基于LS-SVM的天然气管网负荷组合预测

针对现有组合预测模型,基于经验风险最小化原则,克服预测精度受组合模型限制的缺点,提出一种基于最小二乘支持向量机（LS-SVM）的天然气管网负荷组合预测模型,并与AR模型、BP神经网络模型、GM（1,1）模型以及最优权重组合模型进行了比较,得出基于最小二乘支持向量机的天然气管网负荷组合预测模型能够得到更高的预测精确度,可为天然气管网的安全运行以及优化调度提供决策支持的结论。     

Forecasting automobile petrol demand in Australia: An evaluation of empirical models

Transport fuel consumption and its determinants have received a great deal of attention since the early 1970s. In the literature, different types of modelling methods have been used to estimate petrol demand, each having methodological strengths and weaknesses. This paper is motivated by an ongoing need to review the effectiveness of empirical fuel demand forecasting models, with a focus on theoretical as well as practical considerations in the model-building processes of different model forms. We consider a linear trend model, a quadratic trend model, an exponential trend model, a single exponential smoothing model, Holt’s linear model, Holt–Winters’ model, a partial adjustment model (PAM), and an autoregressive integrated moving average (ARIMA) model. More importantly, the study identifies the difference between forecasts and actual observations of petrol demand in order to identify forecasting accuracy. Given the identified best-forecasting model, Australia’s automobile petrol demand from 2007 through to 2020 is presented under the “business-as-usual” scenario.     

A novel approach for systematically calibrating transport planning model systems

Calibration of a transport planning model system is a complex process. While trial-and-error methods and modelling expertise are still the backbone of calibration of transport models, analytical approaches automating the calibration process can improve the accuracy of the models. Introducing a model to guide modellers in the calibration process of large-scale transport planning model systems is the core of this study, where a systematic model for choosing the most appropriate models and parameters is discussed. The effectiveness of the proposed model is investigated by comparing three scenarios which are built on the Travel/Activity Scheduler for Household Agents model as a large-scale agent-based model system.

     

Speed profile estimation using license plate recognition data

Vehicle speed profile is a fundamental data support for calculating vehicular emission using the micro-emission model. However, achieving accuracy and breadth for the speed profile estimation is difficult. This study proposes a new vehicle speed profile estimation model using license plate recognition (LPR) data. This model allows speed profile estimation of every individual vehicle between two consecutive intersections. A systematic LPR data-mending method is developed to infer the information of unmatched vehicles. Using the complete arrival and departure information as boundary conditions, a customized car-following model combined with dummy-overtaking hypothesis and boundary constraints is then applied to estimate the speed profile of vehicles. The proposed model is validated using ground truth speed information from a field experiment conducted in Langfang City in China. Results show that the model can fully capture the pattern of ground truth speed profile. A complementary model validation using the Next Generation Simulation dataset and a model application for calculating emissions are also conducted. The numerical results indicate the effectiveness of the proposed model in estimating vehicle speed profile and emissions.     

A nested recursive logit model for route choice analysis

We propose a route choice model that relaxes the independence from irrelevant alternatives property of the logit model by allowing scale parameters to be link specific. Similar to the recursive logit (RL) model proposed by Fosgerau et al. (2013), the choice of path is modeled as a sequence of link choices and the model does not require any sampling of choice sets. Furthermore, the model can be consistently estimated and efficiently used for prediction.A key challenge lies in the computation of the value functions, i.e. the expected maximum utility from any position in the network to a destination. The value functions are the solution to a system of non-linear equations. We propose an iterative method with dynamic accuracy that allows to efficiently solve these systems.We report estimation results and a cross-validation study for a real network. The results show that the NRL model yields sensible parameter estimates and the fit is significantly better than the RL model. Moreover, the NRL model outperforms the RL model in terms of prediction.     

Development and validation of a direct mode choice model

A direct discrete mode choice model is introduced using relative attributes of competing modes as well as socioeconomic characteristics of travelers. The model is calibrated and validated for two available historic databases in the Dallas–Fort Worth region. The validation is conducted against the outputs of a current nested logit model used by the regional planning organization as well as the observed values based on transit ridership surveys for a newly inaugurated commuter rail service. The calibrated model is applied after the introduction of this new transit mode. The results show that the estimated mode shares by the proposed model have a statistically better consistency with the observed values than the estimates of the conventional nested logit model. Unlike the logit model, the structure of the direct model based on relative attributes also has the advantage of not needing recalibration each time a new travel mode is introduced. The model is found to be easier to calibrate and produces more accurate results than the nested logit model, commonly used by many metropolitan planning organizations.     

