Traffic Demand Fluctuations Research Articles

Research on Dynamic Subsidy Based on Deep Reinforcement Learning for Non-Stationary Stochastic Demand in Ride-Hailing

The ride-hailing market often experiences significant fluctuations in traffic demand, resulting in supply-demand imbalances. In this regard, the dynamic subsidy strategy is frequently employed by ride-hailing platforms to incentivize drivers to relocate to zones with high demand. However, determining the appropriate amount of subsidy at the appropriate time remains challenging. First, traffic demand exhibits high non-stationarity, characterized by multi-context patterns with time-varying statistical features. Second, high-dimensional state/action spaces contain multiple spatiotemporal dimensions and context patterns. Third, decision-making should satisfy real-time requirements. To address the above challenges, we first construct a Non-Stationary Markov Decision Process (NSMDP) based on the assumption of ride-hailing service systems dynamics. Then, we develop a solution framework for the NSMDP. A change point detection method based on feature-enhanced LSTM within the framework can identify the changepoints and time-varying context patterns of stochastic demand. Moreover, the framework also includes a deterministic policy deep reinforcement learning algorithm to optimize. Finally, through simulated experiments with real-world historical data, we demonstrate the effectiveness of the proposed approach. It performs well in improving the platform’s profits and alleviating supply-demand imbalances under the dynamic subsidy strategy. The results also prove that a scientific dynamic subsidy strategy is particularly effective in the high-demand context pattern with more drastic fluctuations. Additionally, the profitability of dynamic subsidy strategy will increase with the increase of the non-stationary level.

A spatiotemporal control method at isolated intersections under mixed‐autonomy traffic conditions

AbstractWith the introduction of connected and automated vehicles (CAVs), the integrated control of traffic signals, lane assignments, and vehicle trajectories becomes feasible, offering notable benefits for enhancing intersection operations. However, during the prolonged transition to an entirely CAV environment, how to fully leverage the advantage of CAVs while considering the characteristics of human‐driven vehicles remains a huge challenge. To address this challenge, this paper proposes a joint optimization method for spatiotemporal resources at isolated intersections under mixed‐autonomy traffic conditions. Initially, the lane assignment optimization problem is modeled as a mixed integer linear program model to maximize the reserve capacity. Subsequently, the signal‐vehicle coupled control is formulated as a dynamic programming model with the objective of reducing vehicle travel time. Additionally, criteria are established to assess the need for re‐optimizing lane assignments. Simulations validate the superiority of the proposed control method over adaptive control in terms of traffic efficiency and intersection capacity amid substantial traffic demand fluctuations. Sensitivity analyses reveal that the proposed control method can yield higher benefits under medium traffic demand levels. Furthermore, the proposed algorithm exhibits no significant sensitivity to the CAV market adoption rate, suggesting its applicability throughout the CAV adoption process.

A Queuing Model for Mixed Traffic Flows on Highways considering Fluctuations in Traffic Demand

Modelling the mixed traffic flows of autonomous vehicles (AVs) and human-driven vehicles (HVs) on highways is challenging. Randomness, fluctuations, and congestion exist in the mixed traffic flows. This paper extends the current literature by proposing an M/G(n)/c/c state-dependent queuing model operating in a random environment. The fluctuating traffic demand is addressed by arrival rates modulated by the random environment. Meanwhile, a Markovian arrival process (MAP) is incorporated to describe the platoons. We investigate the performance of the mixed traffic flow under the I policy (AVs and HVs travel together in all lanes) and the D policy (one lane is designated to AVs). Numerical experiments reveal the following interesting findings: (1) the fluctuation degree of traffic demand, the traffic intensity, and the penetration rate of AVs play essential roles in determining the performance of mixed traffic flows. (2) The I policy should always be adopted if the travel time is more valuable. In terms of output rate, the choice between the I and the D policies depends on the traffic intensity, SCV of arrival rates and penetration rate. (3) A larger penetration rate is required to completely eliminate congestion on a longer highway segment.

Dynamic Traffic Engineering Considering Service Grade in Integrated Service Network

This study proposes a dynamic traffic engineering method to improve network resource utilization efficiency without affecting important services in an integrated service network where multiple grades of service are accommodated. Network resource utilization is biased over time because future fluctuations in traffic demand are unpredictable. Although a service network provider prefers to re-optimize network resource utilization using a dynamic traffic engineering, it is often superfluous for users who do not want their mission-critical communications, for example, executive web meetings or online surgery, to be affected. Therefore, we classified traffic into very important packets and commoners, and only commoners were dynamically optimized. To classify traffic, we assigned the identifier to a packet on the application side. In this approach, only the application and edge nodes of the network required modification; the core network routers were unaffected. Furthermore, we established the architecture of the edge node using a software-defined network controller and P4 switch. We also provided an algorithm for optimization based on linear programming and demonstrated that it is possible to improve network resource utilization efficiency without affecting very important packets and that the computational and memory costs are practical.

