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.     

The hybrid model of empirical wavelet transform and relevance vector regression for monthly wind speed prediction

ABSTRACT

In order to improve the prediction ability for the monthly wind speed of RVR, the hybrid model of empirical wavelet transform and relevance vector regression (EWT-RVR) is proposed for monthly wind speed prediction in this study. Compared with empirical mode decomposition (EMD), empirical wavelet transform (EWT) can obtain a more consistent decomposition and have a mathematical theory. In order to testify the superiority of EWT-RVR, several traditional RVR models are used to compare with the proposed EWT-RVR method under the situation of the same embedding dimensions. The experimental results show that the proposed EWT-RVR method has a better prediction ability for monthly wind speed than RVR. It can be concluded that the proposed EWT-RVR method for monthly wind speed is effective.     

Catalytic decomposition of hydrocarbon into hydrogen and carbon in a spouted-bed reactor as the second-stage reactor of a plastic recycling process

A two-stage process for the chemical recycling of plastics is proposed. In this process, which consists of two reactors, plastics are converted into hydrogen and carbon. In the first reactor, plastic chips are thermally decomposed into hydrocarbons. In the second reactor, the hydrocarbons formed in the first reactor are catalytically decomposed into carbon and hydrogen. In this study, in order to obtain basic data for the second reactor, propene was catalytically decomposed in a laboratory-scale spouted-bed reactor (600mm high, 21.6mm internal diameter, made of SUS304). The effect of the type of spouting medium used on the decomposition behavior of propene was investigated using four types of spouting medium (nickel-plated -alumina, palladium-plated -alumina, nickel-impregnated -alumina, and -alumina). The nickel-impregnated -alumina gave the best propene conversion and hydrogen yield.     

Lowest Effect Levels of Lead and Mercury on Decomposition of Mor Layer Samples in a Long-Term Experiment

Indications of possible negative effects of lead (Pb) and mercury(Hg) on microbial respiration in Southern Swedish forest humus layers led to experiments on dose-response relationships by additions of metal salts in the laboratory. Respiration rates andweight loss due to decomposition of organic material were measured. For relevance to field situations metal doses were low,the time span was long, 550 days including freeze storage, and microbial activity was kept up by plant litter additions. We looked for effects of Pb and Hg at levels moderately elevated above the Southern Swedish reference, as well as combined effectsof Pb + Hg. A reduction in respiration and decomposition of10% was found at about 225–245 g g^-1 of total Pb, i.e. ata Pb level elevated 3.5 times. Although small effects of Hg werefound even at the lowest dose level, 10% inhibition of microbialactivity appeared temporarily at about 2–3 g g^-1 of total Hg, i. e. at 6–8 times the reference level. There were nolong-term additive effects of Pb and Hg on decomposition. Type of anion had a strong influence on the test, chlorides of Pbbeing more toxic than nitrates. Long-term monitoring and maintenance of microbial activity during the experiment were prerequisites for the occurrence of effects at low metal levels.     

印度夏季风降水周期性研究

印度夏季风降水(ISMR)在南亚气候系统中是一个非常重要的内容,近年来对它的研究日益受到人们的重视。为了深入认识ISMR的变化特征,主要利用Scargle周期图和小波变换研究了1871-2004年间ISMR变化的周期性。结果表明,ISMR的周期性波动非常复杂,相应的周期参数具有明显的时变特征。文中还简单讨论了ISMR周期时变的可能原因。     

数据安全新思路

利用小波的时频局部化的特征,将信息的加密过程由传统的时域中进行改为在时域和频域中进行,达到信息加密和增强信息安全性的目的。采用两种方法实现信息的加密与解密的过程,一种是将明文保存为图像文件格式,对图像文件进行小波的分解与重构,实现信息的加密与解密;另一种是将明文数值化为一个系数矩阵,对数值矩阵进行小波的分解与重构,实现信息的加密与解密。通过小波分解过程进行加密,小波的重构过程进行解密,改变了传统的在空域中通过一系列的移位、迭代和置换的方式进行的加密过程,因此也不能通过传统的解密方式进行解密,增强了信息的安全性。由于小波的多样性,不同的小波变换得到的结果也会不同,增加了解密的难度,保证了数据的安全。     

