Wind power prediction using a three stage genetic ensemble and auxiliary predictor
Introduction
Alternate energy sources is a hot area of research today as the world is facing energy crises and shortfalls due to diminishing conventional fossil fuel sources for power production. This shift to new energy resources for power generation has led to various avenues of research including exploration of novel methodologies for estimating power production. Recently, with increasing usage of wind power plants worldwide, accurate and reliable power prediction is a challenging task. Wind power prediction (WPP) is based on different time horizons which categorize into very-short-term, short-term, medium-term and long-term predictions. Different researchers describe the time frame in various ways including time range and application perspective [1], [2].
Scientific literature presents various statistical and physical (deterministic) models for forecasting wind power, for instance, one can refer to statistical approaches [3], [4] for power prediction exploiting the relationship between wind power and the variables effecting its generation using historical data logs without using meteorological variables. In statistical approaches, artificial neural networks (ANNs) and neuro-fuzzy networks have been frequently implemented [5]. Physical or deterministic models entirely depend upon numerical weather predictions having many features, such as atmospheric behavior, surface conditions, terrain orography, climate of the site, etc., essentially collecting wind speed from meteorological service centers of the region under consideration and converting to wind power [6], [7]. Niya et al. describe regression and time series based model for prediction of short term wind speed by utilizing statistical method based on wavelet and Gaussian processes [8]. The combination of statistical and deterministic modeled is termed as hybrid models, which effectively deal with the time series based problems. Stathopoulos, C. et al. proposed a hybrid model which takes input as meteorological forecasts for different prediction perspectives [9]. Peng et al. proposed a hybrid strategy involving the integration of physical method and ANN technique [10]. This technique calculates the wind speed and direction at each wind turbine hub height and to predict the power for each turbine, which is used to synthesize the wind power of whole wind farm. Peiyuan et al. suggested autoregressive integrated moving average (ARIMA) model which uses few parameters for the generation of nonstationary characteristic of the wind [11]. Billinton et al. presented a basic AR(24) model, that subsequently predicted equally the hourly wind speed and direction [12]. Jiang et al. reported two hybrid-forecasting models, namely, autoregressive integrated moving average with ANNs (ARIMA-ANN) and with support vector machine (ARIMA-SVM). These models employ an ARIMA model for the linear characteristics and an artificial neural network (ANN) or SVM to cater nonlinear characteristics [13].
Exploitation of computational intelligence algorithms for power prediction has been reported in the recent past and is still in continuous exploration and implementation phase. Wind energy production is a challenging task due to nature of complexity and nonlinearity inherently involved in the wind energy [14], [15]. Various machine learning algorithms such as support vector machine are used for better generalization by using characteristics of structural risk minimization [16]. Najeebullah et al. [17] proposed support vector regression (SVR) along with ANN to provide better performance. However, Mohandas et al. illustrated the comparison based on SVM and multilayer perceptron (MLP) where MLP employs the empirical risk minimization to decrease the error on training data [18]. De Giorgi et al. [19] used hybrid technique of least-squares support vector machines (LS-SVM) and ANN for higher accuracy and to avoid over fitting. Ahmed et al. suggested the solution based on feed forward ANN to identify the model that provides prediction of average daily production of electricity from the wind [20]. Ren et al. presented a very interesting work in this context [21]. They employed nearest neighbor search and ANN for developing a short-term wind power prediction model. Hourly wind power predictions are possible using this technique. Work published by Grassi et al. is an important scientific contribution for long-term wind power prediction [22]. Their idea is to use two hidden layer neural network for predictions on a monthly basis. Another hybrid neural networks is introduced by Amjady [23]. In this approach ARIMA is replaced by RBF and combined with MLP that helps to explore the local and global characteristics of input data. Zameer et al. presented GP based ensemble of ANNs for short term power forecast [24]. Asifullah Khan et al. suggested deep belief network (DBN) which show characteristics of stochastic feature generation and produced unsupervised pre-training for good generalization [25]. Qureshi et al. used ensemble of deep learning in which auto-encoder employs as base-regressor and DBN as meta-regressor for robust forecasting of wind power [26].
We propose auxiliary predictor (AxP) composed of relevant vector machine (RVM) and radial basis function (RBFNN) based ensemble of GP with ANNs, AxP-GPNN. Here, mutual information (MI) based feature reduction is carried out and back propagation ANNs are used as base predictors and selected feature data is provided to GP for final predictions. Salient features of our presented work are the following:
- •
A three stage learning mechanism of prediction is proposed to reduce variations in the predicted wind power and hence minimization of prediction error.
- •
Exploration of learning abilities of GP based meta learner to utilize prediction spaces of both 1st stage (auxiliary learner) and 2nd stage (base learner) simultaneously.
- •
Reducing the variations in prediction of the 2nd stage (base learner) through 1st stage (auxiliary learners).
- •
RVM overcomes the over fitting issues in the training phase and improves the generalization on unseen data.
- •
AxP provides initial decision space to base learners and GP.
- •
We experimentally show the reduction in prediction variation bottom-up in the multistage and ensemble learning mechanism.