Modeling adaptive reversible lanes: A cellular automata approach

Dealing with traffic congestion is one of the most pressing challenges for cities. Transport authorities have implemented several strategies to reduce traffic jams with varying degrees of success. The use of reversible lanes is a common approach to improve traffic congestion during rush hours. A reversible lane can change its direction during a time interval to the more congested direction. This strategy can improve traffic congestion in specific scenarios. Most reversible lanes in urban roads are fixed in time and number; however, traffic patterns in cities are highly variable and unpredictable due to this phenomenon’s complex nature. Therefore, reversible lanes may not improve traffic flow under certain circumstances; moreover, they could worsen it because of traffic fluctuations. In this paper, we use cellular automata to model adaptive reversible lanes(aka dynamic reversible lanes). Adaptive reversible lanes can change their direction using real-time information to respond to traffic demand fluctuations. Using real traffic data, our model shows that adaptive reversible lanes can improve traffic flow up to 40% compared to conventional reversible lanes. Our results show that there are significant fluctuations in traffic flow even during rush hours, and thus cities would benefit from implementing adaptive reversible lanes.

DEVELOPMENT AND EVALUATION OF A QUICK METHOD FOR OPTIMIZING A SPACE AND SIGNAL TIMING PLAN FOR ISOLATED SIGNALIZED INTERSECTIONS

One major cause of congestion at intersections is the fluctuation of traffic demand during the day. This phenomenon necessitates developing new models that can be used to enhance the performance of signalized intersections. We suggest a quick procedure for optimizing signal timing plans after identifying the best phasing scheme and selecting optimal lane allocation (space optimization) for any volume characteristics during the day at a typical four-leg intersection. The main contribution of this study is developing a method for collectively optimizing a signal-timing plan, intersection space, and phasing scheme. TRANSYT-7F, SYNCHRO and HCS2010 were used to assess the developed models in a case study. It was found that regardless of the optimization software used for timing-plan optimization, optimizing both space and timing plan together produce significant reductions in average intersection delay compared to optimizing only the timing plan. Furthermore, this study showed that the developed model, which optimizes space and time, consistently provided better results in terms of average intersection delay compared to TRANSYT-7F, SYNCHRO and HCS2010 in the case study.

A Distributed Control Method for Urban Networks Using Multi-Agent Reinforcement Learning Based on Regional Mixed Strategy Nash-Equilibrium

Urban network traffic congestion can be caused by disturbances, such as fluctuation and disequilibrium of traffic demand. This paper designs a distributed control method for preventing disturbance-based urban network traffic congestion by integrating Multi-Agent Reinforcement Learning (MARL) and regional Mixed Strategy Nash-Equilibrium (MSNE). To enhance the disturbance-rejection performance of Urban Network Traffic Control (UNTC), a regional MSNE concept is integrated, which models the competitive relationship between each agent and its neighboring agents in order to improve the decision-making process of MARL. The learning rate is enhanced with a self-adaptive ability to avoid a local optimal dilemma; Jensen-Shannon (JS) divergence is utilized to define the learning rate of the modified MARL. A two-way rectangular grid network with nine intersections is modeled via a Cell Transmission Model (CTM). A probability distribution mechanism, which can update the turn ratio of each approach dynamically and discretely, is established to represent the segmented route-decision process of the vehicles. The effectiveness of the proposed control method is evaluated through simulations in the grid network. The results show the influence of major disturbances, such as fluctuation of vehicle arrival rate, fluctuation of traffic demand (e.g. a rapidly rising flow and extreme changes in origin-destination distribution), and disequilibrium of traffic demand (e.g. different arrival flows at each boundary of the urban network), on the performance of the suggested control method. The results can be used to improve the state of the art in order to reduce urban network traffic congestion due to these disturbances.

