Time-series forecasting using a system of ordinary differential equations

This paper presents a hybrid evolutionary method for identifying a system of ordinary differential equations (ODEs) to predict the small-time scale traffic measurements data. We used the tree-structure based evolutionary algorithm to evolve the architecture and a particle swarm optimization (PSO) algorithm to fine tune the parameters of the additive tree models for the system of ordinary differential equations. We also illustrate some experimental comparisons with genetic programming, gene expression programming and a feedforward neural network optimized using PSO algorithm. Experimental results reveal that the proposed method is feasible and efficient for forecasting the small-scale traffic measurements data.     

基于小波分解的网络流量时间序列建模与预测

提出一种基于小波分解的网络流量时间序列的分析和预测方法。将非平稳的网络流量时间序列通过小波分解成为多个平稳分量,采用自回归滑动平均方法分别对各平稳分量进行建模,将所有分量的模型进行组合,得到原始非平稳网络流量时间序列的预测模型。在仿真实验中,利用网络流量文库的时间序列数据建立了预测模型,并对其进行独立测试检验。仿真结果表明,本预测方法提高了网络流量时间序列的预测准确率,是一种有效、稳健的网络流量预测方法。     

Time series forecasting based on wavelet decomposition and feature extraction

Time series forecasting is one of the most important issues in numerous applications in real life. The objective of this study was to propose a hybrid neural network model based on wavelet transform (WT) and feature extraction for time series forecasting. The motivation of the proposed model, which is called PCA-WCCNN, is to establish a single simplified model with shorter training time and satisfactory forecasting performance. This model combines the principal component analysis (PCA) and WT with artificial neural networks (ANNs). Given a forecasting sequence, order of the original forecasting model is determined firstly. Secondly, the original time series is decomposed into approximation and detail components by employing WT technique. Then, instead of using all the components as inputs, feature inputs are extracted from all the sub-series obtained from the above step. Finally, based on the extracted features and all the sub-series, a famous neural network construction method called cascade-correlation algorithm is applied to train neural network model to learn the dynamics. As an illustration, the proposed model is compared with two classical models and two hybrid models, respectively. They are the traditional cascade-correlation neural network, back-propagation neural network, wavelet-based cascade-correlation network using all the wavelet components as inputs to establish one model (WCCNN) and wavelet-based cascade-correlation network with combination of each sub-series model (WCCNN multi-models). Results obtained from this study indicate that the proposed method improves the accuracy of ANN and can yield better efficiency than other four neural network models.

     

基于二次分解重构策略的航空客流需求预测

考虑到航空客流需求序列的季节性、非线性和非平稳等特点,提出了一个基于二次分解重构策略的航空客流需求预测模型。首先,通过STL和自适应噪声互补集成经验模态分解（CEEMDAN）方法对航空客流需求序列进行二次分解,并根据数据复杂度和相关度的特征分析结果进行分量重构;然后,采用模型匹配策略分别选取自回归单整移动平均季节（SARIMA）、自回归单整移动平均（ARIMA）、核极限学习机（KELM）和双向长短期记忆（BiLSTM）网络模型对各重构分量进行预测,其中KELM和BiLSTM模型的超参数通过自适应树Parzen估计（ATPE）算法确定;最后,将重构分量预测结果进行线性集成。以北京首都国际机场、深圳宝安国际机场和海口美兰国际机场的航空客流数据作为研究对象进行了1步和多步预测实验,实验结果表明,与一次分解集成模型STL-SAAB相比,所提模型的均方根误差（RMSE）提升了14.98%～60.72%。可见以“分而治之”思想为指导,所提模型结合模型匹配和重构策略挖掘出了数据的内在发展规律,从而为科学预判航空客流需求变化趋势提供了新思路。     

Global and decomposition evolutionary support vector machine approaches for time series forecasting

