基于深度学习的城市轨道交通短时客流量预测

我国城市轨道交通已进入快速发展期,准确预测城轨交通短时客流量,对于城轨运营安全、运营效率及运营成本具有重要意义.城轨交通短时客流量由于具有强随机性、周期性、相关性及非线性的特征,浅层模型的预测精度并不理想.对此,基于深度信念网络(DBN)和支持向量回归机(SVM),提出城轨交通短时客流深层预测模型(DBN-P/GSVM),同时基于遗传算法(GA)和粒子群算法(PSO)实现SVM的参数寻优.最后,对成都地铁火车北站客流量预测进行实例分析.结果表明,DBN-P/GSVM深度预测模型在均方误差、均方根误差、绝对误差均值及绝对百分比误差均值等方面均优于浅层模型——GA-SVM模型、PSO-SVM模型和BP神经网络模型,以及深层模型长短期记忆网络(LSTM)与LSTM-Softmax.     

结合注意力机制与LSTM的短期风电功率预测模型

风力发电预测在电力系统的运行中发挥着重要作用。现有风电功率的短期预测模型因风速的复杂性和随机性,难以确定风速与风电功率的非线性映射关系,导致预测精度降低。提出一种结合变分模态分解、双阶段注意力机制、误差修正模块与深度学习算法的短期风电功率预测模型。通过对原始数据进行互信息特征选择,获得与风电功率相关性较强的特征,并对其进行信号预处理,利用变分模态分解对多维特征序列进行分解,得到具有一定中心频率的模态分量,以降低各个特征序列的复杂性和非平稳性。采用基于双阶段注意力机制与编解码架构的长短时记忆（LSTM）神经网络对模态分量进行训练与预测,得到初始预测误差。在此基础上,利用误差修正模块对初始预测误差进行变分模态分解和修正,从而提高模型的预测精度。实验结果表明,与自回归移动平均模型、标准编解码结构的LSTM模型相比,该预测模型的平均绝对误差最高可降低约87%,具有较优的预测性能。     

基于经验模态分解的小波神经网络预测模型

针对小波神经网络(WNN)在非平稳、非线性时间序列预测上无法实现自适应多分辨率分析,且其预测精度有待提高的问题,提出基于经验模态分解的小波神经网络预测模型。首先,对非线性、非平稳时间序列进行经验模态分解(EMD),以降低时间序列的非平稳性;然后对EMD分析得到的固有模态分量(IMF)和余项分别构建WNN模型;最后,汇总预测结果,得到预测值。通过数据验证,新模型的预测精度高于BP神经网络和WNN。     

含有误差校正的小波神经网络交通流量预测

交通流量的准确预测对于高速路管理者进行决策至关重要;建立了小波神经网络(WNN)交通流量预测模型,并通过预测训练误差和测试误差校正预测结果来提高预测精度;首先构建WNN模型对交通流量进行初步预测,然后利用经验模态分解(EMD)和WNN模型对训练误差和测试误差进行预测;分别用训练误差预测值、测试误差预测值和两种误差预测值的加权对流量初步预测结果进行修正得到最终预测值;采用四川省成灌高速路交通流量数据进行了仿真对比实验,仿真结果表明含有误差校正的小波神经网络模型能有效提高交通流量预测精度,并且利用两种误差加权修正模型的预测精度高于利用测试误差的修正模型和利用训练误差的修正模型。     

灰色神经网络模型在物流需求预测中的研究

研究物流准确预测,进行物流优化管理问题,由于现代物流需求变化是多种因素综合的结果,传统单一模型只能反映部分变化规律,不能全面反映其需求变化规律,导致预测精度不高.为了提高了物流需求的预测精度,提出一种灰色神经网络的物流需求预测方法.组合方法首先采用灰色预测模型对训练样本进行学习,得到BP神经网络的输入值,然后采用BP神经网络对其进行预测,得到最终物流需求值.将组合模型应用于湖南省物流需求预测中,实验结果表明,改进的模型提高了物流需求预测精度,发挥了2种单一模型优势,克服了单一模型不足,提供一种物流优化管理的有效方法.     

泊松分布灰色理论在物流需求预测中的应用

研究物流需求预测准确度问题。物流需求预测中存在数据小以及非线性特点,使预测系统存在不确定性。为解决上述问题,提出了一种泊松分布的神经网络需求预测算法,采用泊松分布算法对物流的整体需求进行分类,然后采用灰色理论算法选择物流需求影响因子,对物流的需求进行实时预测,仿真结果表明,改进物流需求预测方法比传统的灰色理论预测模型以及BP神经网络具有更高的预测精确度,有效地提高了区域物流需求的预测准确度,具有一定的实际应用价值。     

