Multistep short-term wind speed prediction using nonlinear auto-regressive neural network with exogenous variable selection

Noman, Fuad; Alkawsi, Gamal; Alkahtani, Ammar Ahmed; Al-Shetwi, Ali Q.; Tiong, Sieh Kiong; Alalwan, Nasser; Ekanayake, Janaka; Alzahrani, Ahmed Ibrahim

doi:10.1016/j.aej.2020.10.045

Cited by 34 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third and last scenario is designed to show the performance of the optimizing ensemble-based AD-PSO-Guided WOA algorithm compared with PSO [18], WOA [22], GA [23], GWO [19], HHO [25], [26], MPA [27], ChOA [28], and SMA [29]. The AD-PSO-Guided WOA algorithm ensemble model is also compared with four deep learning techniques including TDNN [30], DNN [31], SAE [32], and BRNN [33].…”

Section: Comparisons Scenariomentioning

confidence: 99%

“…The AD-PSO-Guided WOA algorithm ensemble model is compared with the state-of-the-art optimization techniques including PSO [18],WOA [22], GA [23], GWO [19], Harris Hawks Optimization (HHO) [25], [26], Marine Predators Algorithm (MPA) [27], Chimp Optimization Algorithm (ChOA) [28], and Slime Mould Algorithm (SMA) [29]. The AD-PSO-Guided WOA algorithm ensemble model is also compared with the state-of-the-art deep learning techniques including Time delay neural network (TDNN) [30], Deep Neural Networks (DNN) [31], Stacked Denoising Autoencoder (SAE) [32], and Bidirectional Recurrent Neural Networks (BRNN) [33]. The statistical analysis of different tests is performed to confirm the accuracy of the algorithm, including Wilcoxon's rank-sum and one-way analysis of variance (ANOVA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wind Speed Ensemble Forecasting Based on Deep Learning Using Adaptive Dynamic Optimization Algorithm

et al. 2021

View full text Add to dashboard Cite

The development and deployment of an effective wind speed forecasting technology can improve the stability and safety of power systems with significant wind penetration. However, due to the wind's unpredictable and unstable qualities, accurate forecasting of wind speed and power is extremely challenging. Several algorithms were proposed for this purpose to improve the level of forecasting reliability. A common method for making predictions based on time series data is the long short-term memory (LSTM) network. This paper proposed a machine learning algorithm, called adaptive dynamic particle swarm algorithm (AD-PSO) combined with guided whale optimization algorithm (Guided WOA), for wind speed ensemble forecasting. The proposed AD-PSO-Guided WOA algorithm selects the optimal hyperparameters value of the LSTM deep learning model for forecasting purposes of wind speed. In experiments, a wind power forecasting dataset is employed to predict hourly power generation up to forty-eight hours ahead at seven wind farms. This case study is taken from the Kaggle Global Energy Forecasting Competition 2012 in wind forecasting. The results demonstrated that the AD-PSO-Guided WOA algorithm provides high accuracy and outperforms a number of comparative optimization and deep learning algorithms. Different tests' statistical analysis, including Wilcoxon's rank-sum and one-way analysis of variance (ANOVA), confirms the accuracy of proposed algorithm.

show abstract

Section: Comparisons Scenariomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Wind Speed Ensemble Forecasting Based on Deep Learning Using Adaptive Dynamic Optimization Algorithm

et al. 2021

View full text Add to dashboard Cite

show abstract

“…More operations are required with few algorithms employed 28–40 Premature and delayed convergence due to the global stuck of the algorithms 64–67 Loss of information and henceforth lacks in prediction accuracy 14,23,24,49 …”

Section: Introductionmentioning

confidence: 99%

“…[24][25][26] • Difficult to maintain the stability of the algorithms. [61][62][63][64][65] • More operations are required with few algorithms employed. [28][29][30][31][32][33][34][35][36][37][38][39][40] • Premature and delayed convergence due to the global stuck of the algorithms.…”

mentioning

confidence: 99%

Multi‐step wind speed and wind power forecasting using variational momentum factor and deep learning based intelligent neural network models

