Forecasting China’s natural gas consumption based on a combination model

Ensuring a sufficient energy supply is essential to a country. Natural gas constitutes a vital part in energy supply and therefore forecasting natural gas consumption reliably and accurately is an essential part of a country＇s energy policy. Over the years, studies have shown that a combinative model gives better projected results compared to a single model. In this study, we used Polynomial Curve and Moving Average Combination Projection （PCMACP） model to estimate the future natural gas consumption in China from 2009 to 2015. The new proposed PCMACP model shows more reliable and accurate results： its Mean Absolute Percentage Error （MAPE） is less than those of any previous models within the investigated range. According to the PCMACP model, the average annual growth rate will increase for the next 7 years and the amount of natural gas consumption will reach 171600 million cubic meters in 2015 in China.

Forecasting Alzheimer’s Disease Using Combination Model Based on Machine Learning

As the acceleration of aged population tendency, building models to forecast Alzheimer’s Disease (AD) is essential. In this article, we surveyed 1157 interviewees. By analyzing the results using three machine learning methods—BP neural network, SVM and random forest, we can derive the accuracy of them in forecasting AD, so that we can compare the methods in solving AD prediction. Among them, random forest is the most accurate method. Moreover, to combine the advantages of the methods, we build a new combination forecasting model based on the three machine learning models, which is proved more accurate than the models singly. At last, we give the conclusion of the connection between life style and AD, and provide several suggestions for elderly people to help them prevent AD.

A Weighted Combination Forecasting Model for Power Load Based on Forecasting Model Selection and Fuzzy Scale Joint Evaluation

To solve the medium and long term power load forecasting problem,the combination forecasting method is further expanded and a weighted combination forecasting model for power load is put forward.This model is divided into two stages which are forecasting model selection and weighted combination forecasting.Based on Markov chain conversion and cloud model,the forecasting model selection is implanted and several outstanding models are selected for the combination forecasting.For the weighted combination forecasting,a fuzzy scale joint evaluation method is proposed to determine the weight of selected forecasting model.The percentage error and mean absolute percentage error of weighted combination forecasting result of the power consumption in a certain area of China are 0.7439%and 0.3198%,respectively,while the maximum values of these two indexes of single forecasting models are 5.2278%and 1.9497%.It shows that the forecasting indexes of proposed model are improved significantly compared with the single forecasting models.

A new hybrid method with data‑characteristic‑driven analysis for artificial intelligence and robotics index return forecasting

Forecasting returns for the Artificial Intelligence and Robotics Index is of great significance for financial market stability,and the development of the artificial intelligence industry.To provide investors with a more reliable reference in terms of artificial intelligence index investment,this paper selects the NASDAQ CTA Artificial Intelligence and Robotics(AIRO)Index as the research target,and proposes innovative hybrid methods to forecast returns by considering its multiple structural characteristics.Specifically,this paper uses the ensemble empirical mode decomposition(EEMD)method and the modified iterative cumulative sum of squares(ICSS)algorithm to decompose the index returns and identify the structural breakpoints.Furthermore,it combines the least-square support vector machine approach with the particle swarm optimization method(PSO-LSSVM)and the generalized autoregressive conditional heteroskedasticity(GARCH)type models to construct innovative hybrid forecasting methods.On the one hand,the empirical results indicate that the AIRO index returns have complex structural characteristics,and present time-varying and nonlinear characteristics with high complexity and mutability;on the other hand,the newly proposed hybrid forecasting method(i.e.,the EEMD-PSO-LSSVM-ICSS-GARCH models)which considers these complex structural characteristics,can yield the optimal forecasting performance for the AIRO index returns.

Wavelet Decomposition Impacts on Traditional Forecasting Time Series Models

This investigative study is focused on the impact of wavelet on traditional forecasting time-series models,which significantly shows the usage of wavelet algorithms.Wavelet Decomposition(WD)algorithm has been combined with various traditional forecasting time-series models,such as Least Square Support Vector Machine(LSSVM),Artificial Neural Network(ANN)and Multivariate Adaptive Regression Splines(MARS)and their effects are examined in terms of the statistical estimations.The WD has been used as a mathematical application in traditional forecast modelling to collect periodically measured parameters,which has yielded tremendous constructive outcomes.Further,it is observed that the wavelet combined models are classy compared to the various time series models in terms of performance basis.Therefore,combining wavelet forecasting models has yielded much better results.