The dogit model

This paper presents the dogit model. That model is flexible enough to permit the choice among specific pairs of alternatives to be consistent with the independence from irrelevant alternatives axiom, as in a logit model, but it simultaneously allows the choice among other pairs not to be. Dogit parameters add an “income effect” to the “substitution effect” already built into the logit model; alternatively, they allow for the joint presence of compulsive and discretionary elements in consumer behavior, or for the identification of captive markets. Eventual estimation of the values of the parameters of the dogit model appears simpler than for the probit model.     

Competing risk mixture model and text analysis for sequential incident duration prediction

Predicting the duration of traffic incidents sequentially during the incident clearance period is helpful in deploying efficient measures and minimizing traffic congestion related to such incidents. This study proposes a competing risk mixture hazard-based model to analyze the effect of various factors on traffic incident duration and predict the duration sequentially. First, topic modeling, a text analysis technique, is used to process the textual features of the traffic incident to extract time-dependent topics. Given four specific clearance methods and the uncertainty of these methods when used during traffic incidents, the proposed mixture model uses the multinomial logistic model and parametric hazard-based model to assess the influence of covariates on the probability of clearance methods and on the duration of the incident. Subsequently, the performance of estimated mixture model in sequentially predicting the incident duration is compared with that of the non-mixture model. The prediction results show that the presented mixture model outperforms the non-mixture model.     

A car-following model considering asymmetric driving behavior based on long short-term memory neural networks

Asymmetric driving behavior is a critical characteristic of human driving behaviors and has a significant impact on traffic flow. In consideration of the asymmetric driving behavior, this paper proposes a long short-term memory (LSTM) neural networks (NN) based car-following (CF) model to capture realistic traffic flow characteristics by incorporating the driving memory. The NGSIM data are used to calibrate and validate the proposed CF model. Meanwhile, three characteristics closely related to the asymmetric driving behavior are investigated: hysteresis, discrete driving, and intensity difference. The simulation results show the good performance of the proposed CF model on reproducing realistic traffic flow features. Moreover, to further demonstrate the superiority of the proposed CF model, two other CF models including recurrent neural network based CF model and asymmetric full velocity difference model, are compared with LSTM-NN model. The results reveal that LSTM-NN model can capture the asymmetric driving behavior well and outperforms other models.     

Dynamic network loading: A stochastic differentiable model that derives link state distributions

We present a dynamic network loading model that yields queue length distributions, accounts for spillbacks, and maintains a differentiable mapping from the dynamic demand on the dynamic queue lengths. The model also captures the spatial correlation of all queues adjacent to a node, and derives their joint distribution. The approach builds upon an existing stationary queueing network model that is based on finite capacity queueing theory. The original model is specified in terms of a set of differentiable equations, which in the new model are carried over to a set of equally smooth difference equations. The physical correctness of the new model is experimentally confirmed in several congestion regimes. A comparison with results predicted by the kinematic wave model (KWM) shows that the new model correctly represents the dynamic build-up, spillback and dissipation of queues. It goes beyond the KWM in that it captures queue lengths and spillbacks probabilistically, which allows for a richer analysis than the deterministic predictions of the KWM. The new model also generates a plausible fundamental diagram, which demonstrates that it captures well the stationary flow/density relationships in both congested and uncongested conditions.     

New insights on random regret minimization models

This paper develops new methodological insights on Random Regret Minimization (RRM) models. It starts by showing that the classical RRM model is not scale-invariant, and that – as a result – the degree of regret minimization behavior imposed by the classical RRM model depends crucially on the sizes of the estimated taste parameters in combination with the distribution of attribute-values in the data. Motivated by this insight, this paper makes three methodological contributions: (1) it clarifies how the estimated taste parameters and the decision rule are related to one another; (2) it introduces the notion of “profundity of regret”, and presents a formal measure of this concept; and (3) it proposes two new family members of random regret minimization models: the μRRM model, and the Pure-RRM model. These new methodological insights are illustrated by re-analyzing 10 datasets which have been used to compare linear-additive RUM and classical RRM models in recently published papers. Our re-analyses reveal that the degree of regret minimizing behavior imposed by the classical RRM model is generally very limited. This insight explains the small differences in model fit that have previously been reported in the literature between the classical RRM model and the linear-additive RUM model. Furthermore, we find that on 4 out of 10 datasets the μRRM model improves model fit very substantially as compared to the RUM and the classical RRM model.     