- •
Better performance of the proposed algorithm in terms of statistical performance indices, such as MAE, SDE and RMSE is evaluated for accurate wind power prediction.
Rest of the paper is organized as follows: Section 2 describes windmills datasets and proposed methodology consisting of auxiliary and ANN predictors and GP based predictions. Experimental results and discussion are provided in Section 3 along with result comparison, while Section 4 deals with the conclusions drawn on the basis of results achieved.
Section snippets
Wind power dataset
The dataset used for wind power prediction has been taken from five wind farms situated in similar climatological Europe regions. This three-year data includes measured values of wind power and meteorological predictions for its components. Measured power available from all wind farms has temporal sequential data on hourly scale. Here, power values have been normalized between 0-1 to avoid any scaling issue for the sake of comparison and to mask the physiognomies of different wind farms.
Experimental results and discussion
Initially, raw data is preprocessed, which contains 124 features. Feature reduction is carried out through irrelevancy and redundancy filters and on the basis of MI indices leaving behind five highly relevant features only. Seventy percent (70%) of the processed data with reduced features is passed to NN and auxiliary blocks for training and thirty percent (30%) for testing, which is then fed to GP block along with initial processed data. In GP, data is divided into 66.66% for GP training and
Conclusion
GP based ensemble of auxiliary predictor and NN is reported for wind power forecast of five wind farms in similar meteorological regions of Europe. Effectiveness, reliability and robustness of the proposed hybrid approach have been accessed through statistical indices in terms of MAE, RMSE and SDE. Furthermore, these results have been compared with the actual power measurements as well as reported results in the literature for short time predictions. Comparison reveals improved predictions by
CRediT authorship contribution statement
Farah Shahid: Validation, Investigation, Methodology. Asifullah Khan: Conceptualization, Methodology. Aneela Zameer: Writing - original draft, Validation, Writing - review & editing. Junaid Arshad: Software, Data curation. Kamran Safdar: Visualization.
Declaration of Competing Interest
No author associated with this paper has disclosed any potential or pertinent conflicts which may be perceived to have impending conflict with this work. For full disclosure statements refer to https://doi.org/10.1016/j.asoc.2020.106151.
References (48)
- et al.
Evaluation of hybrid forecasting approaches for wind speed and power generation time series
Renew. Sustain. Energy Rev.
(2012) Wind power prediction based on numerical and statistical models
J. Wind Eng. Ind. Aerodyn.
(2013)- et al.
A hybrid strategy of short term wind power prediction
Renew. Energy
(2013) - et al.
Time-series models for reliability evaluation of power systems including wind energy
Microelectron. Reliab.
(1996) - et al.
Short-term wind speed forecasting using a hybrid model
Energy
(2017) Support vector machines for wind speed prediction
Renew. Energy
(2004)- et al.
Wind energy prediction using a two-hidden layer neural network
Commun. Nonlinear Sci. Numer. Simul.
(2010) Wind power prediction using deep neural network based meta regression and transfer learning
Appl. Soft Comput.
(2017)- et al.
On comparing three artificial neural networks for wind speed forecasting
Appl. Energy
(2010) Optimal algorithms and the BFGS updating techniques for solving unconstrained nonlinear minimization problems
J. Appl. Math.
(2014)
On the training of radial basis function classifiers
Neural Netw.
Application of the relevance vector machine to canal flow prediction in the Sevier River Basin
Agric. Water Manag.
Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine
Renew. Sustain. Energy Rev.
Review of evaluation criteria and main methods of wind power forecasting
A Review of Wind Power Forecasting Models
On Error Measures in Wind Forecasting Evaluations
A recent survey on the applications of genetic programming in image processing
Short-term prediction of wind power using a hybrid pseudo-inverse Legendre neural network and adaptive firefly algorithm
Neural Comput. Appl.
Multistep Wind Speed Forecasting Based on Wavelet and Gaussian Processes
ARIMA-Based Time Series Model of Stochastic Wind Power Generation
Machine learning for energy-water nexus: challenges and opportunities
Big Earth Data
A comparative analysis of ANN and chaotic approach-based wind speed prediction in India
Performance evaluation of short term wind speed prediction techniques
IJCSNS Int. J. Comput. Sci. Netw. Secur.
Cited by (35)
Ultra-short-term wind power probabilistic forecasting based on an evolutionary non-crossing multi-output quantile regression deep neural network
2024, Energy Conversion and ManagementUltra-short-term probabilistic wind power forecasting with spatial-temporal multi-scale features and K-FSDW based weight
2023, Applied EnergyCitation Excerpt :Being the biggest developing country in the world, China will increase its national independent contribution, adopt more effective policies and measures. Reducing coal consumption in the power industry is indeed an effective means to reduce CO2 emissions [1], therefore, the confidence to achieve the double carbon goal come not only from the realities we see, but also from the data that China’s wind power installed capacity ranks first in the world for 10 consecutive years behind these realities. However, the endogenous random fluctuations and uncertainties involved have always posed serious risks to the power system [2].
A hybrid attention-based deep learning approach for wind power prediction
2022, Applied Energy