Demand of Electric Power and Its Forecasting in Iron and Steel Complex

A systematic study on the electrical load forecasting for large-scale iron and steel companies was made. After analyzing the electrical load＇s characteristics, an algorithm framework for the load forecasting in iron and steel complex was formulated based on model combination and scheme filtration. The algorithm features data quality self- adaptation, convenient forecasting model extension, easy practical application, etc. , and has been successfully applied in Baoshan Iron and Steel Co Ltd, Shanghai, China, resulting in great economic benefit.

A COMBINED MODEL OF WIND, WAVE, TIDE AND STORM SURGES

A combined numerical model of wind, wave, tide, and storm surges was built on the basis of the “wind field model in limited sea surface areas”. When used to forecast the sea surface wind, wave height and water level, it can describe them very well.

Forecasting Realized Volatility Using Subsample Averaging

When the observed price process is the true underlying price process plus microstructure noise, it is known that realized volatility (RV) estimates will be overwhelmed by the noise when the sampling frequency approaches infinity. Therefore, it may be optimal to sample less frequently, and averaging the less frequently sampled subsamples can improve estimation for quadratic variation. In this paper, we extend this idea to forecasting daily realized volatility. While subsample averaging has been proposed and used in estimating RV, this paper is the first that uses subsample averaging for forecasting RV. The subsample averaging method we examine incorporates the high frequency data in different levels of systematic sampling. It first pools the high frequency data into several subsamples, then generates forecasts from each subsample, and then combines these forecasts. We find that in daily S&P 500 return realized volatility forecasts, subsample averaging generates better forecasts than those using only one subsample.

基于极点对称模态分解的中长期径流预报组合模型

为提高径流预报精度,解决径流序列分解后高频分量波动范围大、预报精度差的问题,基于极点对称模态分解法(ESMD)平稳化处理技术将径流序列分解,通过分析不同频率分量特征,择优选取预报方法,结合粒子群优化最小二乘支持向量机(PSO-LSSVM)全局优化和非线性建模能力及适应性强的特点,对高频分量进行预测,利用BP神经网络非线性映射能力和逼近任意非线性函数的优势对中低频分量和趋势分量进行预报,构建了ESMD-PSO-LSSVM-BP组合预报模型,对西江干流上中下游三座水文站的年、月尺度径流开展中长期径流预报。结果表明,对不同频率分量采用不同预报方法的组合模型可以有效提高径流预报精度。

基于CEEMDAN-GRU组合模型的碳排放交易价格预测研究

准确的碳价格预测有助于监管部门观测碳交易市场运行状况及投资者进行科学决策,对实现碳达峰和碳中和具有重要作用。但碳价序列具有非线性、非平稳性和高噪声的特性,很难对其进行准确预测。将完全自适应噪声集合经验模态分解(CEEMDAN)方法与门控循环单元(GRU)相结合,构建一个碳排放交易价格预测模型。该模型基于分解、集成思想,利用CEEMDAN将原始碳价序列分解,获得不同频率的本征模函数(IMF)和残差序列,使用GRU神经网络分别为各子序列建立预测模型,最后集成预测结果得到碳价预测值。以湖北省碳交易市场的日度成交价为例进行实证分析,结果表明:相较于其他5种基准模型,CEEMDAN-GRU模型具有更小的预测误差和更高的拟合优度,在碳价格预测上具有一定的优势。