Multi-step ahead time series forecasting (TSF) is a key tool for supporting tactical decisions (e.g., planning resources). Recently, the support vector machine (SVM) emerged as a natural solution for TSF due to its nonlinear learning capabilities. This paper presents two novel evolutionary SVM (ESVM) methods for multi-step TSF. Both methods are based on an estimation distribution algorithm search engine that automatically performs a simultaneous variable (number of inputs) and model (hyperparameters) selection. The global ESVM (GESVM) uses all past patterns to fit the SVM, while the decomposition ESVM (DESVM) separates the series into trended and stationary effects, using a distinct ESVM to forecast each effect and then summing both predictions into a single response. Several experiments were held, using six time series. The proposed approaches were analyzed under two criteria and compared against a recent evolutionary artificial neural network (EANN) and two classical forecasting methods, Holt–Winters and autoregressive integrated moving average. Overall, the DESVM and GESVM obtained competitive and high-quality results. Furthermore, both ESVM approaches consume much less computational effort when compared with EANN.     

考虑频域分解后数据特征的空调负荷预测模型

针对空调负荷预测实际应用中容易存在数据散杂且可用信息匮乏的问题,从负荷序列的非线性、非平稳性和随机性出发,提出了一种基于变分模态分解(VMD)的负荷预测方法.对不同数据特征序列考虑不同算法的数据观测与训练原理差异,充分发挥各个模型优势.首先采用随机森林(RF)进行特征选择,利用VMD将负荷序列按趋势分量、平稳分量和噪声分量进行分类重构,并分别对非线性序列建立最小二乘支持向量机(LSSVM)预测模型,时序平稳序列建立极端梯度提升(XGBoost)预测模型,采用正态分布拟合随机误差,得到各子序列预测结果并进行叠加输出最终负荷预测结果.实验结果表明,所提方法能准确反映负荷的特性并具有更好的预测精度,能有效预测空调负荷,为空调节能优化控制策略提供依据.     

Web traffic demand forecasting using wavelet‐based multiscale decomposition

In this paper we propose an experimental forecasting strategy taking into account the long‐range dependence of aggregate network traffic, and we apply it to provide one‐minute‐ahead World‐Wide Web (Web) traffic demand forecasts in terms of average number of bytes transferred. Recently, statistical examination of Web traces have shown evidence that Web traffic arising from file transfers exhibits a behavior that is consistent with the notion of self‐similarity. Essentially, self‐similarity indicates that significant burstiness is present on a wide range of time scales (i.e., the process is long‐range dependent). Hence the idea of exploiting this multiscale property with a view towards discovering and capturing regularities underlying the time series which may prove useful for short‐term traffic load forecasting. We carry out a wavelet transform decomposition of the original series to decompose the traffic time series into varying scales of temporal resolution, with the aim of making the underlying temporal structures more tractable. In a second step, each individual wavelet series—supposed to capture some features of the series—is fitted with a dynamical recurrent neural network (DRNN) model to output the wavelet forecast. The latter are afterwards recombined to form the next‐minute Web Traffic demand. The method is applied on a large set of HTTP logs and is shown to yield good results. © 2001 John Wiley & Sons, Inc.     

A spatio-temporal decomposition based deep neural network for time series forecasting

Spatio-temporal problems arise in a broad range of applications, such as climate science and transportation systems. These problems are challenging because of unique spatial, short-term and long-term patterns, as well as the curse of dimensionality. In this paper, we propose a deep learning framework for spatio-temporal forecasting problems. We explicitly design the neural network architecture for capturing various types of spatial and temporal patterns, and the model is robust to missing data. In a preprocessing step, a time series decomposition method is applied to separately feed short-term, long-term and spatial patterns into different components of the neural network. A fuzzy clustering method finds clusters of neighboring time series residuals, as these contain short-term spatial patterns. The first component of the neural network consists of multi-kernel convolutional layers which are designed to extract short-term features from clusters of time series data. Each convolutional kernel receives a single cluster of input time series. The output of convolutional layers is concatenated by trends and followed by convolutional-LSTM layers to capture long-term spatial patterns. To have a robust forecasting model when faced with missing data, a pretrained denoising autoencoder reconstructs the model’s output in a fine-tuning step. In experimental results, we evaluate the performance of the proposed model for the traffic flow prediction. The results show that the proposed model outperforms baseline and state-of-the-art neural network models.     