Decomposition Analysis of Sectoral Energy Use in Beijing （1981-2005） Using the LMDI Method

This paper aims to identify the main driving force for changes of total primary energy consumption in Beijing during the period of 1981-2005. Sectoral energy use was investigated when regional economic structure changed significantly. The changes of total primary energy consumption in Beijing are decomposed into production effects, structural effects and intensity effects using the additive version of the logarithmic mean Divisia index （LMDI） method. Aggregate decomposition analysis showed that the major contributor of total effect was made by the production effect followed by the intensity effect, and the structural effect was relatively insignificant. The total and production effects were all positive. In contrast, the structural effect and intensity effect were all negative. Sectoral decomposition investigation indicated that the most effective way to slow down the growth rate of total primary energy consumption （TPEC） was to reduce the production of the energy-intensive industrial sectors and improving industrial energy intensity. The results show that in this period, Beijing＇s economy has undergone a transformation from an industrial to a service economy. However, the structures of sectoral energy use have not been changed yet, and energy demand should be increasing until the energy-intensive industrial production to be reduced and energy intensity of the region reaches a peak. As sequence energy consumption data of sub-sectors are not available, only the fundamental three sectors are considered： agriculture, industry and service. However, further decomposition into secondary and tertiary sectors is definitely needed for detailed investigations.     

富氧条件下等离子体协同改性NaY分子筛催化分解NO_x研究

用不同浓度的Cu、Ce和La离子交换Na Y分子筛,对比了不同改性条件下等离子体协同分解NO_x的性能.实验结果表明:Cu是NO_x催化分解的主要活性组分,对于8%Cu-Na Y催化剂,当放电电压为10 k V,放电功率为7.6 W时,NO_x转化率可达46.3%,反应产物中没有NO_2,只有11 ppm的N_2O.Ce的加入可以有效提高催化剂催化活性,对于5%Ce-8%Cu-NaY催化剂,当放电电压为7.8 kV,功率为3.6 W时,NO_x转化率可达67.3%.La的加入同样可以使催化剂活性上升,但不同La含量催化剂的NO_x转化率相差较小.     

Mercury adsorption characteristics of HBr-modified fly ash in an entrained-flow reactor

In this study, the mercury adsorption characteristics of HBr-modified fly ash in an entrained-flow reactor were investigated through thermal decomposition methods. The results show that the mercury adsorption performance of the HBr-modified fly ash was enhanced significantly. The mercury species adsorbed by unmodified fly ash were HgCl₂, HgS and HgO. The mercury adsorbed by HBr-modified fly ash, in the entrained-flow reactor, existed in two forms, HgBr₂ and HgO, and the HBr was the dominant factor promoting oxidation of elemental mercury in the entrained-flow reactor. In the current study, the concentration of HgBr₂ and HgO in ash from the fine ash vessel was 4.6 times greater than for ash from the coarse ash vessel. The fine ash had better mercury adsorption performance than coarse ash, which is most likely due to the higher specific surface area and longer residence time.     

集合经验模态分解在长江中下游梅雨变化多尺度分析中的应用

基于长江中下游流域5个梅雨监测站1961~2012年的日数据,利用集合经验模态分解（EEMD）方法,对研究期内梅雨时间序列进行多尺度的分析,探讨其在不同时间尺度上的振荡模态结构特征。结果表明：近50多年来,长江中下游梅雨变化呈现出显著的年际和年代际尺度振荡特征,在年际尺度上表现出准3 a和6 a的周期变化,而在年代际尺度上显示准13 a和24 a的周期变化;各分量方差〖JP2〗贡献率显示,年际振荡在梅雨长期变化中占据主导地位;自1961年以来,EEMD分解的梅雨长期变化趋势表现出先增加后减少的倒“U”型特征,其中1961~1985年呈上升趋势,1985~2012年呈下降趋势,尤其是在2000年之后的下降趋势最为明显。由此可以看出,EEMD能够有效地揭示梅雨长期序列在不同时间尺度上的变化规律,可用于诊断非线性、非平稳性信号变化的复杂性特征