白条猪价格预测模型构建

【目的】增强农产品价格预测准确度,为农产品价格的有效预测提供参考。【方法】以河南省白条猪每周平均批发价格为研究对象,提出一种基于序列分解、主成分分析和神经网络(CEEMDAN-PCA-CNN-LSTM)的白条猪价格预测方法。首先,使用自适应白噪声完全集合模态分解方法(CEEMDAN)对白条猪价格序列进行分解;其次,选用皮尔逊相关系数筛选影响价格波动的相关因素;再次,利用主成分分析(PCA)对影响因素及分解得到的子序列降维处理并作为原始价格序列的特征值,并行输入到作为编码器的卷积神经网络(CNN)中进行特征提取;最后,引入长短期记忆网络(LSTM)作为解码器输出得到预测结果。将该方法应用于河南省白条猪每周平均价格数据,与LSTM、门控循环单元(GRU)、CNN、基于卷积的长短期记忆网络(ConvLSTM)模型进行比较。【结果】CEEMDAN-PCA-CNN-LSTM组合模型预测方法得到的平均绝对误差分别降低了44.95%、27.30%、28.13%、43.17%。【结论】CEEMDAN-PCA-CNN-LSTM模型对于河南省白条猪市场价格的预测性能更优,有助于相关部门针对河南省白条猪价格波动做出科学决策。

SARIMA-GRU组合模型的水位预测

相较于传统的单一模型,组合模型在一定条件下具有更优的预测精度。为验证组合模型是否有利于提高模型的预测精度,本文以长江中游支流澧水石龟山水电站的水位数据为基础,建立SARIMA模型和GRU神经网络模型,并将这两种模型基于方差倒数法和IOWA算子进行组合,最后比较单一模型和组合模型在该水位数据集上的预测精度差异。结果表明,适当的组合方式有利于提高模型预测精度,基于IOWA算子的组合模型具优良的预测性能。

基于网络搜索数据的GDP组合预测研究

网络搜索数据(Web Search Data, WSD)是研究宏观经济现象的重要微观信息依据。从需求、供给与政策环境等方面选取和筛选关键词来合成网络搜索指数,采用金枪鱼群(Tuna Swarm Optimization, TSO)算法优化的最小二乘支持向量回归(Least Squares Support Vector Regression, LSSVR)模型,对GDP进行预测。结果表明,网络搜索指数与GDP具有强相关性,合成的网络搜索指数能较好地反映GDP的波动走势;网络搜索数据的加入使得预测结果呈现出强时效性,预测效果及预测精度都取决于对最优模型的选择,引入参数智能优化算法可提高模型的预测性能。提出的TSO-LSSVR&WSD模型充分利用网络搜索数据及组合预测优势,提高了GDP的预测精度和时效性,可应用于宏观经济指标预测中。

基于VMD-改进最优加权法的短期负荷变权组合预测策略

为提升短期电力负荷预测精度,提出了一种变权组合预测策略。首先,为了降低负荷数据的不平稳度,使用变分模态分解(variational mode decomposition,VMD)将负荷数据分解成了高频、低频、残差3种特征模态分量。其次,充分计及负荷数据的时序特点,参考指数加权法原理设计自适应误差重要性量化函数,并结合组合模型在时间窗口内的历史负荷数据的均方预测误差设计改进最优加权法的目标函数和约束条件,以完成子模型的准确变权。最后,针对波动较强的高频分量选定极端梯度提升(XGBoost)和卷积神经网络-长短期记忆(CNN-LSTM)模型并使用改进最优加权法进行组合预测、低频分量使用多元线性回归(MLR)模型预测、残差分量使用LSTM模型预测,叠加各模态分量的预测结果,实现了短期负荷数据的准确预测。实验结果表明,使用策略组合模型的平均绝对百分比误差为4.18%。与使用传统组合策略的组合模型相比,平均绝对百分比预测误差平均降低了0.87%。

Nonlinear Combination Forecasting Model and Its Application

This paper mainly discusses the nonlinear combination forecasting model and states that the nonlinear combination forecasting model is better than linear combination forecasting model in many aspect.