A clustering-based short-term load forecasting using independent component analysis and multi-scale decomposition transform

The Journal of Supercomputing - A short-term electrical load forecasting model is proposed in this work. The proposed model is based on independent component analysis (ICA), discrete wavelet...     

时序规则挖掘

提出了新颖的时间序列模式和规则挖掘技术。该技术先把待挖掘的时间序列转换成子时间序列数据,然后利用子时间序列所隐藏的知识,来指导对原时间序列的挖掘,从中提取模式或规则。给出了时间序列模式和规则的挖掘算法,并举例说明该算法是有效和可行的。     

时序规则发现及其算法

该技术先把要考察的时间序列转换成子时间序列数据,然后对这些子时间序列数据进行挖掘, 从中提取关联规则。给出了时间序列关联规则的挖掘算法, 并举例说明该算法是有效的和可行的。     

A novel axle temperature forecasting method based on decomposition,reinforcement learning optimization and neural network

Axle temperature forecasting technology is important for monitoring the status of the train bogie and preventing the hot axle and other dangerous accidents. In order to achieve high-precision forecasting of axle temperature, a hybrid axle temperature time series forecasting model based on decomposition preprocessing method, parameter optimization method, and the Back Propagation (BP) neural network is proposed in this study. The modeling process consists of three phases. In stage I, the empirical wavelet transform (EWT) method is used to preprocess the original axle temperature series by decomposing them into several subseries. In stage II, the Q-learning algorithm is used to optimize the initial weights and thresholds of the BP neural network. In stage III, the Q-BPNN network is used to build the forecasting model and complete predicting all subseries. And the final forecasting results are generated by combining all prediction results of subseries. By comparing all results over three case predictions, it can be concluded that: (a) the proposed Q-learning based parameter optimization method is effective in improving the accuracy of the BP neural network and works better than the traditional population-based optimization methods; (b) the proposed hybrid axle temperature forecasting model can get accurate prediction results in all cases and provides the best accuracy among eight general models.     

A secondary decomposition based hybrid structure with meteorological analysis for deterministic and probabilistic wind speed forecasting

Accurate wind speed forecasting could ensure the reliability and controllability for the wind power system. In this paper, a new hybrid structure based on meteorological analysis is proposed for the wind speed vector (wind speed and direction) deterministic and probabilistic forecasting. Twelve kinds of secondary decomposition methods are employed to decrease the interference existing in the data. To improve the training efficiency and accelerate the sample selection process, active learning is employed. Four different wind speed datasets collected from Ontario Province, Canada, are utilized as case studies to evaluate the forecasting performance of the proposed structure. Experimental results show that the proposed structure based on meteorological analysis is suitable for wind speed vector forecasting and could obtain better forecasting performance. Furthermore, except accurate deterministic forecasts, the proposed structure also provides more probabilistic forecasting information.     

A hybrid ANFIS model based on empirical mode decomposition for stock time series forecasting

Time series forecasting is an important and widely popular topic in the research of system modeling, and stock index forecasting is an important issue in time series forecasting. Accurate stock price forecasting is a challenging task in predicting financial time series. Time series methods have been applied successfully to forecasting models in many domains, including the stock market. Unfortunately, there are 3 major drawbacks of using time series methods for the stock market: (1) some models can not be applied to datasets that do not follow statistical assumptions; (2) most time series models that use stock data with a significant amount of noise involutedly (caused by changes in market conditions and environments) have worse forecasting performance; and (3) the rules that are mined from artificial neural networks (ANNs) are not easily understandable.To address these problems and improve the forecasting performance of time series models, this paper proposes a hybrid time series adaptive network-based fuzzy inference system (ANFIS) model that is centered around empirical mode decomposition (EMD) to forecast stock prices in the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and Hang Seng Stock Index (HSI). To measure its forecasting performance, the proposed model is compared with Chen's model, Yu's model, the autoregressive (AR) model, the ANFIS model, and the support vector regression (SVR) model. The results show that our model is superior to the other models, based on root mean squared error (RMSE) values.     

