Wind power forecasting based on new hybrid model with TCN residual modification

Wind energy has been widely utilized to alleviate the shortage of fossil resources.When wind power is integrated into the power grid on a large scale,the power grid’s stability is severely harmed due to the fluctuating and intermittent properties of wind speed.Accurate wind power forecasts help to formulate good operational strategies for wind farms.A short-term wind power forecasting method based on new hybrid model is proposed to increase the accuracy of wind power forecast.Firstly,wind power time series are separated using the complete ensemble empirical mode decomposition with adaptive noise method to obtain multiple components,which are then predicted using a support vector regression machine model optimized through using the grid search and cross validation(GridSearchCV)algorithm.Secondly,a residual modification model based on temporal convolutional network is constructed,and variables with high correlation are selected as the input features of the model to predict the residuals of wind power.Finally,the prediction accuracy of the proposed method is compared to other models using the actual wind power data of the wind farm to demonstrate the validity of the described method,and the results reveal that the proposed method has better prediction performance.

Preparation of Bio-polyols by Liquefaction of Hardwood Residue and Their Application in the Modification of Polyurethane Foams

Hardwood residue（HR）,a byproduct of paper industry,was liquefied by using polyethylene glycol 400（PEG400） and ethylene carbonate（EC） as the liquefaction solvents,and concentrated sulfuric acid as the catalyst to produce bio-polyols（HRLP）,which were used to synthesize polyurethane（PU） foams.The effects of conditions on the properties of HRLP and modified PU foams were investigated and the mechanism of biomass liquefaction was discussed.The optimum conditions of liquefaction were obtained as follows： reaction temperature of 160 °C,reaction time of 60 min,ratio of PEG400/EC of 8：2（w/w）,and ratio of liquid/solid of 5：1（w/w）.The characterization of HRLP modified PU foams suggested that HRLP could partially replace the petroleum polyols to synthesize PU foams.With the increase of the replacement percentage of HRLP,the apparent density and compressive strength of the foams increased firstly,and then decreased.Meanwhile,the thermal stability was improved slightly.

Analyzing China’s OFDI using a novel multivariate grey prediction model with Fourier series

Purpose–With the development of economy,China’s OFDI constantly increase in recent year.Meanwhile,OFDI hasspillovereffectoneconomicdevelopmentandtechnologicaldevelopmentofhomecountry.Thus,accurateOFDI prediction is a prerequisite for the effective development of international investment strategies.The purpose of this paper is to predict China’s OFDI accurately using a novel multivariable grey prediction model with Fourier series.Design/methodology/approach–This paper applied a multivariable grey prediction model,GM(1,N),to forecast China’s OFDI.In order to improve the prediction accuracy and without changing local characteristics of grey model prediction,this paper proposed a novel grey prediction model to improve the performance of the traditionalGM(1,N)modelbycombiningwithresidualmodificationmodelusingGM(1,1)modelandFourierseries.Findings–The coefficients indicate that the export and GDP have positive influence on China’s OFDI,and,according to the prediction result,China’s OFDI shows a growing trend in next five years.Originality/value–This paper proposed an effective multivariable grey prediction model that combined the traditionalGM(1,N)modelwitharesidualmodificationmodelinordertopredictChina’sOFDI.Accurateforecasting of OFDI provides reference for the Chinese Government to implement international investment strategies.

Removal of polycyclic aromatic hydrocarbons from aqueous solution by raw and modified plant residue materials as biosorbents

Removal of polycyclic aromatic hydrocarbons （PAHs）, e.g., naphthalene, acenaphthene, phenanthrene and pyrene, from aqueous solution by raw and modified plant residues was investigated to develop low cost biosorbents for organic pollutant abatement. Bamboo wood, pine wood, pine needles and pine bark were selected as plant residues, and acid hydrolysis was used as an easily modification method. The raw and modified biosorbents were characterized by elemental analysis, Fourier transform infrared spectroscopy and scanning electron microscopy. The sorption isotherms of PAHs to raw biosorbents were apparently linear, and were dominated by a partitioning process. In comparison, the isotherms of the hydrolyzed biosorbents displayed nonlinearity, which was controlled by partitioning and the specific interaction mechanism. The sorpfion kinetic curves of PAHs to the raw and modified plant residues fit well with the pseudo second-order kinetics model. The sorption rates were faster for the raw biosorbents than the corresponding hydrolyzed biosorbents, which was attributed to the latter having more condensed domains （i.e., exposed aromatic core）. By the consumption of the amorphous cellulose component under acid hydrolysis, the sorption capability of the hydrolyzed biosorbents was notably enhanced, i.e., 6-18 fold for phenanthrene, 6-8 fold for naphthalene and pyrene and 5-8 fold for acenaphthene. The sorpfion coefficients （Kd） were negatively correlated with the polarity index [（O＋N）/C], and positively correlated with the aromaticity of the biosorbents. For a given biosorbent, a positive linear correlation between logKoc and logKow for different PAHs was observed. Interestingly, the linear plots of logKoc-logKow were parallel for different biosorbents. These observations suggest that the raw and modified plant residues have great potential as biosorbents to remove PAHs from wastewater.