湖泊型水库环库实时洪水预报方法研究

湖泊型水库的修建,改变了水库坝址控制流域的下垫面和河流水系结构,进而影响流域产汇流机制。针对湖泊型水库环库周边流域产汇流特点,构建了包含库面不透水产流区、环库破碎产流区的组合洪水预报模型,提出了不同分区的产汇流计算方法。以响洪甸水库为例,进行洪水模拟效果的对比分析,结果表明:组合洪水预报模型的精度显著高于整体新安江模型,确定性系数提升0.1,洪量相对误差降低5.3%,洪峰相对误差降低2.8%;组合预报模型的不透水面积,产流和汇流等相关模型参数,更为符合碎片化小流域产汇流的特性,并能较好地反映入库洪水的组成;水库水面的直接产流占有较大比重,是地表、壤中、地下径流之外的第4种径流组分。此方法可为湖泊型水库流域的实时洪水预报提供模型支撑,具备较好的应用前景。

基于邻域互信息的组合预测最优子集选择算法

为在候选模型集中高效地选择时间序列组合预测的最优子集,提出一种CSPSO-NMI-MRMR最优子集选择算法。利用邻域互信息(neighborhood mutual information, NMI)度量相关性和冗余度,避免数值型数据的离散化,按最大相关最小冗余原则(minimal redundancy and maximal relevance, MRMR)筛选最优子集;邻域互信息中的邻域参数与子集选择效果密切相关,采用CSPSO算法寻找最优邻域参数,充分利用布谷鸟算法(cuckoo search, CS)和粒子群优化算法(particle swarm optimization, PSO)的优势,兼顾搜索效率和全局搜索能力;在寻参过程中设计一种淘汰策略,优化邻域参数的寻优区间并淘汰部分单模型,减少计算量。仿真结果表明,所提方法在预测精度、运行时间和稳健性上效果更优。

基于奇异谱分解和LSTM-ARIMA组合模型的生猪价格预测

针对生猪价格波动过于剧烈难以预测的问题,提出基于奇异谱分解的LSTM-ARIMA组合模型对生猪价格进行预测。以2000年1月-2021年12月的月度价格数据作为样本,利用奇异谱分析对生猪价格数据进行分解,得到趋势项和波动项,选用累计贡献率达前70%的构建趋势项,剩下的30%构造波动项。趋势项非平稳且具有长记忆性,对其建立LSTM模型;波动项平稳,对其建立ARIMA模型,最后将两部分预测结果重组作为生猪价格的预测值,构建LSTM-ARIMA组合预测模型。将预测值和生猪真实价格进行对比,结果表明:预测值与真实值之间的均方根误差RMSE为2.75,平均绝对百分比误差MAPE为10.81%,平均绝对误差MAE为2.27,方向对称性DS为81.81;此组合模型能很好地预测生猪价格走势,对我国生猪价格预测具有更高地适用性与参考。

基于ConvLSTM-LSTM的短期负荷预测方法

长短时记忆(LSTM)网络和结合卷积神经网络(CNN)的CNN-LSTM预测模型由于其网络模型本身的缺陷,限制了预测精度的提高。针对以上问题,提出了一种结合卷积长短时记忆(ConvL⁃STM)网络的ConvLSTM-LSTM负荷预测模型。利用ConvLSTM网络充分提取时序特征,将提取到的信息输入到LSTM网络中进行进一步的选择性记忆,并输出预测结果。将该模型与CNN-LSTM网络模型、LSTM网络模型、以及门控循环单元(GRU)网络模型进行了对比,结果显示所构建的Con⁃vLSTM-LSTM模型的预测效果均优于对比模型,在精度评价指标平均绝对百分比误差(MAPE)上,分别减小了1.10%、1.54%、1.91%。

基于趋势分解和IOWA算子的组合预测模型

不同的数据有着自身的不同特性,对于时序数据而言,数据往往有着与时间相关的趋势,通过分解这种趋势,并对趋势和趋势以外的部分分别进行预测再组合,可以得到更好的预测结果 .选用2013年1月4日—8月11日的人民币对美元的汇率数据进行实证检验,分别采用灰色预测模型、ARIMA模型、LSTM模型以及它们的组合模型对数据进行预测,实证分析结果表明,基于趋势分解和IOWA算子的组合预测模型相较单项预测而言有着更良好的预测精度.