Short-term wind speed forecasting based on random forest model combining ensemble empirical mode decomposition and improved harmony search algorithm

ABSTRACT

Wind speed forecasting plays an important role in power grid dispatching management. This article proposes a short-term wind speed forecasting method based on random forest model combining ensemble empirical modal decomposition and improved harmony search algorithm. First, the initial wind speed data set is decomposed into several ensemble empirical mode functions by EEMD, then feature extraction of each sub-modal IMF is performed using fast Fourier transform to solve the cycle of each sub-modal IMF. Next, combining the high-performance parameter optimization ability of the improved harmony search algorithm, two optimal parameters of random forest model, number of decision trees, and number of split features are determined. Finally, the random forest model is used to forecast the processing results of each submodal IMF. The proposed model is applied to the simulation analysis of historical wind data of Chaoyang District, Liaoning Province from April 27, 2015 to May 22, 2015. To illustrate the suitability and superiority of the EEMD-RF-IHS model, three types of models are used for comparison: single models including ANN, SVM, RF; EMD combination models including EMD-ANN, EMD-SVM, EMD-RF; EEMD combination models including EEMD-ANN, EEMD-SVM, EEMD-RF. The analysis results of evaluation indicators show that the proposed model can effectively forecast short-term wind data with high stability and precision, providing a reference for forecasting application in other industry fields.     

A stochastic approach for the operation of a wind and pumped storage plant under a deregulated environment

To improve the competiveness in the energy market, it is necessary that the wind power plants provide guaranteed power generation, although, it is not possible to forecast power availability from wind power plant accurately. This paper presents a stochastic model and solution technique for the combined operation of wind and pumped storage power plants to improve the power availability and increasing the profit considering uncertainties of wind power generation. In this model, uncertainties in wind data have been forecasted for grid connected day-ahead market using Weibull distribution model. The imbalances in the forecasted wind data and the market demand have been reduced by operating the pumped storage power plant. In this stochastic mixed integer problem, pumped storage plant can take the supply either from the grid or from the wind power plant for the pumping operation to store the energy in order to utilize this energy during peak hours for increasing the overall revenue. The reliability of the pumped storage is improved by replacing the conventional unit with the adjustable speed type pumped storage unit. In order to prove the optimality of the solution, two case studies were considered. In case study–I, scheduling is provided by operating the conventional pumped storage unit, whereas in case study–II, adjustable speed pumped storage unit has been used. It has been found that the adjustable speed pumped storage unit has further reduced the imbalance between generated power and demand. The complete approach has been formulated and implemented using AMPL software.     

Prediction of dissolved gases content in power transformer oil using BASA-based mixed kernel RVR model

In this paper, beetle antennae search algorithm-based mixed kernel relevance vector regression (BASA-MkRVR) model is presented and applied to predict the dissolved gases content in power transformer, and beetle antennae search algorithm (BASA) is used to select the appropriate kernel parameters and controlled parameter. The RVR model with RBF kernel (RBFRVR) and the RVR model with Sigmoid kernel (SigmoidRVR) are, respectively, used to compare with the proposed BASA-MkRVR model in order to testify the superiority of BASA-MkRVR compared with RBFRVR and SigmoidRVR. The experimental results indicate that BASA-MkRVR has more excellent prediction ability for the dissolved gases content in power transformer oil than RBFRVR and SigmoidRVR.     

A novel blade design for Savonius wind turbine based on polynomial bezier curves for aerodynamic performance enhancement

ABSTRACT

Advanced wind turbine designs and technologies have been evolved to take advantage of wind energy. Despite the significant progress already attained, the need for a dependable wind energy converter particularly devoted to small-scale applications remains a challenging issue. Due to its design simplicity, Savonius wind turbine is the most suitable candidate for such applications. It operates at low wind speed, with the necessary starting capacity and insensitivity to wind directions. Moreover, in the literature related to wind energy, the Savonius rotor is known for its low performance compared to other types of wind turbines. In this paper, we present a study into the utilization of Bézier curves and transient computational fluid dynamics (CFD) to optimize the conventional Savonius blade design. The k-ω SST turbulence model is employed to perform a series of CFD simulations in order to assess the power coefficient of each generated design. A validation of optimization results using the Taguchi method was carried out. The comparative analysis of the torque and power coefficients shows a significant increase in the power coefficient (C_p). The optimal C_p is 0.35 and is 29% higher than the conventional Savoniu wind turbine (SWT). Subsequently, the effectiveness of the innovative geometry is proved by improved pressure and velocity distributions around blades of novel design.     

