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.

An Investigation of Coal Demand in China Based on the Variable Weight Combination Forecasting Model

Variable weight combination forecasting combines individual forecasting models after giving them proper weights at each time point. Weight is the type of function that changes with forecast time. A relatively rational description of the system can be proposed with the forecasting method, which is of higher precision and better stability. Two individual forecasting models, grey system forecasting and multiple regression forecasting, were generated based on the historical data and influencing factors of coal demand in China from 1981 to 2008. According to the theory of combination forecasting, the variable weight combination forecasting model was formulated to forecast coal demand in China for the next 12 years.

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.

PRELIMINARY STUDY OF BAROTROPIC STOCHASTIC DIFFERENCE MODEL APPLIED TO WEATHER PREDICTION

In order to consider both the deterministic and the stochastic property of atmospheric motion simul- taneously,in this paper,the weather prediction is proposed as the problem of the evolution of meteorological field.The historical viewpoint of atmospheric motion is emphasized here.Based on time series analysis te- chnique,a stochastic-dynamical model with multiple initial fields is derived.Thus,weather forecasting is sum- meal up as a problem of solving a set of stochastic difference equations.For the barotropic atmosphere,the numerical solutions of the equations are obtained by using the method of empirical orthogonal functions (EOF),and examples of medium-range weather prediction are given here.Meanwhile,selecting the order of time series,i.e.,determining the number of initial fields properly,is also discussed.

A Three-dimensional Forecasting Model for Oil Spill

A 3-D forecasting model for oil-spill is developed using the finite difference method to numerically solve the shallow water equation. The instantaneous flow distribution in the studied area is calculated and the trajectory of the oil-slick centroid is predicted by means of Lagrange’s method. The computed results agree with the observed data well, this shows that this 3-D forecasting model has high accuracy.

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.

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.

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。

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%。

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。

基于集成学习与深度学习的洪水径流预报研究

深度学习模型凭借其对水文因素间复杂作用的优秀处理能力,在水文预报领域得到了一定的应用,然而,针对集成学习与深度学习耦合模型的研究仍有所缺失。通过融合集成学习AdaBoost算法与深度学习Informer模型,提出了一种组合模型,称为AdaBoost-Informer模型,以提高洪水径流预报的精度。该模型以历史雨量和径流数据作为数据输入,将具备长时序依赖捕获能力的Informer作为集成学习的弱预测器,使用网格搜索法进行超参数调优,使用AdaBoost集成学习算法对弱预测器进行加权组合得到强预测器。在浙江省椒江流域的应用分析表明:对比Random Forest、AdaBoost、Transformer、Informer等模型,AdaBoost-Informer模型表现最佳,RMSE为62.08 m^(3)/s,MAE为23.83 m^(3)/s,NSE为0.980,预报合格率为100%。所提模型可有效提高洪水预报精度,为防汛抢险和防洪系统调度提供决策依据。

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。

考虑时序特征的深圳港集装箱吞吐量组合方法预测

集装箱吞吐量预测对港口企业运营及决策具有重要的作用。传统集装箱吞吐量预测方法存在预测精度不高的缺点。为解决这一问题,提出了一种考虑季节性和不确定性的SARIMA-XGBoost组合预测方法。针对集装箱吞吐量的季节性特征,选取季节性自回归移动平均模型(seasonal autoregressive integrated moving average model,SARIMA)捕捉周期性特征和线性特征;针对集装箱吞吐量中的不确定性因素,选取极致梯度提升树算法(extreme gradient boosting,XGBoost)自适应学习时间序列数据中的复杂模式和非线性特征。通过选取优化指标并计算分配权重的方式实现了预测模型中线性和非线性特征的有效融合,从而提升预测精度。通过对深圳港2013—2022年集装箱吞吐量月度数据进行实证研究和对比分析,结果表明SARIMA-XGBoost组合方法预测精度最高、稳定性好,验证了该组合方法在集装箱吞吐量预测中的有效性。

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。

配电网负荷预测中信号分解和预测模型组合的双层优化策略

负荷时间序列的波动性和非线性特征的加剧对负荷预测方法提出了更高的要求,而常规组合预测方法针对海量负荷数据存在应用局限性问题。为此,提出了配电网负荷预测中时序分解方法和预测模型组合的双层优化策略。首先针对某一负荷预测数据,在时序信号分解层配置权重,以负荷均方根误差最小寻优各分解方法的权重系数,进而获得各时序信号分解方法的最优组合;在此基础上,在预测模型层进行组合方案寻优,通过配置权重系数以获得各预测模型的最优组合,进一步提升负荷预测的精度。仿真结果表明,所提策略可根据预测对象的特征优化组合各信号分解方法和预测模型,降低了配电网负荷序列的非平稳性对预测精度的影响。

基于CNN-LSTM电力消耗预测模型及系统开发

有效预测电能负荷,对提高电力负荷时间序列测量准确度及合理制定用电能管理措施具有重要意义。针对传统预测模型在电能负荷预测中无法充分挖掘时间序列数据中隐藏特征的问题,基于电能数据时间序列的趋势,融合数值信息提出一种卷积神经网络(convolutional neuralnetwork,CNN)与长期短期记忆循环神经网络(long short-term memory network,LSTM)相结合的混合多隐层CNN-LSTM电力能耗预测模型。首先,通过设定最小目标函数作为优化目标,Adam优化算法更新神经网络的权重,并对网络层和批大小进行自适应调优以确定最佳层数和批大小。其次,构建混合多隐层模型并进行隐层组合优化与讨论,确定最佳时间维度的参数,进行时间维度的特征学习进而预测下一时间序列的耗电量。然后以某公司的电力负荷数据为例进行验证,并与LSTM、CNN、RNN等模型的预测结果分析比较。结果表明上述混合多隐层模型预测准确度达98.94%,平均绝对误差(MAE)达到0.0066,均优于其他相关模型,证明以上混合预测模型在电力负荷预测精度方面具有更好的性能。基于上述理论,开发了能耗监控决策系统,实现设备状态实时监控和能耗智能预测功能,为解决传统制造业能耗需求不精确和能源库存浪费问题提供参考和指导。

基于SARIMA‑LSTM模型的航空旅客运输市场需求分析与预测

市场需求预测是航空公司开展生产活动的前提,科学合理的预测结果能为航空公司降低成本、提高效益。首先,选取影响航空旅客运输市场需求的因素,并对其进行相关性分析;其次,采用季节性差分自回归移动平均(SARIMA)模型和长短期记忆(LSTM)网络模型,对航空旅客运输市场需求量进行特征分析,构建了基于SARIMA模型、LSTM网络模型的组合预测(SARIMA⁃LSTM)模型,提高市场需求时间序列预测的精度;最后,以北京市航空运输市场为例,分析结果显示,SARIMA⁃LSTM组合模型的预测准确性高于单一模型,对于市场需求的预测准确率较高。

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。