Large-Scale Traffic Network Control Based on Mixed Integer Non-linear System Formulation

This paper presents a new framework for traffic flow control based on an integrated model description by means of a Hybrid Dynamical System (HDS). The geometrical information on the traffic network is characterized by a Hybrid Petri Net (HPN). Then, the algebraic behavior of traffic flow is transformed into a Mixed Logical Dynamical System (MLDS) form in order to introduce an optimization technique. These expressions involve both continuous evolution of traffic flow and event driven behavior of traffic light. HPN allows us to formulate the problem easily for complicated and large-scale traffic network due to its graphical understanding. MLDS enables us to optimize the control policy for traffic light by means of its algebraic manipulability and use of model predictive control framework. Since the behavior represented by HPN can be directly transformed into corresponding MLDS form, the seamless incorporation of two different modeling schemes provide a systematic design scenario for traffic flow control.

This paper proposes an effective control system for a container crane that takes into account disturbances such as a wind. For efficient crane operation, it is necessary to realize accurate positioning of cranes, to minimize oscillation of containers and to realize the fastest possible control time while they are being carried. The crane input is assumed to be a binary with maximum and minimum values for quick control. The entire crane system including the binary input is considered as a hybrid system. A hybrid system is a generic term for a system in which continuous and discrete dynamics exist together. We control the entire crane system using the Mixed Logical Dynamical (MLD) system. An MLD system, which is a representation method for a hybrid system, is used for the crane system. It is generally known that an MLD system can be controlled by Model Predictive Control (MPC). We confirm the effectiveness of the proposed technique through computer simulation of the crane.

Traffic control at road intersections is based on traffic lights (TLs). The control mechanism typically used for traffic lights operates based on a periodic schedule to change the light (red/yellow/green). In many cases, a different schedule is used in late night/early morning hours. This fixed control mechanism does not adequately account for changing traffic conditions, and is unaware of/unresponsive to congestion. In this work, we propose a framework for dynamic traffic light control at intersections. The framework relies on a simple sensor network to collect traffic data and includes novel protocols for traffic flow control to handle congestion and facilitate flow. We show that our proposed algorithms have low overhead and are practical to employ in live traffic flow scenarios. Through extensive simulations, we demonstrate the benefits of our framework in optimizing traffic flow metrics, such as traffic throughput, average vehicle waiting time, and vehicle waiting line length.

The main technological barrier in the commercialization of fuel cells lies in the difficulty of on-board hydrogen storage, especially for portable applications. The technology adopted in this paper to overcome this drawback is to store hydrogen indirectly, in a hydrocarbon form. The stored hydrocarbon fuel can be converted to a hydrogen-rich stream utilizing an autothermal reformer. Pure hydrogen gas can be separated from the gas mixtures exiting the reformer by passing it through a palladium membrane-based gas separation unit. The purified hydrogen gas can be fed to the fuel cell anode and air to the cathode to generate power. A battery unit is considered that serves as a supplementary power source to assist the fuel cell to deliver delay free power, in the presence of uncertainties in the external load. This work basically focuses on the dynamic mathematical modeling and advanced, optimization based control of the integrated reformer–membrane–fuel cell–battery hybrid power system. This work is an extension to an earlier work, where dynamic analysis and basic control studies of the integrated system without a battery unit, were examined. This paper includes a battery unit along with the fuel cell in order to meet the power demand, especially during sudden load fluctuations and plant startup. The presence of two energy sources to control the uncertainty in demand leads to the formation of a mixed logical dynamical (MLD) system. The control of such a MLD system has been attempted in a model predictive control (MPC) framework in this paper. This resulting advanced control scheme has been implemented on the hybrid system to analyze the performance for a representative power application.

With rapid advancements in transportation, issues related to traffic congestion, scheduling, and management have become increasingly prominent. Traffic flow prediction serves as a key support tool for traffic scheduling and management, making it a primary focus of research in intelligent transportation systems. Given the complex spatio-temporal nature of traffic data, effective modeling for large-scale traffic flow prediction presents a significant challenge. This study proposes a large-scale traffic flow prediction neural network based on an AI-driven Encoder-Decoder architecture. The network utilizes adaptive convolutional layers to capture spatial features and Gated Recurrent Units to model temporal dependencies, achieving efficient spatio-temporal representation of traffic flow. Tested on a large-scale traffic flow prediction network, we processed and compared with other models, the proposed network demonstrates strong predictive performance, enhancing the accuracy of urban traffic flow forecasting on a large scale.