Validation of an extended discrete first-order model with variable speed limits

This paper validates the prediction model embedded in a model predictive controller (MPC) of variable speed limits (VSLs). The MPC controller was designed based on an extended discrete first-order model with a triangular fundamental diagram. In our previous work, the extended discrete first-order model was designed to reproduce the capacity drop and the propagation of jam waves, and it was validated with reasonable accuracy without the presence of VSLs. As VSLs influence traffic dynamics, the dynamics including VSLs needs to be validated, before it can be applied as a prediction model in MPC. For conceptual illustrations, we use two synthetic examples to show how the model reproduces the key mechanisms of VSLs that are applied by existing VSL control approaches. Furthermore, the model is calibrated by use of real traffic data from Dutch freeway A12, where the field test of a speed limit control algorithm (SPECIALIST) was conducted. In the calibration, the original model is extended by using a quadrangular fundamental diagram which keeps the linear feature of the model and represents traffic states at the under-critical branch more accurately. The resulting model is validated using various traffic data sets. The accuracy of the model is compared with a second-order traffic flow model. The performance of two models is comparable: both models reproduce accurate results matching with real data. Flow errors of the calibration and validation are around 10%. The extended discrete first-order model-based MPC controller has been demonstrated to resolve freeway jam waves efficiently by synthetic cases. It has a higher computation speed comparing to the second-order model-based MPC.     

CDUBGM-Markov模型在铁路客运量预测中的应用

文章在传统的灰色模型和马尔柯夫模型的基础上,提出了动态无偏灰色马尔柯夫模型,阐述了该模型的建立方法,并采用这三种模型对我国铁路客运量进行了预测,对比结果表明动态无偏灰色马尔柯夫模型的拟合效果较好,预测精度较高,是一种行之有效的预测方法。     

Modeling traffic noise in a mountainous city using artificial neural networks and gradient correction

Different regions have established traffic noise prediction models to adapt to their particular environmental characteristics. This paper aimed to develop a traffic noise prediction model for mountainous cities. In China, the traffic noise prediction model HJ 2.4-2009, which itself is based on the sound pressure level corrected for roadway gradients (RGs), has been receiving widespread acceptance. On the basis of the model in HJ 2.4-2009, the RG correction coefficient was proposed to modify the original model and a per-vehicle noise prediction model was built using a multilayer feedforward artificial neural network (ANN) model. The data collected from a municipal road of a hilly city, Chongqing, was used to train and validate the ANN model. The predictor variables comprised the per-vehicle noise value, vehicle type, vehicle velocity, and roadway gradient. The results showed that the modified HJ 2.4-2009 model incorporating the gradient correction coefficient achieved a significantly higher R² for mountainous cities than the original model. Besides, the ANN-based noise prediction model achieved considerable accuracy improvement over the empirical predictive equations.     

油气管道腐蚀速度灰色动态多级残差模型的确立及应用

为客观评价及预测油气管道的腐蚀速度和现状,人们一般采用灰色系统的GM(1,1)理论,但该方法有其固有的缺陷,预测精度不高,初始点的选择不尽合理,文中针对初始点和预测精度问题,运用最小二乘法拟合原理及残差修正理论进行了两处改进,从而提高了预测精度。最后针对某输油管道的实际监测腐蚀速度进行了分析预测,并对方法改进前后的预测结果进行了对比,可以看出预测精度大大提高。     

城市交叉口交通拥挤最大排队长度估算模型

文章针对交通波模型应用于城市道路排队长度估算所存在的问题,评述了累计到达-离去模型应用的优势。通过对累计到达-离去模型的三种变形形式的分析比较,选用出其中的一种模型为基础模型进行改进,得到城市交叉口交通拥挤最大排队长度估算模型,并通过VISSIM仿真实验验证了这一改进模型的实用性。     

Online Prediction of Travel Time: Experience From a Pilot Trial

Abstract

This study was designed to present an online model which predicted travel times on an interurban two-lane two-way highway section on the basis of field measurements. The study included two parts: an evaluation of the performance of the model, and an examination of the possibility to improve the model in case of unsatisfactory performance. The model was based on MLP neural networks. The main results of the evaluation showed that the prediction model outperformed a non-predictive system. However, the model for one section had not performed as well during the trial period as was expected. This might be due to a slight change in the congestion phenomenon. After further development, the findings showed that the model could be improved considerably with new data. The main implication was that even a simple prediction model improves the quality of travel time information substantially, compared to estimates based directly on the latest measurements.     

Feedback control strategy of a new car-following model based on reducing traffic accident rates

ABSTRACT

To reduce the traffic accident death rate effectively and alleviate the traffic congestion phenomenon, this study proposes a new type of car-following model under the influence of drivers’ time-varying delay response time. Based on Lyapunov function theory, this paper reduces the traffic accident rate problem to the stability issues of the new model. By constructing suitable Lyapunov functions and using the linear matrix inequality method, the stability problem of the new car-following model is studied. The model, under the action of the controller, can effectively restrain traffic congestion. Using the traffic accident rate model proposed by Solomon, compared with the car-following model without the controller, the model under the controller shows a stronger convergence. This also means that the traffic congestion phenomenon has been effectively suppressed while greatly reducing the mortality rate of traffic accidents.