Showing papers by "Vadim Sokolov published in 2016"

POLARIS: Agent-based modeling framework development and implementation for integrated travel demand and network and operations simulations

Abstract: This paper discusses the development of an agent-based modeling software development kit, and the implementation and validation of a model using it that integrates dynamic simulation of travel demand, network supply and network operations. A description is given of the core utilities in the kit: a parallel discrete event engine, interprocess exchange engine, and memory allocator, as well as a number of ancillary utilities: visualization library, database IO library, and scenario manager. The overall framework emphasizes the design goals of: generality, code agility, and high performance. This framework allows the modeling of several aspects of transportation system that are typically done with separate stand-alone software applications, in a high-performance and extensible manner. The issue of integrating such models as dynamic traffic assignment and disaggregate demand models has been a long standing issue for transportation modelers. The integrated approach shows a possible way to resolve this difficulty. The simulation model built from the POLARIS framework is a single, shared-memory process for handling all aspects of the integrated urban simulation. The resulting gains in computational efficiency and performance allow planning models to be extended to include previously separate aspects of the urban system, enhancing the utility of such models from the planning perspective. Initial tests with case studies involving traffic management center impacts on various network events such as accidents show the potential of the system.

Coordinated Platoon Routing in a Metropolitan Network.

Abstract: Platooning vehicles—connected and automated vehicles traveling with small intervehicle distances—use less fuel because of reduced aerodynamic drag. Given a network defined by vertex and edge sets and a set of vehicles with origin/destination nodes/times, we model and solve the combinatorial optimization problem of coordinated routing of vehicles in a manner that routes them to their destination on time while using the least amount of fuel. Common approaches decompose the platoon coordination and vehicle routing into separate problems. Our model addresses both problems simultaneously to obtain the best solution. We use modern modeling techniques and constraints implied from analyzing the platoon routing problem to address larger numbers of vehicles and larger networks than previously considered. While the numerical method used is unable to certify optimality for candidate solutions to all networks and parameters considered, we obtain excellent solutions in approximately one minute for much larger networks and vehicle sets than previously considered in the literature.

Deep Learning Predictors for Traffic Flows

Abstract: We develop a deep learning model to predict traffic flows. The main contribution is development of an architecture that combines a linear model that is fitted using $\ell_1$ regularization and a sequence of $\tanh$ layers. The challenge of predicting traffic flows are the sharp nonlinearities due to transitions between free flow, breakdown, recovery and congestion. We show that deep learning architectures can capture these nonlinear spatio-temporal effects. The first layer identifies spatio-temporal relations among predictors and other layers model nonlinear relations. We illustrate our methodology on road sensor data from Interstate I-55 and predict traffic flows during two special events; a Chicago Bears football game and an extreme snowstorm event. Both cases have sharp traffic flow regime changes, occurring very suddenly, and we show how deep learning provides precise short term traffic flow predictions.

Bayesian Particle Tracking of Traffic Flows

Abstract: The authors develop a Bayesian particle filter for tracking traffic flows that is capable of capturing non- linearities and discontinuities present in flow dynamics Their model includes a hidden state variable that captures sudden regime shifts between traffic free flow, breakdown and recovery The authors develop an efficient particle learning algorithm for real time on-line inference of states and parameters This requires a two step approach, first, resampling the current particles, with a mixture predictive distribution and second, propagation of states using the conditional posterior distribution Particle learning of parameters follows from updating recursions for conditional sufficient statistics To illustrate their methodology, the authors analyze measurements of daily traffic flow from the Illinois inter- state I-55 highway system They demonstrate how their filter can be used to inference the change of traffic flow regime on a highway road segment based on a measurement from freeway single-loop detectors Finally, they conclude with directions for future research

Assessing the regional energy impact of connected vehicle deployment

Abstract: Connected and automated vehicle technologies are likely to have significant impacts on not only how vehicles operate within the transportation system, but also on how individuals behave and utilize their vehicles. While many connected and autonomous vehicle technologies have the potential to increase network throughput and/or efficiency, i.e. connected adaptive cruise control, eco-signals, many of these same technologies have a secondary effect of reducing driver burden which can drive changes in travel behaviour. Such changes in travel behaviour, in effect lowering the cost of driving, have the potential to greatly increase the utilization of the transportation systems with concurrent negative externalities such as congestion, energy use, emissions, and so on, working against the positive effects on the transportation system due to increased capacity. To date relatively few studies have analysed the potential impacts on CAV technologies from a systems perspective, often focusing on gains and losses to an individual vehicle, at a single intersection, or along a corridor. However, travel demand and traffic flow is a complex, adaptive, non-linear system, so in this study we use an advanced transportation systems simulation model, POLARIS, which includes cosimulation of travel behaviour and traffic flow, to study potential impacts of several connected and automated vehicle technologies at the regional-level. We have analysed potential impacts, in terms of changes in vehicle miles travelled, over various market penetration levels for a feasible range of changes in travel time sensitivity to determine a potential range of VMT impacts from CAV. © 2017 The Authors. Published by Elsevier B.V. Peer-review under responsibility of WORLD CONFERENCE ON TRANSPORT RESEARCH SOCIETY.