Robust Signal Control of Exit Lanes for Left-Turn Intersections With the Consideration of Traffic Fluctuation

Traffic throughput at intersections can be improved by using exit lanes for left-turning (EFL), tidal flow lanes near an intersection, which has been recently introduced. This paper considers the operational robustness of the EFL intersection in relation to the control scheme applied to the traffic light setting. For safety and efficiency, it is important that the tidal lanes are emptied before traffic in the opposing direction uses these lanes. Hence, the signal control should not only be optimized for the mean value but be robust for all kinds of fluctuations. This paper formulates a traffic control scheme using robust optimization, i.e. an optimization scheme which explicitly accounts for extreme events. The fluctuation of traffic is considered from three aspects: the distribution of traffic demand, the distribution of base saturation flow rate, and the distribution of actual travel speed. Via a case study and extensive numerical analysis, we find that the established robust optimization method produces an efficient design of signal control and design speed at the EFL intersection under traffic demand and supply fluctuations. Though the optimization method is now applied to intersections with an EFL, it is considered useful for all intersections with high fluctuation of traffic demand and saturation flow rate.

Developing an Eco-Driving Application for Semi-Actuated Signalized Intersections and Modeling the Market Penetration Rates of Eco-Driving

Eco-driving is one of the most effective techniques for making the transportation sector more sustainable in relation to fuel consumption and greenhouse gas emissions. Eco-driving applications guide drivers approaching signalized intersections to optimize the fuel consumption and reduce greenhouse gas emissions. Unlike pre-timed traffic signals, developing eco-driving applications for semi-actuated signals is more challenging because of variations in cycle length as a result of fluctuations in traffic demand. This paper presents a framework for developing an eco-driving application for connected/automated vehicles passing through semi-actuated signalized intersections. The proposed algorithm takes into consideration the queue effects because of traditional and connected/automated vehicles. Results showed that the fuel consumption for vehicles controlled by the developed model was 29.2% less than for the case with no control. A sensitivity analysis for the impact of market penetration (MP) indicated that the savings in fuel consumption increase with higher MP. Furthermore, when MP is greater than 50%, the model provides appreciable savings in travel times. In addition, the estimated acceleration noise for the vehicles controlled by the algorithms was 21.9% less than for the case with no control. These reductions in fuel consumption and acceleration noise demonstrate the ability of the algorithm to provide more environmentally sustainable semi-actuated signalized intersections.

A Review of the Self-Adaptive Traffic Signal Control System Based on Future Traffic Environment

The self-adaptive traffic signal control system serves as an effective measure for relieving urban traffic congestion. The system is capable of adjusting the signal timing parameters in real time according to the seasonal changes and short-term fluctuation of traffic demand, resulting in improvement of the efficiency of traffic operation on urban road networks. The development of information technologies on computing science, autonomous driving, vehicle-to-vehicle, and mobile Internet has created a sufficient abundance of acquisition means for traffic data. Great improvements for data acquisition include the increase of available amount of holographic data, available data types, and accuracy. The article investigates the development of commonly used self-adaptive signal control systems in the world, their technical characteristics, the current research status of self-adaptive control methods, and the signal control methods for heterogeneous traffic flow composed of connected vehicles and autonomous vehicles. Finally, the article concluded that signal control based on multiagent reinforcement learning is a kind of closed-loop feedback adaptive control method, which outperforms many counterparts in terms of real-time characteristic, accuracy, and self-learning and therefore will be an important research focus of control method in future due to the property of “model-free” and “self-learning” that well accommodates the abundance of traffic information data. Besides, it will also provide an entry point and technical support for the development of Vehicle-to-X systems, Internet of vehicles, and autonomous driving industries. Therefore, the related achievements of the adaptive control system for the future traffic environment have extremely broad application prospects.

Traffic-Aware Energy-Saving Base Station Sleeping and Clustering in Cooperative Networks

We consider energy efficient base station (BS) sleeping and clustering problems in cooperative cellular networks, where clusters of base stations jointly transmit to users. Our key idea of energy saving is to exploit spatio-temporal fluctuation of traffic demand, and use minimal energy to provide achievable data rate only slightly greater than varying traffic demand. However, it is highly challenging to design traffic-aware algorithms without the future traffic demand information. To overcome this difficulty, we develop joint BS sleeping and clustering algorithms using queue instead of the future traffic information. The queue length information captures spatio-temporal mismatch between traffic demand and offered data rate. For BS clustering problem, we propose an optimal algorithm under given BS sleep mode state that has polynomial complexity. We integrate the optimal clustering solution into the sleeping problem, which is a complex combinatorial problem, and develop a joint optimal clustering and sleeping algorithm with reduced complexity compared to the exhaustive search. We also develop a greedy algorithm that finds a near-optimal clustering and sleeping solution with polynomial complexity. Through extensive simulations, we show that the proposed algorithms can save significant energy when traffic load is low.