On-line distributed prediction of traffic flow in a large-scale road network

Introduction Drag on city traffic has escalated to be a pivotal problem in almost all cities in the world, and commuter travel time, fuel consumption and emission have also soared. Fixed-time signal control systems have been traditionally used in traffic signal control, but their optimality highly depends on the time of day they are applied and they are not capable of real-time traffic control. In order to overcome these drawbacks, intelligent and adaptive traffic control approaches are being explored by both scientists and traffic developers. Objective The purpose of this research is to create and assess a dynamic traffic light control system by utilizing Snake Optimization (SO), a novel meta-heuristic algorithm. In order to minimize vehicle queues, cut down on delays, and enhance overall traffic flow, the main goal is to examine how well SO optimizes traffic signal timings based on real-time traffic data. by contrasting conventional static control techniques and meta-heuristics with the SO-based dynamic approach. Proposed Method To find the best traffic light phase durations at intersections, the suggested approach uses the Snake Optimization (SO) algorithm, a bio-inspired meta-heuristic technique. Real traffic data from the Algerian city of Algiers, which depicts realistic traffic volumes and patterns, is used to test the method. The SUMO (Simulation of Urban Mobility) simulator, an open-source program popular for simulating microscopic traffic, is used to construct the experimental framework. Traffic scenario modeling, control algorithm implementation, and performance evaluation in a simulated urban setting are all made possible by SUMO. The following steps are part of the optimization process: gathering of data, using the SUMO simulator to model traffic flow and intersections, incorporating the SO algorithm to modify traffic light timings in real time in response to inputs, evaluation of performance using metrics like vehicle throughput, average waiting time, reduction of CO2 emission and total travel time, and evaluation of the benefits obtained by the SO-based approach through comparison with a baseline static control system and ACO-DSOS meta-heuristic. Conclusion According to the simulation results, the suggested approach, which is based on the Snake Optimization algorithm, performs better than other meta-heuristics and conventional static control systems. The algorithm's effectiveness in controlling traffic flows is validated by quantitative comparisons. According to the study's findings, SO is a practical and successful strategy for maximizing traffic light control in practical settings.

Traffic problems often occur due to the traffic demands by the outnumbered vehicles on road. Maximizing traffic flow and minimizing the average waiting time are the goals of intelligent traffic control. Each junction wants to get larger traffic flow. During the course, junctions form a policy of coordination as well as constraints for adjacent junctions to maximize their own interests. A good traffic signal timing policy is helpful to solve the problem. However, as there are so many factors that can affect the traffic control model, it is difficult to find the optimal solution. The disability of traffic light controllers to learn from past experiences caused them to be unable to adaptively fit dynamic changes of traffic flow. Considering dynamic characteristics of the actual traffic environment, reinforcement learning algorithm based traffic control approach can be applied to get optimal scheduling policy. The proposed Sarsa(λ)-based real-time traffic control optimization model can maintain the traffic signal timing policy more effectively. The Sarsa(λ)-based model gains traffic cost of the vehicle, which considers delay time, the number of waiting vehicles, and the integrated saturation from its experiences to learn and determine the optimal actions. The experiment results show an inspiring improvement in traffic control, indicating the proposed model is capable of facilitating real-time dynamic traffic control.

A hybrid modelling framework for the estimation of dynamic origin–destination flows

STEPPING OVER EXCESS OF OBSTACLE FOR BIPED ROBOT BASED ON HYBRID CONTROL

The conventional traffic light control frameworks are governed by fixed time interims of the traffic lights. These traditional fixed traffic light controllers have certain constraints and are less effective on the grounds that they utilize an equipment, which have capacities as indicated by the program that comes up with limitations of the inconsistent adaptability of adjustments. Along these lines, due to the fixed time interims of green and red signs, there is overabundance average waiting time and superfluous holding up time on lanes, due to which vehicles tend to devour more fuel. This in the long run indicates the ecological contamination and makes a few medical related problems among the individuals on street and living close by, as they tend to inhale the impure air. Likewise, these customary traffic light control frameworks do not have any advancements or arrangements to give any data on traffic densities on different streets, which prompt traffic clogs. Consequently, to make the traffic light scheme control and traffic guideline progressively productive, the proposed work makes use of the development of a novel strategy called as Adaptive Traffic Light Control System, modelled with highly proficient framework. The proposed framework utilizes a complete system of cluster of sensors for detecting the traffic with priority based traffic management. On positioning this effectively detected traffic, the planning interims of red and green light signals across the streets are cleverly chosen and changed in order to keep the holding up time least. In this way, enhancement of the traffic light with periodically exchanges, builds the street limit, spares time for voyaging and forestalls traffic blockages. The traffic related details are intermittently updated to the multi-cloud environment. The model is assessed by means of rebuilding in the Simulation of Urban Mobility framework (SUMO) in a vehicular system using Reinforced Decision Process (RDP), and the reenactment results show the significantly improved efficiency of the model in controlling and regulating the traffic with dynamic and self-adaptive management.

