Innovative hybrid models for forecasting time series applied in wind generation based on the combination of time series models with artificial neural networks

Camelo, Henrique do Nascimento; Lúcio, Paulo Sérgio; Leal, João Bosco Verçosa; Carvalho, Paulo César Marques de; Santos, Daniel von Glehn dos

doi:10.1016/j.energy.2018.03.077

Cited by 68 publications

(24 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among them, autoregressive models based on moving averages have proved effective in several problems [24]. In particular, there are applications of autoregressive models to predict renewable energy (wind, solar, hydro) production and demand [25][26][27][28][29][30][31][32][33].…”

Section: Box-jenkins and Box-tiao Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Time Series Analysis for Predicting Hydroelectric Power Production: The Ecuador Case

et al. 2019

View full text Add to dashboard Cite

Electrical generation in Ecuador mainly comes from hydroelectric and thermo-fossil sources, with the former amounting to almost half of the national production. Even though hydroelectric power sources are highly stable, there is a threat of droughts and floods affecting Ecuadorian water reservoirs and producing electrical faults, as highlighted by the 2009 Ecuador electricity crisis. Therefore, predicting the behavior of the hydroelectric system is crucial to develop appropriate planning strategies and a good starting point for energy policy decisions. In this paper, we developed a time series predictive model of hydroelectric power production in Ecuador. To this aim, we used production and precipitation data from 2000 to 2015 and compared the Box-Jenkins (ARIMA) and the Box-Tiao (ARIMAX) regression methods. The results showed that the best model is the ARIMAX (1,1,1) (1,0,0)12, which considers an exogenous variable precipitation in the Napo River basin and can accurately predict monthly production values up to a year in advance. This model can provide valuable insights to Ecuadorian energy managers and policymakers.

show abstract

Section: Box-jenkins and Box-tiao Methodsmentioning

confidence: 99%

“…The mean absolute percentage error (MAPE) is another statistical parameter considered in this study. The advantage of using this parameter is that it uses percentages (%) to show the data, which allows an easy and quick evaluation of the predicted model [30]. The MAPE is described mathematically as follows:…”

Section: Measures Of Accuracymentioning

confidence: 99%

Time Series Analysis for Predicting Hydroelectric Power Production: The Ecuador Case

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The hybrid system composed of KF and MLP attained better results than the ones using ARIMA, MLP, and a combination of ARIMA with KF. Camelo et al [70] proposed a hybrid system that uses multivariate statistical models to predict the linear patterns of the time series. In that paper, Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) and the Holt-Winters model (HW) were combined with an MLP to forecast the wind speed in regions of Brazil.…”

Section: Related Workmentioning

confidence: 99%

“…Such hybrid systems generally employ a linear statistical technique for time series modeling, a nonlinear AI technique to predict the error series, or residuals 1 of the linear model, and the combination of the output of these two models to produce the final forecast [23], [51]. This class of systems has been successfully applied for very short-term (hourly) [12], [64], [69], [70], [76] and monthly (long-term) [3], [16], [65], [70] forecasts.…”

mentioning

confidence: 99%

“…Moreover, the linear model may take into consideration external variables, This unprecedented strategy makes the proposed hybrid system versatile, flexible and efficient. In order to analyse the influence of the exogenous variables [70], ARIMA and ARI-MAX models are employed for time series modeling. For the prediction of the error series, three traditional AI models are employed: MLP, SVR, and RBF.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Nonlinear Combination System for Monthly Wind Speed Forecasting

et al. 2020

View full text Add to dashboard Cite

Wind speed is one of the primary renewable sources for clean power. However, it is intermittent, presents nonlinear patterns, and has nonstationary behavior. Thus, the development of accurate approaches for its forecasting is a challenge in wind power generation engineering. Hybrid systems that combine linear statistical and Artificial Intelligence (AI) forecasters have been highlighted in the literature due to their accuracy. Those systems aim to overcome the limitations of the single linear and AI models. In the literature about wind speed, these hybrid systems combine linear and nonlinear forecasts using a simple sum. However, the most suitable function for combining linear and nonlinear forecasts is unknown and the linear relationship assumption can degenerate or underestimate the performance of the whole system. Thus, properly combining the forecasts of linear and nonlinear models is an open question and its determination is a challenge. This paper proposes a hybrid system for monthly wind speed forecasting that uses a nonlinear combination of the linear and nonlinear models. A data-driven intelligent model is used to search for the most suitable combination, aiming to maximize the performance of the system. An evaluation has been carried out using the monthly data from three wind speed stations in northeast Brazil, evaluated with two traditional metrics. The assessment is performed for two scenarios: with and without exogenous variables. The results show that the proposed hybrid system attains an accuracy superior to other hybrid systems and single linear and AI models.

show abstract

Wind speed prediction for small sample dataset using hybrid first‐order accumulated generating operation‐based double exponential smoothing model

Yousuf

Al‐Bahadly

Avci

2022

Energy Science & Engineering

View full text Add to dashboard Cite

Wind power has proliferated in recent decades. Despite massive disruptions from the global pandemic and the decline in the gross domestic product (GDP) in 2020, wind capacity grew almost double its previous highest annual increase (equivalent to 111 GW). 1 As of the end of the last year, installed wind capacity increased by 17.84% to 733.3 GW, and wind power generation increased by 12% to 1591 TWh. 2 Overall, wind power accounts for 5.93% of global power generation.According to renewable capacity statistics 2021, 1 China, the USA, Germany, and India account for 38.46%, 16.06%, 8.48%, and 5.26% share, respectively. In addition, an impressive increase in new installations is observed for Colombia and Russia, with almost 28 and 9 times more capacity than the previous year. Other notable countries include Sri Lanka (1.96 times), Kazakhstan (1.71 times),

show abstract

Innovative hybrid models for forecasting time series applied in wind generation based on the combination of time series models with artificial neural networks

Cited by 68 publications

References 23 publications

Time Series Analysis for Predicting Hydroelectric Power Production: The Ecuador Case

Time Series Analysis for Predicting Hydroelectric Power Production: The Ecuador Case

A Hybrid Nonlinear Combination System for Monthly Wind Speed Forecasting

Wind speed prediction for small sample dataset using hybrid first‐order accumulated generating operation‐based double exponential smoothing model

Contact Info

Product

Resources

About