GENERATION OF SYNTHETIC AND MISSING CLIMATIC DATA FOR PUERTO RICO1

ABSTRACT: Climatic data such as temperature, solar radiation, relative humidity, and wind speed have been widely used to estimate evapotranspiration. Moat of the solar radiation data and portions of the relative humidity data are either not available or missing from the records in Puerto Rico. Depending upon the availability and data characteristics of records, three methods (including a regression technique, an averaging of historical data, and a regional average) were used to generate missing data, and a time series analysis was used to synthesize a series of climatic data. The limitations and applicability of each method are discussed. The results showed that the time series analysis method can be successfully used to synthesize a series of monthly solar radiations for several stations. The regression technique and the regional average can be successfully applied to generate missing monthly solar radiation data. The regression technique and the averaging of historical data have been satisfactorily used to interpolate missing monthly relative humidity. The explained variance (R²) varied from 0.68 to 0.88, which are both significant at the 0.05 level of significance.     

Performance enhancement of a stand-alone induction generator-based wind energy system using neural network controller

ABSTRACT

The limitation of self-excited induction generator (SEIG) when used in the stand-alone wind energy system (WES) is poor voltage regulation at variable speed. The indirect vector control (IVC) technique is employed for both the generator-side converter (GSC) and load-side converter (LSC) to regulate the variation of SEIG speed, DC link voltage, and electromagnetic torque independently. Further performance of the proposed IVC technique has been analyzed independently with neural network controller (NNC) and fuzzy logic controller (FLC) as its components. The FLC is replaced by an NNC to improve the performance of the proposed system. IVC of SEIG-based WES has been simulated in MATLAB/SIMULINK software, and the prototype model of the proposed WES is developed to experimentally validate the performance using dSPACE DS-1104 R&D controller board.     

Research on Coupling Mechanism of China’s Wind Power Industry Chain

ABSTRACT

Firstly, on the basis of literature research, sort out and summarize the critical coupling relationship among the upstream, middle, and downstream enterprises in the wind power industry chain. Secondly, the evaluation index system of coupling coordination degree of China’s wind power industry chain was established. Based on entropy weight method and subsystem efficiency function, the capacity coupling (CC) coefficient model of wind power industry chain subsystem was established. The coupling coordination degree between the upstream subsystem and the midstream subsystem of the wind power industry chain, and between the midstream subsystem and the downstream subsystem is dynamically evaluated, and the coupling coordination degree evaluation model of the wind power industry chain in China is proposed. Thirdly, according to the relevant statistical data of China from 2010 to 2017, this paper conducts an empirical study on the coupling of the upstream, middle and downstream subsystems of the wind power industry chain. Finally, based on the collaborative coupling study of China’s wind power industry chain, this paper analyzes the key factors influencing the collaborative development of wind power industry chain, and puts forward Suggestions on the optimization of the collaborative development of China’s wind power industry chain.     

An Analysis of the Wind Energy Potential of Elazig,Turkey

Abstract

In this study, the wind energy potential of Elazig is statistically analyzed based on hourly measured wind speed data over the five-year period from 1998 to 2002. The probability density distributions are derived from cumulative distribution functions. Two probability density functions are fitted to the measured probability distribution on a yearly basis. The wind energy potential of the location is studied based on the Weibull and Rayleigh distributions. It was found that the numerical values of both Weibull parameters (k and c) for Elazig vary over a wide range. The yearly values of k range from 1.653 to 1.878 with an average value of 1.819, while those of c are in the range of 2.757–2.994 m/s with an average value of 2.824 m/s. In addition, yearly mean wind speed and mean power density of Elazig is found as 2.79 m/s and 38.76 W/m², respectively. The wind speed distributions are represented by Weibull distribution and also by Rayleigh distribution, with a special case of the Weibull distribution for k = 2. As a result, the Rayleigh distribution is found to be suitable to represent the actual probability of wind speed data for Elazig.     