基于卷积长短时记忆神经网络的城市轨道交通短时客流预测

我国城市轨道交通正处在快速发展阶段,城轨交通短时客流预测对保障运营安全、优化线网结构,进而构建智慧城市具有重要意义.城轨短时客流除了具有周期性、随机性等时间特征之外,跨时段的断面客流具有相似性,并且相邻站点客流之间存在空间联系.对此,充分考虑以上城轨短时客流的时空特征,基于卷积长短时记忆神经网络(ConvLSTM)与自适应k-means聚类算法,提出城轨短时客流预测的深度学习模型k-ConvLSTM,并通过实验对模型关键参数进行寻优;同时,基于深圳市地铁IC卡的真实客流数据对模型的有效性进行检验.结果表明,k-ConvLSTM在均方根误差、绝对误差均值、绝对误差百分比方面,均优于仅考虑时空特征的深度学习模型-----卷积网络(CNN)与长短时记忆网络(LSTM)的并行混合模型和ConvLSTM内嵌式网络模型,仅考虑时间特征的深度学习模型-----LSTM网络和双向长短时记忆网络(Bi-LSTM),以及浅层机器学习模型-----BP神经网络和支持向量回归模型(SVR).     

基于神经网络模型的最小预测误差非线性自适应控制器

主要研究基于神经网络模型的最小预测误差非线性自适应控制算法.利用神经网 络激励函数的分段局部线性近似,将基于神经网络的非线性系统一步前向预测控制转化为一 系列局部的线性预测控制问题.利用线性系统参数估计方法获得神经网络预测模型的参数估 计.在此基础上利用并联线性系统的预测控制方法设计全局收敛的非线性系统预测控制器.     

基于CEEMDAN分解的短时交通流组合预测

短时交通流预测是实现交通流诱导与控制的重要保障,鉴于交通流的随机性和复杂性,提出基于自适应噪声完全集合经验模态分解（CEEMDAN）的短时交通流组合预测模型。利用CEEMDAN算法对非线性序列具有自适应分解的特性,将交通流时间序列通过CEEMDAN分解为频率不同、复杂度不同的多个时间序列分量;利用PE算法分析各个分量的随机特性,根据时间序列分量的不同随机特性分为高频序列分量、中频序列分量和低频序列分量,根据高频、中频和低频序列分量的随机特性分别建立GWO-BP模型、GWO-LSSVM模型和ARIMA模型进行预测;叠加高频、中频和低频各个分量的预测结果,得到短时交通流最终预测值。仿真分析结果表明,与其他预测模型相比,基于CEEMDAN分解的短时交通流组合预测模型提升了预测精度。     

基于因子分析与神经网络的区域物流需求预测

研究区域物流需求预测问题。影响区域物流需求影响因子较多,因子之间呈非线性关系,导致预测模型结果复杂,运行时间长,预测精度低。为提高区域物流需求预测精度,提出一种因子分析和BP神经网络相结合的区域物流需求预测方法(FA-BP)。首先通过因子分析对影响因子进行降维处理,然后将降维后的区域物流需求数据作为BP神经网络的输入进行训练建立预测模型,最后得到区域物流需求的预测结果。对某省1993-2007年区域物流需求预测进行实例分析,结果证明FA-BP模型提高了区域物流需求预测精度,网络的收敛速度加快,在区域物流需求预测方面有着广阔的应用前景。     

状态空间时间序列的区域物流需求预测研究

区域物流需求是制定区域物流发展政策、基础设施建设和物流系统规划的重要依据,由区域各项相关经济指标共同决定。针对区域物流需求预测中样本数量小的问题,提出了互信息高维度特征降维方法,在保证相关综合信息完整性基础上降低原始数据维度,在此基础上建立了状态空间时间序列预测模型,同时采用局部线性小波神经网络和LIBSVM支持向量回归模型进行对比实验。算例分析及实验结果表明,采用互信息降维后的预测模型相对误差平均减少54.8%,互信息与状态空间时间序列模型相结合的预测方法对于区域物流需求预测问题预测精度较高,相对误差约为0.08。     

A variational mode decompoisition approach for analysis and forecasting of economic and financial time series

The empirical mode decomposition (EMD) has been successfully applied to adaptively decompose economic and financial time series for forecasting purpose. Recently, the variational mode decomposition (VMD) has been proposed as an alternative to EMD to easily separate tones of similar frequencies in data where the EMD fails. The purpose of this study is to present a new time series forecasting model which integrates VMD and general regression neural network (GRNN). The performance of the proposed model is evaluated by comparing the forecasting results of VMD-GRNN with three competing prediction models; namely the EMD-GRNN model, feedforward neural networks (FFNN), and autoregressive moving average (ARMA) process on West Texas Intermediate (WTI), Canadian/US exchange rate (CANUS), US industrial production (IP) and the Chicago Board Options Exchange NASDAQ 100 Volatility Index (VIX) time series are used for experimentations. Based on mean absolute error (MAE), mean absolute percentage error (MAPE), and the root mean of squared errors (RMSE), the analysis results from forecasting demonstrate the superiority of the VMD-based method over the three competing prediction approaches. The practical analysis results suggest that VMD is an effective and promising technique for analysis and prediction of economic and financial time series.     