An optimization modeling of coordinated traffic signal control based on the variational theory and its stochastic extension

This study considers an optimal coordinated traffic signal control under both deterministic and stochastic demands. We first present a new mixed integer linear programming (MILP) for the deterministic signal optimization wherein traffic flow is modeled based on the variational theory and the constraints on a signal control pattern are linearly formulated. The resulting MILP has a clear network structure and requires fewer binary variables and constraints as compared with those in the existing formulations. We then extend the problem so as to treat the stochastic fluctuations in traffic demand. We here develop an accurate and efficient approximation method of expected delays and a solution method for the stochastic version of the signal optimization by exploiting the network structure of the problem. Using a set of proposed methods, we finally examine the optimal control parameters for deterministic and stochastic coordinated signal controls and discuss their characteristics.

An optimization modeling of coordinated traffic signal control based on the variational theory and its stochastic extension

Abstract: This study considers an optimal coordinated traffic signal control under both deterministic and stochastic demands. We first present a new mixed integer linear programming (MILP) for the deterministic signal optimization wherein traffic flow is modeled based on the variational theory and the constraints on a signal control pattern are linearly formulated. The resulting MILP has a clear network structure and requires fewer binary variables and constraints as compared with those in the existing formulations. We then extend the problem so as to treat the stochastic fluctuations in traffic demand. We here develop an accurate and efficient approximation method of expected delays and a solution method for the stochastic version of the signal optimization by exploiting the network structure of the problem. Using a set of proposed methods, we finally examine the optimal control parameters for deterministic and stochastic coordinated signal controls and discuss their characteristics.

Robust Optimal Lane Allocation for Isolated Intersections

AbstractLane allocation including approach and exit lane numbers and lane markings of approach lanes plays an important role in improving the capacity of an intersection. Conventional approaches for optimizing lane allocation often ignore fluctuations in traffic demand (TD). This article presents a stochastic model for robust optimal lane allocation of an isolated intersection under stochastic traffic conditions. This model is built in three steps. In the first step, an enhanced lane‐based model in the form of a binary mixed‐integer nonlinear program is proposed to optimize lane allocation and traffic signals for both vehicles and pedestrians in a unified framework under deterministic traffic conditions. In the second step, a two‐level stochastic model is developed to obtain a robust lane allocation that is less sensitive to traffic flow fluctuations considering the flexibility of traffic signals. In the third step, the two‐level model is further transformed into a TD‐based stochastic model in a two‐phase form to reduce the solution dimension for efficient computation. A TD‐based genetic algorithm procedure is presented for solvability. Numerical studies are conducted to validate the model formulations and solution algorithms.

Traffic demand-aware topology control for enhanced energy-efficiency of cellular networks

The service provided by mobile networks operated today is not adapted to spatio-temporal fluctuations in traffic demand, although such fluctuations offer opportunities for energy savings. In particular, significant gains in energy efficiency are realizable by disengaging temporarily redundant hardware components of base stations. We therefore propose a novel optimization framework that considers both the load-dependent energy radiated by the antennas and the remaining forms of energy needed for operating the base stations. The objective is to reduce the energy consumption of mobile networks, while ensuring that the data rate requirements of the users are met throughout the coverage area. Building upon sparse optimization techniques, we develop a majorization-minimization algorithm with the ability to identify energy-efficient network configurations. The iterative algorithm is load-aware, has low computational complexity, and can be implemented in an online fashion to exploit load fluctuations on a short time scale. Simulations show that the algorithm can find network configurations with the energy consumption similar to that obtained with global optimization tools, which cannot be applied to real large networks. Although we consider only one currently deployed cellular technology, the optimization framework is general, potentially applicable to a large class of access technologies.

Intersection Control and MFD Shape: Vehicle-Actuated versus Back-Pressure Control

Various studies have demonstrated that the state and dynamics of an urban network can be described by Macroscopic Fundamental Diagrams (MFD) and that MFDs can be used for perimeter flow control. Perimeter flow control aims at a higher throughput in an urban network by controlling the flow at the boundaries of sub-networks. For perimeter flow control it is desirable that the MFD has a favourable and consistent shape, independent of fluctuations in traffic demand and of intersection signal variations. From literature it is known that a consistent shape is related to the homogeneity of vehicle accumulation in the sub-network. However, also the signal controller type may influence homogeneity and the MFD shape. In this paper we investigate the relationship between the type of intersection control and the shape and scatter of the MFD, and the homogeneity of the sub-network, for Vehicle-Actuated (VA) and Back-Pressure (BP) control. The comparison of the two control methods is performed by means of microsimulation. The results show that for both control methods the free-flow branch of the MFD has a low scatter with an average relative deviation around 2%. The congested branch shows a much larger deviation, 15% for the Vehicle-Actuated control, 16% for the Back-Pressure control. Furthermore, there is a distinct difference in the shape of the MFDs: for VA control the production increases faster as function of the accumulation than for BP control, but the network breakdown starts at a lower accumulation. So, based on the simulation results, VA control is better in undersaturated situations, and BP is better at higher accumulation levels.

