was characterized by root mean square error and mean absolute percentage error. The proposed hybrid model is applied to two real load series that are energy consumption in Bawen substation and in Java-Bali area. Comparing with other existing models, results show that the proposed hybrid model generate the most accurate forecast

scholarly journals PV Power Prediction, Using CNN-LSTM Hybrid Neural Network Model. Case of Study: Temixco-Morelos, México

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6512
Author(s):  
Mario Tovar ◽  
Miguel Robles ◽  
Felipe Rashid
Keyword(s):  
Neural Network ◽  
Hybrid Model ◽  
Network Model ◽  
Neural Network Model ◽  
Short Term Memory ◽  
Lasso Regression ◽  
Neural Network Models ◽  
Model Case ◽  
Hybrid Neural Network ◽  
Photovoltaic Power

Due to the intermittent nature of solar energy, accurate photovoltaic power predictions are very important for energy integration into existing energy systems. The evolution of deep learning has also opened the possibility to apply neural network models to predict time series, achieving excellent results. In this paper, a five layer CNN-LSTM model is proposed for photovoltaic power predictions using real data from a location in Temixco, Morelos in Mexico. In the proposed hybrid model, the convolutional layer acts like a filter, extracting local features of the data; then the temporal features are extracted by the long short-term memory network. Finally, the performance of the hybrid model with five layers is compared with a single model (a single LSTM), a CNN-LSTM hybrid model with two layers and two well known popular benchmarks. The results also shows that the hybrid neural network model has better prediction effect than the two layer hybrid model, the single prediction model, the Lasso regression or the Ridge regression.

Genetic algorithms and hybrid neural network modelling for aluminium stress—strain prediction

2003 ◽  
Vol 217 (1) ◽  
pp. 7-21 ◽  
Author(s):  
Y Y Yang ◽  
D A Linkens ◽  
M Mahfouf
Keyword(s):  
Neural Network ◽  
Genetic Algorithms ◽  
Constitutive Model ◽  
Hybrid Model ◽  
Network Model ◽  
Neural Network Model ◽  
Constitutive Equations ◽  
Model Performance ◽  
Hybrid Neural Network ◽  
Real Value

This paper addresses the design of genetic algorithms in developing a hybrid neural network model for aluminium alloy flow stress prediction. The hybrid neural network model consists of a parallel grey-box model structure, with the resulting predictions combining the outputs from the constitutive equations and a neural network. Previous work shows that the hybrid neural network model can deliver better model performance than a neural network model or the constitutive equations. However, the level of performance improvement of the hybrid model depends on the quality of the constitutive model used. This motivates the search for a better constitutive model, with genetic algorithms being employed to optimize its parameters. The advantage of genetic algorithms is that they do not require any gradient information nor continuity assumption in searching for the best parameters. A number of genetic optimization schemes, with different coding schemes (such as binary coding and real-value chromosomes) and different genetic operators for selection, crossover and mutation, have been investigated. The real-value coded genetic algorithms converge much more rapidly and are more efficient since there is no need for chromosome encoding and decoding. Compared with previous work, the resulting hybrid model performance has been improved, mainly in the generalization capability and with a simpler neural network structure. Also, the model response surfaces are much smoother and more metallurgically convincing.

scholarly journals Bayesian Stochastic Neural Network Model for Turbomachinery Damage Prediction

2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Shuhua Yang ◽  
Xiaomo Jiang ◽  
Shengli Xu ◽  
Xiaofang Wang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Signal Processing ◽  
Network Model ◽  
Neural Network Model ◽  
Time Series Data ◽  
Series Data ◽  
Stochastic Neural Network ◽  
Damage Prediction ◽  
Multivariate Correlation

Turbomachinery often suffers various defects such as impeller cracking, resulting in forced outage, increased maintenance costs, and reduced productivity. Condition monitoring and damage prognostics has been widely used as an increasingly important and powerful tool to improve the system availability, reliability, performance, and maintainability, but still very challenging due to multiple sources of data uncertainties and the complexity of analytics modeling. This paper presents an intelligent probabilistic methodology for anomaly prediction of high-fidelity turbomachine, considering multiple data imperfections and multivariate correlation. The proposed method adeptly integrates several advanced state-of-the-art signal processing and artificial intelligence techniques: wavelet multi-resolution decomposition, Bayesian hypothesis testing, probabilistic principal component analysis, and fuzzy stochastic neural network modeling. The advanced signal processing is employed to reduce dimensionality and to address multivariate correlation and data uncertainty for damage prediction. Instead of conventionally using raw time series data, principal components are utilized in the establishment of stochastic neural network model and anomaly prediction. Bayesian interval hypothesis testing metric is then presented to quantitatively compare the predicted and measured data for model validation and anomaly evaluation, thus providing a confidence indicator to judge the model quality and evaluate the equipment status. Bayesian method is developed in this study for denoising the raw data with multiresolution wavelet decomposition, quantifying the model accuracy, and assessing the equipment status. The dynamic stochastic neural network model is established via the nonlinear autoregressive moving average with exogenous inputs approach. It seamlessly integrates the fuzzy clustering and independent Bernoulli random function into radial basis function neural network. A natural gradient method based on Kullback-Leibler distance criterion is employed to maximize the log-likelihood loss function. The effectiveness of the proposed methodology and procedure is demonstrated with the 11-variable time series data and the forced outage event of a real-world centrifugal compressor.

Neural network model ensembles for building-level electricity load forecasts

2014 ◽  
Vol 84 ◽  
pp. 214-223 ◽  
Author(s):  
Jorjeta G. Jetcheva ◽  
Mostafa Majidpour ◽  
Wei-Peng Chen
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Electricity Load ◽  
Model Ensembles ◽  
Building Level

Coal Demand Prediction in Shandong Province Based on Artificial Firefly Wavelet Neural Network

2014 ◽  
Vol 962-965 ◽  
pp. 1931-1935
Author(s):  
Jing Hong Yang ◽  
Chang You Wu ◽  
Gui Mei Zhang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Optimization Method ◽  
Wavelet Neural Network ◽  
Systematic Research ◽  
Optimal Solutions ◽  
Demand Forecast ◽  
Demand Prediction ◽  
Firefly Optimization

On the basis of the existing research results, after a systematic research of the wavelet neural network model, we found that the slow convergence and easily get into local optimal solutions. To solve this problem, using artificial firefly optimization method to optimize the parameters in wavelet neural network, and Artificial Firefly Wavelet neural network model is established. Apply this model to the Shandong coal demand forecast achieve better results, proved that establishing artificial Firefly Wavelet neural network model is scientific and feasible.

Sign in / Sign up

Export Citation Format

Share Document