Wind power potential assessment for three buoys data collection stations in the Ionian Sea using Weibull distribution function

The present article utilizes wind measurements from three buoys data collection stations in Ionian Sea to study the wind speed and power characteristics using the Weibull shape and scale parameters. Specifically, the site dependent, annual, and monthly mean patterns of mean wind speed, Weibull parameters, frequency distribution, most probable wind speed, maximum energy carrying wind speed, wind power density and wind energy density characteristics have been analyzed. The Weibull distribution was found to represent the wind speed distribution with more than 90% accuracy, in most of the cases. Moreover, the correlation between the percentages of times the wind speed was above cut-in-speed and the measured mean wind speed for the three selected sites, as the correlation between the aforementioned percentages and the scale parameter c were examined and were found linear. At all these sites, no definite increasing or decreasing trends in annual mean wind speed values could be detective over the data reporting period. The mean values of wind speed, scale parameter, most probable wind speed, maximum energy carrying wind speed, wind power and wind energy density values showed higher values during winter time and lower in summer time in Pylos and Zakynthos. Moreover, Pylos and Zakynthos were found to be the best sites from wind power harnessing point of view.     

Chlorophyll a Simulation in a Lake Ecosystem Using a Model with Wavelet Analysis and Artificial Neural Network

Accurate and reliable forecasting is important for the sustainable management of ecosystems. Chlorophyll a (Chl a) simulation and forecasting can provide early warning information and enable managers to make appropriate decisions for protecting lake ecosystems. In this study, we proposed a method for Chl a simulation in a lake that coupled the wavelet analysis and the artificial neural networks (WA–ANN). The proposed method had the advantage of data preprocessing, which reduced noise and managed nonstationary data. Fourteen variables were included in the developed and validated model, relating to hydrologic, ecological and meteorologic time series data from January 2000 to December 2009 at the Lake Baiyangdian study area, North China. The performance of the proposed WA–ANN model for monthly Chl a simulation in the lake ecosystem was compared with a multiple stepwise linear regression (MSLR) model, an autoregressive integrated moving average (ARIMA) model and a regular ANN model. The results showed that the WA-ANN model was suitable for Chl a simulation providing a more accurate performance than the MSLR, ARIMA, and ANN models. We recommend that the proposed method be widely applied to further facilitate the development and implementation of lake ecosystem management.     

A hybrid model based on smooth transition periodic autoregressive and Elman artificial neural network for wind speed forecasting of the Hebei region in China

Wind energy, one of the most promising renewable and clean energy sources, is becoming increasingly significant for sustainable energy development and environmental protection. Given the relationship between wind power and wind speed, precise prediction of wind speed for wind energy estimation and wind power generation is important. For proper and efficient evaluation of wind speed, a smooth transition periodic autoregressive (STPAR) model is developed to predict the six-hourly wind speeds. In addition, the Elman artificial neural network (EANN)-based error correction technique has also been integrated into the new STPAR model to improve model performance. To verify the developed approach, the six-hourly wind speed series during the period of 2000–2009 in the Hebei region of China is used for model construction and model testing. The proposed EANN-STPAR hybrid model has demonstrated its powerful forecasting capacity for wind speed series with complicated characteristics of linearity, seasonality and nonlinearity, which indicates that the proposed hybrid model is notably efficient and practical for wind speed forecasting, especially for the Hebei wind farms of China.     

Optimization of a Wind/PV Hybrid Power Generation System

This study investigates the wind and solar electricity generation availability at the Solar Energy Institute of Ege University, Izmir, Turkey. The main purpose of this study is to design an appropriate wind-PV hybrid system to cover the electricity consumption of the Institute. In order to do this, monthly average solar irradiation and wind speed data are used, which were measured, consisting of hourly records over an eight-year period from 1995–2002. Simple models were developed to determine wind, solar, and hybrid power resources per unit area. Correlations between the solar and wind power data were carried out on an hourly, daily, and monthly basis. It is shown that the hybrid system can be applied for the efficient and economic utilization of these resources.     