Robust energy-aware routing with redundancy elimination

Many studies in literature have shown that energy-aware routing (EAR) can significantly reduce energy consumption for backbone networks. Also, as an arising concern in networking research area, the protocol-independent traffic redundancy elimination (RE) technique helps to reduce (a.k.a compress) traffic load on backbone network. Motivation from a formulation perspective, we first present an extended model of the classical multi-commodity flow problem with compressible flows. Moreover, our model is robust with fluctuation of traffic demand and compression rate. In details, we allow any set of a predefined size of traffic flows to deviate simultaneously from their nominal volumes or compression rates. As an applicable example, we use this model to combine redundancy elimination and energy-aware routing to increase energy efficiency for a backbone network. Using this extra knowledge on the dynamics of the traffic pattern, we are able to significantly increase energy efficiency for the network. We formally define the problem and model it as a Mixed Integer Linear Program (MILP). We then propose an efficient heuristic algorithm that is suitable for large networks. Simulation results with real traffic traces on Abilene, Geant and Germany50 networks show that our approach allows for 16–28% extra energy savings with respect to the classical EAR model.

Urban link travel time estimation based on sparse probe vehicle data

In the urban signalized network, travel time estimation is a challenging subject especially because urban travel times are intrinsically uncertain due to the fluctuations in traffic demand and supply, traffic signals, stochastic arrivals at the intersections, etc. In this paper, probe vehicles are used as traffic sensors to collect traffic data (speeds, positions and time stamps) in an urban road network. However, due to the low polling frequencies (e.g. 1min or 5min), travel times recorded by probe vehicles provide only partial link or route travel times. This paper focuses on the estimation of complete link travel times. Based on the information collected by probe vehicles, a three-layer neural network model is proposed to estimate complete link travel time for individual probe vehicle traversing the link. This model is discussed and compared with an analytical estimation model which was developed by Hellinga et al. (2008). The performance of these two models are evaluated with data derived from VISSIM simulation model. Results suggest that the Artificial Neural Network model outperforms the analytical model.

High-performance network virtualisation for multilayer GMPLS networks

The recent trends in emerging network applications require more flexible network infrastructures. For this purpose, we consider the architecture and enabling technologies of high-performance network virtualisation using multilayer GMPLS networking technologies. The network virtualisation enables virtual network to utilise high-capacity bandwidth of optical network infrastructures without the provision of physical infrastructures. Furthermore, to improve robustness against network environmental changes such as failures and sudden traffic demand fluctuations, the network infrastructure provides virtual networks resource optimisation and on-demand resource distribution functions. One possible problem regarding virtualisation technologies lies in resource contention among multiple virtual networks sharing limited resources on the infrastructure. We thus propose a resource management model for efficient contention resolutions. We also present the design of a network virtualisation platform and the specification of interfaces to virtual network agents. We also developed prototype systems based on our system design and demonstrated the proposed high-performance lower-layer network virtualisation technologies in conjunction with commercially available routers and OXCs that support GMPLS protocols in our experimental network.

Development and Evaluation of a Stochastic Traffic Signal Optimization Method

ABSTRACT Signalized intersections are one of the most common ways of sharing right of ways among vehicular and pedestrian traffic. The design of isolated signalized intersections involves determination of signal timing plan (i.e., the cycle length, phase sequence, and green time allocation). These selections are, in general, conducted through computerized software such as Synchro and TRANSYT-7F. These programs generate optimal signal timing plans by minimizing delay obtained from either analytical models such as the Highway Capacity Manual (HCM) delay equation or traffic simulation models. One of the shortcomings in the state-of-the-practice in signal optimization is that signal timing plans do not necessarily account for day-to-day variability in traffic demand as they are developed on the basis of the average demand volumes from a day or two worth of traffic counts. This paper presents a genetic algorithm–based stochastic signal optimization method that explicitly considers variability in the HCM delay equation due to day-to-day traffic demand fluctuations. The variability in the delay arising from varying demand conditions is evaluated using an integration technique. The proposed approach was compared with Synchro, a traffic signal timing optimization software, through a stochastic microscopic simulation program, CORSIM. The simulation results indicate that signal timing plans generated from genetic algorithm (GA)-based stochastic optimization generally outperformed those from Synchro.