Evolutionary minimization of traffic congestion (original) (raw)
Related papers
Optimising Real-world Traffic Cycle Programs by Using Evolutionary Computation
IEEE Access
Traffic congestion, and the consequent loss of time, money, quality of life and higher pollution, is currently one of the most important problems in cities, and several approaches have been proposed to reduce it. In this paper we propose a novel formulation of the Traffic Light Scheduling Problem in order to alleviate it. This novel formulation of the problem allows more realistic scenarios to be modelled, and as a result, it becomes much harder to solve in comparison to previous formulations. The proposal of more advanced and efficient techniques than those applied in past research is thus required. We propose the application of diversity-based multi-objective optimisers, which have shown to provide promising results when addressing singleobjective problems. The wide experimental evaluation performed over a set of real-world instances demonstrates the good performance of our proposed diversity-based multi-objective method to tackle traffic at a large scale, especially in comparison to the best-performing single-objective optimiser previously proposed in the literature. Consequently, in this work, we provide new state-of-the-art algorithmic schemes to address the traffic light scheduling problem that can deal with a whole city, instead of just a few streets and junctions, with a higher level of detail than the one found in present studies due to our micro-analysis of streets.
Road Traffic Optimisation Using an Evolutionary Game
In a commuting scenario, drivers expect to arrive at their destinations on time. Drivers have an expectation as to how long it will take to reach the destination. To this end, drivers make independent decisions regarding the routes they take. Independent decision-making is uncoordinated and unlikely to lead to a balanced usage of the road network. However, a well-balanced traffic situation is in the best interest of all drivers, as it minimises their travel times on average over time. This study investigates the possibility of using an Evolutionary Game, Minority Game (MG), to achieve a balanced usage of a road network through independent decisions made by drivers assisted by the MG algorithm. The experimental results show that this simple gametheoretic approach can achieve a near-optimal distribution of traffic in a network. An optimal distribution can be assumed to lead to equitable travel times which are close to the possible minimum considering the number of cars in the network.
AETROS: Adaptive Evolutionary Travel Route Optimization System
In the last decades modern cities have improved their facilities making them very comfortable for citizens. However, there is one area where much work is still pending: that is mobility. As both population and economical activity rise year by year, metropolises need higher capacity and more efficient traffic infrastructures. Specially in Latin countries, private use stills being a big component of traffic.
A hybrid genetic algorithm for road congestion minimization
2009
ABSTRACT One of the main goals in a transportation planning process is to achieve solutions for two classical problems: the traffic assignment problem, which minimizes the total travel delay among all travelers, and the toll pricing problem which settles, based on data derived from the first problem, the tolls that would collectively benefit all travelers and would lead to a user equilibrium solution. Acquiring precision for this framework is a challenge for large networks.
Advances in Engineering Software
Traffic flow is considered as a stochastic process in road traffic modeling. Computer simulation is a widely used tool to represent traffic system in engineering applications. The increased traffic congestion in urban areas and their impacts require more efficient controls and management. While the effectiveness of control schemes highly depends on accurate traffic model and appropriate control settings, optimization techniques play a central role for determining the control parameters in traffic planning and management applications. However, there is still a lack of research effort on the scientific computing framework for optimizing traffic control and operations and facilitating real planning and management applications. To this end, the present study proposes a model-based optimization framework to integrate essential components for solving road traffic control problems in general. In particular, the framework is based on traffic simulation models, while the solution needs extensive computation during the engineering optimization process. In this work, an advanced genetic algorithm, extended by an external archive for storing globally elite genes, governs the computing framework, and in application it is further enhanced by a sampling approach for initial population and utilizations of adaptive crossover and mutation probabilities. The final algorithm shows superior performance than the ordinary genetic algorithm because of the reduced number of fitness function evaluations in engineering applications. To evaluate the optimization algorithm and validate the whole software framework, this paper illustrates a detailed application for optimization of traffic light controls. The study optimizes a simple road network of two intersections in Stockholm to demonstrate the model-based optimization processes as well as to evaluate the presented algorithm and software performance.
Cogent Engineering, 2018
This work investigates levels of service in urban transportation coupling a multi-objective evolutionary algorithm with the multi-agent traffic simulator MATSim. The evolutionary algorithm searches combinations of the number of private/public transportation users, capacity of buses, and time interval between bus departures minimizing traffic density and travel time simultaneously. MATSim simulates the movement of 27,000 agents according to the solutions of the evolutionary algorithm on a model of the traffic network of Quito city. We study the trade-off in objectives and analyze the solutions produced to gain knowledge about the conditions to achieve different levels of service. Also, we analyze fuel consumption and particulate matter emissions for the trade-off solutions. This work is useful for decision makers to suggest policies that can improve mobility combining private and public transportation.
A hybrid genetic algorithm for road
2010
One of the main goals in a transportation planning process is to achieve solutions for two classical problems: the traffic assignment problem, which minimizes the total travel delay among all travelers, and the toll pricing problem which settles, based on data derived from the first problem, the tolls that would collectively benefit all travelers and would lead to a user equilibrium solution. Acquiring precision for this framework is a challenge for large networks. In this article, we propose an approach to solve the two problems jointly, making use of a Hybrid Genetic Algorithm for the optimization of transportation network performance by strategically allocating tolls on some of the links. Since a regular transportation network may have thousands of intersections and hundreds of roads, our algorithm takes advantage of mechanisms for speeding up shortest path algorithms.
New heuristic and evolutionary operators for the multi-objective urban transit routing problem
2013 IEEE Congress on Evolutionary Computation, 2013
The urban transit routing problem (UTRP) involves finding efficient routes in a public transport system. However, developing effective heuristics and metaheuristics for the UTRP is hugely challenging because of the vast search space and multiple constraints that make even the attainment of feasible results exceedingly difficult, as the problem size increases. Moreover, progress with academic research on the UTRP appears to be seriously hampered by: 1) a lack of benchmark data, and 2) the complex and diverse range of methods used in the literature to evaluate solution quality. It is not currently possible for researchers to effectively compare the performance of their algorithms with anyone else's. This paper presents new problemspecific genetic operators within a multi-objective evolutionary framework, and furthermore proposes an effective and efficient heuristic method for seeding the population with feasible route sets. In addition new data sets are provided and made available for download, to aid future researchers. Excellent results are presented for Mandl's problem, which is currently the only benchmark available, while the results obtained for the new data sets provide a challenge for future researchers to beat.
Simulation-Driven Multi-objective Evolution for Traffic Light Optimization
Lecture Notes in Computer Science, 2020
The constant growth of vehicles circulating in urban environments poses a number of challenges in terms of city planning and traffic regulation. A key aspect that affects the safety and efficiency of urban traffic is the configuration of traffic lights and junctions. Here, we propose a general framework, based on a realistic urban traffic simulator, SUMO, to aid city planners to optimize traffic lights, based on a customized version of NSGA-II. We show how different metrics-such as number of accidents, average speed of vehicles, and number of traffic jams-can be taken into account in a multi-objective fashion to obtain a number of Pareto-optimal light configurations. Our experiments, conducted on two city scenarios in Italy and different combinations of fitness functions, demonstrate the validity of this approach and show how evolutionary optimization is an effective tool for traffic light optimization.