Blade thickness effect on the aerodynamic performance of an asymmetric NACA six series blade vertical axis wind turbine in low wind speed

ABSTRACT

Vertical axis wind turbine (VAWT) is an economic and widely used energy converter for converting wind energy into useful form of energy, like mechanical and electrical energy. For efficient energy conversion in low wind speed and to have improved power coefficient of asymmetric blade VAWT, selection of optimum blade thickness is needed thus entailing its detailed investigation with respect to different operating wind speed conditions. Present study methodically explores the impact of thickness to chord (t/c) ratio on aerodynamic performance of a three bladed asymmetrical blade H-Darrieus VAWT at different low wind speed conditions by using 2D unsteady CFD simulations. The optimal t/c is obtained on the basis of maximum power coefficient and average moment coefficient of the turbine. The aerodynamic performance curves are obtained at different operating and t/c conditions and the performance insights are corroborated with the findings from the flow physics study to come to some concrete conclusions on the effects of the thickness to chord ratio. The present study identifies large blade curvature to create a large diverging passage on the blade suction surface as the prominent reason for aerodynamic performance drop at a high t/c ratio.     

Predicting Carbon Monoxide Concentrations in the Air of Pardis City,Iran, Using an Artificial Neural Network

To date, several methods have been proposed to explain the complex process of air pollution prediction. One of these methods uses neural networks. Artificial neural networks (ANN) are a branch of artificial intelligence, and because of their nonlinear mathematical structures and ability to provide acceptable forecasts, they have gained popularity among researchers. The goal of our study as documented in this article was to compare the abilities of two different ANNs, the multilayer perceptron (MLP) and radial basis function (RBF) neural networks, to predict carbon monoxide (CO) concentrations in the air of Pardis City, Iran. For the study, we used data collected hourly on temperature, wind speed, and humidity as inputs to train the networks. The MLP neural network had two hidden layers that contained 13 neurons in the first layer and 25 neurons in the second layer and reached a mean bias error (MBE) of 0.06. The coefficient of determination (R²), index of agreement (IA), and the Nash–Scutcliffe efficiency (E) between the observed and predicted data using the MLP neural network were 0.96, 0.9057, and 0.957, respectively. The RBF neural network with a hidden layer containing 130 neurons reached an MBE of 0.04. The R², IA, and E between the observed and predicted data using the RBF neural network were 0.981, 0.954, and 0.979, respectively. The results provided by the RBF neural network had greater acceptable accuracy than was the case with the MLP neural network. Finally, the results of a sensitivity analysis using the MLP neural network indicated that temperature is the primary factor in the prediction of CO concentrations and that wind speed and humidity are factors of second and third importance when forecasting CO levels.     

LAKE SHORE PROTECTION AGAINST WIND-GENERATED WAVES1

ABSTRACT: A method is reported for estimating the height of wind waves in any lake for a given wind condition. Maximum wind speeds from five climatological stations in and around Ilinois for the period of 1950–1972 were analyzed and the maximum wind speed for various durations and return periods were presented. Statistical analysis of wind wave data collected from Carlyle Lake indicated the Rayleigh distribution fitted the wave height distribution reasonably well and that the nondimensional energy spectra followed the (f/f_m)^-5 rule in the equilibrium range of frequencies. From a consideration of various forces and physical properties of riprap particles and water, a relationship was developed to estimate the stable weight of riprap particles. A practical design criteria is proposed to stabilize lake shores against wind waves.     

The effects of sinusoidal leading edge of turbine blades on the power coefficient of horizontal-axis wind turbine (HAWT)

In order to improve the aerodynamic performance of horizontal-axis wind turbine (HAWT), a sinusoidal shape is applied to turbine blade. In this study, four types of modified blades were chosen based on variations in amplitude and wavelength of protuberance along the leading edge. Compared with the baseline model, the power coefficients (C_p) of HAWT with modified blades were improved, especially at low tip speed ratios. At low wind speed (V = 6 m/s), blades with short wavelength obtain significant improvement in C_p compared with the baseline model. As wind speed increases, this improvement decreases. In addition, turbine blade with large amplitude and long wavelength obtains better C_p values at higher wind speeds than lower ones, which have a great potential to be more superior at relatively higher wind speeds.     