A Disaggregate Model System for Assessing the Energy Impact of Transportation at the Regional Level

Abstract: This paper demonstrates how a powertrain simulation software that is usually applied to study a given vehicle technology on a predefined drive cycle can be used to study realistic complex transportation systems, through application to a case study involving Variable Message Signs (VMS) in the Chicago central business district as part of an Advanced Traveler Information System (ATIS). The authors demonstrate that an energy impact associated with ATIS can be estimated though simulation and that energy should be one of the metrics that is applied to studying ITS technologies by looking at each individual vehicle in a context of a complex system. It is possible to study impacts of ITS technologies on transportation systems not only by using aggregate measures such as vehicle miles traveled but by doing more precise microscopic simulation, which is sensitive to many parameters that cannot be represented in a framework that relies on VMT.

Addressing Some Issues of Map-Matching for Large-Scale, High-Frequency GPS Data Sets

Abstract: Data from GPS-enabled vehicles has become more and more widely used by travel-behavior researchers and transportation system modelers. However as the GPS data has measurement and sampling errors it becomes a non-trivial task to infer a map feature associated with a sequence of GPS measurements, especially as maps features may also have inaccuracies. The task of assigning a set of GPS points to a set of map features is called the map matching problem, and the requirement for the assigned features to form a consistent travel route adds additional complexity. The majority of the existing algorithms concentrate on scenarios when sampling rate is low and/or measurement error is high. However, as GPS devices become more accurate and sampling rate becomes higher, a new issue arises, the issue of efficiently of analyzing large scale high frequency GPS data sets. In this paper the authors analyze a high-accuracy and high-frequency GPS data set collected from instrumented vehicles that participated in Safety Pilot Model Deployment project using a modified version of the Multiple Hypothesis Technique to match network links, with accuracy and computational efficiency being the focus. The authors build on previous work in several ways: (i) the authors proposed a speed-up step that significantly reduces the number of candidate paths, (ii) the authors improved the way GPS trace segments are matched to road network at turns and intersections and(iii) the authors added new filtering step to identify U-Turn movements. In addition to these improvements, the authors demonstrate the process of manually fitting the parameters of the algorithm and suggest future direction on how the process of parameter training can be automated.

Assessing the energy impact of traffic management and vehicle hybridisation

Abstract: We provide a review of methodologies previously used to evaluate impacts of transportation systems and changes in transportation infrastructure on energy consumption. We present a new framework that allows estimating the energy impacts of managed traffic lanes in the context of vehicle automation. The presented framework relies on two major components, an integrated transportation system simulator and a powertrain simulator. For the transportation system simulator we propose using integrated transportation system simulator POLARIS. For the powertrain simulator we use AUTONOMIE, a tool funded by the US Department of Energy. Both tools are developed at Argonne National Laboratory. We demonstrate our approach by modelling a transportation corridor along a major highway. Two scenarios are considered, unmanaged, when both trucks and cars use all the lanes of the highway and managed, under which one of the highway lanes is a dedicated lane for truck traffic and trucks are forming platoons using adaptive cruise control technology. We provide the numerical results of the experiment at the end of the paper. We also present the impact of vehicle hybridisation combined with automation on the energy consumption.

Sequential Bayesian Learning for Merton's Jump Model with Stochastic Volatility

Abstract: Jump stochastic volatility models are central to financial econometrics for volatility forecasting, portfolio risk management, and derivatives pricing. Markov Chain Monte Carlo (MCMC) algorithms are computationally unfeasible for the sequential learning of volatility state variables and parameters, whereby the investor must update all posterior and predictive densities as new information arrives. We develop a particle filtering and learning algorithm to sample posterior distribution in Merton's jump stochastic volatility. This allows to filter spot volatilities and jump times, together with sequentially updating (learning) of jump and volatility parameters. We illustrate our methodology on Google's stock return. We conclude with directions for future research.