Co-evolutionary traffic signal control using reinforcement learning for road networks under stochastic capacity

Traffic lights at crossroads help regulate the flow of vehicles so they can run smoothly and avoid congestion. One of the causes of traffic congestion is a traffic control light system that is not optimal because it still uses a fixed timer system, so the lights' duration is less efficient in its application. When the green light is on, the streets are deserted. But there is a traffic jam on another road. Therefore the concept of traffic light timing needs to be developed to get efficient timing. This study aims to create a traffic light control system that uses a PIR (Passive Infrared) motion sensor and an ultrasonic sensor based on the Arduino Mega2560 microcontroller based on the congestion level. The method used in this traffic control prototype is an experimental method of reading vehicle objects mounted with PIR sensors and ultrasonic sensors. This system can detect the movement of vehicles approaching a traffic light, measure the distance between the car and the traffic light, and set the timing of the light signal according to the level of congestion detected. This system has been tested using vehicle movement simulations brought closer to the PIR and ultrasonic sensors at different distances. The test results show the system can work properly and produce the light signal according to the detected traffic conditions. For its application to traffic lights in the future, it is feasible to help the traffic unit.

Introduction. Problematic sections of the road network are intersections with high traffic intensity of conflicting pedestrian and traffic flow, in particular, right and left turns. At such crossings, there are significant traffic delays. In the case of vehicles turning left or right at an intersection when passing at a traffic light signal that allows traffic, should give way to pedestrians crossing the roadway on the crosswalk. In the case of high intensity of pedestrian traffic, it is impossible to complete the turn of such vehicles, they remain at the intersection, so there are significant traffic delays for returning vehicles.Purpose. Therefore, the work aims to study the interaction of traffic and pedestrian flows with high intensity at regulated intersections to improve their capacity.Methods. To study the parameters of traffic flows, in particular, the length of congestion, we used traffic flow models, which include a psychophysiological model of following a vehicle moving in front, and a model based on traffic rules. To model, pedestrian flows the Wiedemann model was used. The leastsquares method was used to obtain empirical nonlinear dependences of congestion length on the intensities of conflicting pedestrian and traffic flows.Results. The paper uses known methods for solving applied problems in the field of traffic for some unique cases, namely the intersection of intensive -traffic and pedestrian flows. Studies of road and pedestrian traffic parameters at crossings have shown that the length of congestion significantly depends on the intensity of traffic flow, but with increas-ing intensity of pedestrian traffic more than 1000 people/h, the length of congestion changes insignificantly. If there are trams at the intersection, the length of congestion increases by an average of 1.14% and depends significantly on the intensity of traffic and pedestrian flows.It is proposed to introduce three-phase traffic light regulation on such sections when one of the phases allows traffic only for pedestrians. The simulation results showed that the length of congestion in the absence of rail vehicles on the approaches to the intersection decreases by an average of 45.3% and is weakly dependent on the intensity of pedestrian flows. If there are rail vehicles at the crossing, the length of congestion can reduce by an average of 13.7%. But in some cases may increase.Conclusion. The research methodology presented in this paper can be used for intersections with another traffic organization scheme to justify the feasibility of introducing threephase traffic light control when one of the phases allows traffic only to pedestrians.

Efficient traffic control and management is a fundamental and urgent challenge in our ever-growing cities. Maximizing roadway capacity usage, balancing traffic flows, decreasing emission, improving traffic safety and providing motorists with the best end-to-end transportation experience are the most important goals of modern intelligent traffic control infrastructures. Evolving traffic light or traffic signal controller systems are playing an important role in these architectures by adaptively and dynamically coordinating individual traffic lights to achieve city-wide objectives of traffic operations. The integration of such systems with vehicle-to-vehicle (V2V) and vehicle-to- infrastructure (V2I) communication techniques (together referred as V2X) could easily be the next step of this evolution allowing for dynamic real-time information exchange between all the players of the traffic controlling ecosystem and fostering cooperative urban mobility. In this paper we propose a possible architecture for a V2X-integrated traffic light controller systems and present the testbed with our proof-of-concept implementation of the proposed scheme.