Location wise comparison of mixture distributions for assessment of wind power potential: A parametric study

Scientific literature discussed various types of mixture models and models derived from maximum entropy principle using short-term wind speed data for their relative assessment. The literature on suitability of these mixture models for long-term data is rarely available. However, for correct assessment of wind power potential both wind speed and wind direction are equally important. Therefore, in this paper, both wind speed and wind direction are simultaneously analyzed using several types of mixture distribution and compared the same with conventional Weibull distribution. For wind speed and wind power density assessment, the mixture distributions such as Weibull--Weibull distribution, Gamma--Weibull distribution, Truncated Normal--Weibull distribution, Truncated Normal--Normal distribution, proposed Truncated Normal--Gamma distribution and Gamma--Gamma distribution along with MEP-distribution are compared with conventional 2-parameter Weibull distribution. Similarly, for wind direction analysis, the finite mixtures of von-Mises distribution are compared with conventional von-Mises distribution. Judgment criteria include R², RMSE, Kolmogorov--Smirnov test and relative percentage error in wind power density. The sites selected are the three onshore locations of India, viz., Calcutta, Trivandrum, and Ahmedabad. The results show that for wind speed assessment, mixture distribution performs better than the conventional Weibull distribution for analyzing wind power density. However, location wise comparison of all mixture distribution is of prime importance. For wind direction analysis, finite mixture of two von-Mises distributions proved to be a suitable candidate for Indian climatology.     

Economic and employment impacts of offshore wind for Ireland: A value chain analysis

ABSTRACT

The imminent development of a number of offshore wind farms in the Republic of Ireland presents a sizable opportunity to stimulate the Irish economy through the growth of an indigenous and globally competitive offshore wind supply chain. This study uses a value chain analysis to evaluate the economic and employment potential of the offshore wind sector for Ireland. The analysis is based on the expenditure on products and services required to develop an offshore wind farm, the planned capacity of projects in the pipeline, and the ability of Irish companies to supply the sector. Results suggest that by 2030, 2.5–4.5GW of domestic offshore wind development could create between 11,424 and 20,563 supply chain jobs and generate between €763 m and €1.4bn in gross value added. This is the first study to estimate domestic GVA potential for the sector.     

Streamflow Forecasting Using Singular Value Decomposition and Support Vector Machine for the Upper Rio Grande River Basin

The current study improves streamflow forecast lead‐time by coupling climate information in a data‐driven modeling framework. The spatial–temporal correlation between streamflow and oceanic–atmospheric variability represented by sea surface temperature (SST), 500‐mbar geopotential height (Z₅₀₀), 500‐mbar specific humidity (SH₅₀₀), and 500‐mbar east–west wind (U₅₀₀) of the Pacific and the Atlantic Ocean is obtained through singular value decomposition (SVD). SVD significant regions are weighted using a nonparametric method and utilized as input in a support vector machine (SVM) framework. The Upper Rio Grande River Basin (URGRB) is selected to test the applicability of the proposed model for the period of 1965–2014. The April–August streamflow volume is forecasted using previous year climate variability, creating a lagged relationship of 1–13 months. SVD results showed the streamflow variability was better explained by SST and U₅₀₀ as compared to Z₅₀₀ and SH₅₀₀. The SVM model showed satisfactory forecasting ability with best results achieved using a one‐month lead to forecast the following four‐month period. Overall, the SVM results showed excellent predictive ability with average correlation coefficient of 0.89 and Nash–Sutcliffe efficiency of 0.79. This study contributes toward identifying new SVD significant regions and improving streamflow forecast lead‐time of the URGRB.     

Numerical modeling and optimization of a power augmented S-type vertical axis wind turbine

An axial symmetry augmented vertical axis wind turbine, which is suitable for arbitrary wind directions, is proposed in this paper. In order to improve the power generation ability of the S-type vertical axis wind turbine, a set of so-called “collection-shield boards” are installed symmetrically around the rotating S-type rotor. The flow fields around this type of wind turbine are numerically simulated with the aid of CFD method. The optimized design of geometrical parameters of the rotor and collection-shield boards is conducted by using the orthogonal design method. The obtained results suggest that the power output of the optimized augmented wind turbine can reach nearly three times higher than that of the conventional S-type vertical axis wind turbine.