Nachimuthu

Banerjee

Karuppaiah

2021

Concurrency and Computation

View full text Add to dashboard Cite

Deep learning based novel intelligent neural network models are developed in this research study and employed for performing multi‐step wind speed and wind power forecasting for the data pertaining to certain wind farms. It has always been tedious to predict wind speed and wind power accurately due the existence of non‐linearity in the wind farm data and as well previous traditional and heuristic techniques has their own merits and demerits in performing the prediction process. This research study intends to handle the prevailing non‐linearity of the wind farm data and as well perform prediction of the parameters in a better manner with increased accuracy rate. The prediction study facilitates the renewable energy community to install the wind mills in the locations with higher accuracy rate and thereby power production gets increased extravagantly. The intelligent neural network developed in this article includes the ELMAN and spiking neuronal models with incorporated deep learning procedure and varying momentum factor criterion to achieve minimal error and better accuracy rate. Multi‐step forecasting is carried for 10‐min ahead and the numerical simulation executed with the proposed intelligent non‐linear forecasting techniques. The attained results confirm the superiority of the developed models over other techniques from previous works.

show abstract

“…A major research line has been dedicated to time series analysis. In this line, exponential smoothing models (Gardner Jr and Everette, 2006;Bergmeir et al, 2016), Box and Jenkins models (Box et al, 2015) and nonlinear autoregressive neural networks (Yu et al, 2014;Wang et al, 2019;Noman et al, 2020) are essentially devoted to forecasting. In addition to the forecasting goal, regime-switching autoregressive models (Ubilava and Helmers, 2013;Hamilton, 1990) also allow to discover hidden behaviors of such systems.…”

Section: Introductionmentioning

confidence: 99%

Partially Hidden Markov Chain Linear Autoregressive model: inference and forecasting

Dama¹,

Sinoquet²

2021

Preprint

View full text Add to dashboard Cite

Time series subject to change in regime have attracted much interest in domains such as econometry, finance or meteorology. For discrete-valued regimes, some models such as the popular Hidden Markov Chain (HMC) describe time series whose state process is unknown at all time-steps. Sometimes, time series are firstly labelled thanks to some annotation function. Thus, another category of models handles the case with regimes observed at all time-steps. We present a novel model which addresses the intermediate case: (i) state processes associated to such time series are modelled by Partially Hidden Markov Chains (PHMCs); (ii) a linear autoregressive (LAR) model drives the dynamics of the time series, within each regime. We describe a variant of the expection maximization (EM) algorithm devoted to PHMC-LAR model learning. We propose a hidden state inference procedure and a forecasting function that take into account the observed states when existing. We assess inference and prediction performances, and analyze EM convergence times for the new model, using simulated data. We show the benefits of using partially observed states to decrease EM convergence times. A fully labelled scheme with unreliable labels also speeds up EM. This offers promising prospects to enhance PHMC-LAR model selection. We also point out the robustness of PHMC-LAR to labelling errors in inference task, when large training datasets and moderate labelling error rates are considered. Finally, we highlight the remarkable robustness to error labelling in the prediction task, over the whole range of error rates.

show abstract

Multistep short-term wind speed prediction using nonlinear auto-regressive neural network with exogenous variable selection

Cited by 34 publications

References 26 publications

Wind Speed Ensemble Forecasting Based on Deep Learning Using Adaptive Dynamic Optimization Algorithm

Wind Speed Ensemble Forecasting Based on Deep Learning Using Adaptive Dynamic Optimization Algorithm

Multi‐step wind speed and wind power forecasting using variational momentum factor and deep learning based intelligent neural network models

Partially Hidden Markov Chain Linear Autoregressive model: inference and forecasting

Contact Info

Product

Resources

About