Daily Urban Water Demand Forecasting Based on Chaotic Theory and Continuous Deep Belief Neural Network

The prediction of daily water demands is a crucial part of the effective functioning of the water supply system. This work proposed that a continuous deep belief neural network (CDBNN) model based on the chaotic theory should be implemented to predict the daily water demand time series in Zhuzhou, China. CDBNN should initially be used to predict the urban water demand time series. First, the power spectrum and the largest Lyapunov exponent is used to determine the chaotic characteristic of the daily water demand time series. Second, C–C method is utilized to reconstruct the water demand time series’ phase space. Lastly, the forecasting model should be produced with the continuous deep belief network and neural network algorithms implemented for feature learning and regression, respectively, and the CDBNN input established by the best embedding dimension of the reconstructed phase space. The proposed method is contrasted with the support vector regression, generalized regression neural networks and feed forward neural networks, and they are accepted with the identical dataset. The predictive performance of the models is examined using normalized root-mean-square error (NRMSE), correlation coefficient (COR), and mean absolute percentage error (MAPE). The results suggest that the hybrid model has the smallest NRMSE and MAPE values, and the largest COR.     

改进IOWHA算子组合预测模型

针对现有单项预测模型提供信息有限,预测误差大的问题,引用最优加权组合建模理论,将灰色关联度与IOWHA算子相结合,提出一种新的组合预测模型权重确定方法,并应用该权重确定方法构建了一种基于RBF神经网络预测模型和GM预测模型的最优组合预测模型。该模型能够克服传统组合预测方法的两个缺陷：加权平均系数不变和以单一误差指标为准则。利用该组合模型对全国物流需求进行组合预测,并与RBF神经网络模型、GM模型的预测结果进行了对比分析。结果表明,相对于单项预测模型,该组合预测模型的预测精度更高,是一种有效的物流需求预测模型。     

基于EMD-TCN-ELM的短期电力负荷预测

为降低负荷序列的复杂性, 利用EMD分解方法得到不同的分量. 为降低训练时间和减小分量逐个预测所带来的累计误差, 利用分量过零率大小将分量重构为高频分量和低频分量, 利用TCN模型预测负荷的高频分量, 利用极限学习机ELM预测负荷低频分量. 通过实验将所提模型EMD-TCN-ELM分别与3个单模型TCN、ELM、LSTM和3个混合模型EMD-TCN、EMD-ELM、EMD-LSTM比较, 其MAPE分别降低0.538%, 1.866%, 1.191%, 0.026%, 1.559%, 0.323%, 所提模型的预测精度最高. 且所提模型在预测精度前3的模型中训练时间最短, 验证了所提模型在负荷预测精度和训练时间方面的优越性.     

Hybrid model combining empirical mode decomposition,singular spectrum analysis,and least squares for satellite-derived sea-level anomaly prediction

In this study, to meet the need for the accurate prediction of sea level anomaly (SLA), a hybrid model is proposed. In this model, empirical mode decomposition is combined with singular spectrum analysis and least-squares extrapolation to predict satellite-derived SLA. Each intrinsic mode function series of an empirical mode decomposition is decomposed and reconstructed using singular spectrum analysis. The reconstructed components and the residual series are predicted using least-squares extrapolation. This hybrid model was used for satellite-derived SLAs that were obtained using multi-mission along-track satellite altimetry data from September 1992 to January 2018, and the prediction errors for 3 years lead times were analysed. The observations and predictions of the principal components for annual or interannual periods correlated well, and the proposed hybrid model effectively predicted the SLAs. For the 3 years lead time predictions, the mean absolute error and root-mean-square error were 1.03 and 1.32 cm, respectively, which were less than those reported for existing methods.     

结合深度学习和分解算法的股票价格预测研究

针对股票价格预测问题,实现对非平稳、非线性股票价格序列的预测,提出一种结合深度学习和分解算法的股票价格预测模型。该模型引入自适应噪声的完整集成经验模态分解（CEEMDAN）算法提取股票价格时间序列在时间尺度上的特征,利用注意力机制捕获输入特征参数的权重并结合门控循环单元（GRU）网络进行股票价格预测。实验对苹果、贵州茅台等国内外四家公司的股票价格和上证指数进行预测,结果表明与RNN、LSTM等模型相比,所提模型能有效减少预测误差,提高模型拟合能力。     

A multi-pattern deep fusion model for short-term bus passenger flow forecasting

Short-term passenger flow forecasting is one of the crucial components in transportation systems with data support for transportation planning and management. For forecasting bus passenger flow, this paper proposes a multi-pattern deep fusion (MPDF) approach that is constructed by fusing deep belief networks (DBNs) corresponding to multiple patterns. The dataset of the short-term bus passenger flow is first segmented into different clusters by an affinity propagation algorithm. The passenger flow distribution of these clusters is subsequently analyzed for identifying different patterns. In each pattern, a DBN is developed as a deep representation for the passenger flow. The outputs of the DBNs are finally fused by chronological order rearrangement. Taking a bus line in Guangzhou city of China as an example, the present MPDF approach is modeled. Five approaches, non-parametric and parametric models, are applied to the same case for comparison. The results show that, the proposed model overwhelms all the peer methods in terms of mean absolute percentage error, root-mean-square error, and determination coefficient criteria. In addition, there exists significant difference between the addressed model and the comparison models. It is recommended from the present study that the deep learning technique incorporating the pattern analysis is promising in forecasting the short-term passenger flow.