A hybrid model based on time series models and neural network for forecasting wind speed in the Brazilian northeast region

2018 ◽  
Vol 28 ◽  
pp. 65-72 ◽  
Author(s):  
Henrique do Nascimento Camelo ◽  
Paulo Sérgio Lucio ◽  
João Bosco Verçosa Leal Junior ◽  
Paulo Cesar Marques de Carvalho
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Wind Speed ◽  
Hybrid Model ◽  
Time Series Models ◽  
Northeast Region ◽  
Model Based ◽  
Brazilian Northeast

scholarly journals A Hybrid Model Based on a Two-Layer Decomposition Approach and an Optimized Neural Network for Chaotic Time Series Prediction

Symmetry ◽  
2019 ◽  
Vol 11 (5) ◽  
pp. 610 ◽  
Author(s):  
Xinghan Xu ◽  
Weijie Ren
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Hybrid Model ◽  
Back Propagation ◽  
Research Field ◽  
Chaotic Time Series ◽  
Good Prospect ◽  
Decomposition Approach ◽  
Model Based ◽  
Mode Decomposition

The prediction of chaotic time series has been a popular research field in recent years. Due to the strong non-stationary and high complexity of the chaotic time series, it is difficult to directly analyze and predict depending on a single model, so the hybrid prediction model has become a promising and favorable alternative. In this paper, we put forward a novel hybrid model based on a two-layer decomposition approach and an optimized back propagation neural network (BPNN). The two-layer decomposition approach is proposed to obtain comprehensive information of the chaotic time series, which is composed of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD). The VMD algorithm is used for further decomposition of the high frequency subsequences obtained by CEEMDAN, after which the prediction performance is significantly improved. We then use the BPNN optimized by a firefly algorithm (FA) for prediction. The experimental results indicate that the two-layer decomposition approach is superior to other competing approaches in terms of four evaluation indexes in one-step and multi-step ahead predictions. The proposed hybrid model has a good prospect in the prediction of chaotic time series.

scholarly journals Previsão de velocidade do vento em termos de médias mensais e horárias a partir da combinação dos modelos Holt-Winters e Redes Neurais Artificiais (Forecast wind speed in terms of monthly and hourly averages from the combination of the Holt-Winters...)

2017 ◽  
Vol 10 (5) ◽  
pp. 1391
Author(s):  
Henrique Do Nascimento Camelo ◽  
Paulo Sérgio Lucio ◽  
João Verçosa Leal Junior
Keyword(s):  
Artificial Intelligence ◽  
Time Series ◽  
Wind Speed ◽  
Hybrid Model ◽  
Northeastern Brazil ◽  
Percentage Error ◽  
Wind Speed Prediction ◽  
Wind Potential ◽  
Speed Prediction ◽  
Brazilian Northeast

O presente artigo propõe a criação de modelo híbrido combinado a partir de modelos de série temporal com inteligência artificial, com o objetivo de fornecer previsões de médias mensais e horárias da velocidade do vento em regiões do nordeste brasileiro. Métodos para previsão de velocidade do vento podem constituir em técnica útil no setor de geração eólica, por exemplo, sendo capaz de adquirir informações importantes de que maneira o potencial eólico local poderá ser aproveitado para possível geração de energia elétrica. É possível constatar a eficiência do modelo híbrido em fornecer perfeitos ajustes aos dados observados, sendo essa afirmativa baseada nos baixos valores encontrados na análise estatística de erros, por exemplo, com erro percentual de aproximadamente 5,0%, e também com o valor do coeficiente de eficiência de Nash-Sutcliffe, cujo valor encontrado em aproximadamente de 0,96. Esses resultados certamente foram importantes nas precisões das séries temporais previstas da velocidade do vento, fazendo com que pudessem acompanhar o perfil das séries temporais observadas da velocidade do vento, principalmente revelando maiores semelhanças de valores máximos e mínimos entre ambas as séries, e mostrando assim, a capacidade do modelo em representar características de sazonalidades local. A importância de fornecer garantias na estimativa da intensidade da velocidade do vento de uma região poderá ser tarefa de auxílio em tomada de decisão no setor de energia.  A B S T R A C TThe present article proposes the creation of hybrid model combined from time series models with artificial intelligence, aiming to provide forecasts of monthly and hourly wind speed averages in regions of northeastern Brazil. Wind speed prediction methods may be a useful technique in the wind power sector, for example, being able to acquire important information about how local wind potential can be harnessed for possible electric power generation. It is possible to verify the efficiency of the hybrid model in providing perfect adjustments to the data observed, being this affirmation based on the low values found in the statistical analysis of errors, for example, with percentage error of approximately 5.0%, and also with the coefficient value Of Nash-Sutcliffe efficiency, whose value was found to be approximately 0.96. These results were certainly important in the precisions of the predicted time series of the wind velocity, so that they could follow the profile of the observed time series of the wind speed, mainly revealing greater similarities of maximum and minimum values between both series, the ability of the model to represent characteristics of local seasonalities. The importance of providing assurances in the estimation of the wind speed intensity of a region may be a decision aid in the energy sector.Keywords: time series, artificial intelligence, wind energy, brazilian northeast. 