Time-series prediction using adaptive neuro-fuzzy networks

In this paper, we propose an Adaptive Neuro-Fuzzy Network (ANFN) to deal with forecasting problems. The ANFN model is inherently a modified Takagi–Sugeno–Kang-type fuzzy-rule-based model possessing a neural network's learning ability. We propose a hybrid learning algorithm which combines the Genetic Algorithm (GA) and the Least-Squares Estimate (LSE) method to construct the ANFN model. The GA is used to tune membership functions at the precondition part of fuzzy rules, while the LSE method is used to tune parameters at the consequent part of fuzzy rules. Simulations demonstrate that the proposed ANFN model has a good predictive capability.     

Time-series prediction with single integrate-and-fire neuron

In this paper, a learning algorithm for a single integrate-and-fire neuron (IFN) is proposed and tested for various applications in which a multilayer perceptron neural network is conventionally used. It is found that a single IFN is sufficient for the applications that require a number of neurons in different hidden layers of a conventional neural network. Several benchmark and real-life problems of classification and time-series prediction have been illustrated. It is observed that the inclusion of some more biological phenomenon in an artificial neural network can make it more powerful.     

Time-series segmentation: A model and a method

The problem of partitioning time series into segments is treated. The segments are considered as falling into classes. A different probability distribution is associated with each class of segment. Parametric families of distributions are considered, a set of parameter values being associated with each class. With each observation is associated an unobservable label, indicating from which class the observation arose. The label process is modeled as a Markov chain. Segmentation algorithms are obtained by applying a relaxation method to maximize the resulting likelihood function. Special attention is given to the situation in which the observations are conditionally independent, given the labels. A numerical example, segmentation of the U.S. gross national product, is given. Choice of the number of classes, using statistical model selection criteria, is illustrated.     

一种快速的子序列匹配算法

提出一种在时间序列上快速匹配子序列的算法,该算法不同于FRM算法,而是采用VA-file这种索引结构,将数据点直接存储在索引上,并在该索引的基础上设计了一种进行范围查询的方法.实验采用了三种时间序列数据集,从不同的角度验证算法的有效性,结果表明该算法大大提高了查询性能.     

Time-series prediction based on pattern classification

In this paper, a new time-series predication method is proposed based on pattern analysis. In this method, basic patterns and their probabilities are extracted from a time series. A probabilistic relaxation method is employed to classify the probability vectors of the basic patterns. In order to verify the effectiveness of the proposed method, several experiments are carried out on a simulation signal and real data. The results show that the proposed method has advantages over existing methods in some applications.     

基于服务负载的时序QoS预测

网络技术的发展和多接入边缘计算的兴起使得计算和网络资源的部署逐渐靠近终端.随着服务数量的增多,为了向用户更好地推荐服务,如何在复杂、动态的边缘计算环境中实时、准确地预测服务质量(quality of service,QoS)成为一项挑战.本文提出一种基于服务负载实时预测QoS的深度神经模型(QPSL),它可以为边缘计算中的QoS预测提供缺少的负载状况感知和周期感知.首先,对服务的负载状况进行特征表示,并通过时序分解模块获取时序特征.其次,将CNN和BiLSTM结合,学习潜在的时序关系,生成不同时刻的状态向量.然后,基于Attention机制为历史时刻的状态向量分配权重,从而构造未来时刻的状态向量.最后,将上下文嵌入向量与状态向量送入感知层完成实时QoS预测.基于真实的融合数据集进行了大量的实验,结果表明QPSL在响应时间和吞吐量任务上的MAE分别平均提升了10.28%和10.87%,优于现有的时间感知QoS预测方法.