scholarly journals Artificial Combined Model Based on Hybrid Nonlinear Neural Network Models and Statistics Linear Models—Research and Application for Wind Speed Forecasting

2018 ◽  
Vol 10 (12) ◽  
pp. 4601 ◽  
Author(s):  
Yuewei Liu ◽  
Shenghui Zhang ◽  
Xuejun Chen ◽  
Jianzhou Wang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Wind Speed ◽  
Wind Farm ◽  
Linear Models ◽  
Search Algorithm ◽  
Forecasting Model ◽  
Neural Network Models ◽  
Wind Speed Forecasting ◽  
Model Based

The use of wind power is rapidly increasing as an important part of power systems, but because of the intermittent and random nature of wind speed, system operators and researchers urgently need to find more reliable methods to forecast wind speed. Through research, it is found that the time series of wind speed demonstrate not only linear features but also nonlinear features. Hence, a combined forecasting model based on an improved cuckoo search algorithm optimizes weight, and several single models—linear model, hybrid nonlinear neural network, and fuzzy forecasting model—are developed in this paper to provide more trend change for time series of wind speed forecasting besides improving the forecasting accuracy. Furthermore, the effectiveness of the proposed model is proved by wind speed data from four wind farm sites and the results are more reliable and accurate than comparison models.

scholarly journals Hybrid Model for Time Series of Complex Structure with ARIMA Components

Mathematics ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 1122
Author(s):  
Oksana Mandrikova ◽  
Nadezhda Fetisova ◽  
Yuriy Polozov
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Hybrid Model ◽  
Complex Structure ◽  
Arima Model ◽  
Ionospheric Parameter ◽  
Arima Models ◽  
Complicated Structure ◽  
Threshold Functions ◽  
Anomalous Component

A hybrid model for the time series of complex structure (HMTS) was proposed. It is based on the combination of function expansions in a wavelet series with ARIMA models. HMTS has regular and anomalous components. The time series components, obtained after expansion, have a simpler structure that makes it possible to identify the ARIMA model if the components are stationary. This allows us to obtain a more accurate ARIMA model for a time series of complicated structure and to extend the area for application. To identify the HMTS anomalous component, threshold functions are applied. This paper describes a technique to identify HMTS and proposes operations to detect anomalies. With the example of an ionospheric parameter time series, we show the HMTS efficiency, describe the results and their application in detecting ionospheric anomalies. The HMTS was compared with the nonlinear autoregression neural network NARX, which confirmed HMTS efficiency.

scholarly journals System for Forecasting COVID-19 Cases Using Time-Series and Neural Networks Models

2021 ◽  
Vol 5 (1) ◽  
pp. 46
Author(s):  
Mostafa Abotaleb ◽  
Tatiana Makarovskikh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Time Series Models ◽  
Third Wave ◽  
The Third ◽  
Modeling And Forecasting ◽  
Auto Regressive ◽  
The Russian Federation ◽  
R Programming

COVID-19 is one of the biggest challenges that countries face at the present time, as infections and deaths change daily and because this pandemic has a dynamic spread. Our paper considers two tasks. The first one is to develop a system for modeling COVID-19 based on time-series models due to their accuracy in forecasting COVID-19 cases. We developed an “Epidemic. TA” system using R programming for modeling and forecasting COVID-19 cases. This system contains linear (ARIMA and Holt’s model) and non-linear (BATS, TBATS, and SIR) time-series models and neural network auto-regressive models (NNAR), which allows us to obtain the most accurate forecasts of infections, deaths, and vaccination cases. The second task is the implementation of our system to forecast the risk of the third wave of infections in the Russian Federation.

Sign in / Sign up

Export Citation Format

Share Document