Simulation and evaluation of urban bus-networks using a multiagent approach

Meignan, David; Simonin, Olivier; Koukam, Abderraf́ıâa

doi:10.1016/j.simpat.2007.02.005

Cited by 91 publications

(36 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Oliveira and Duarte [12] incorporate emergency vehicle priority into their UTC system. Meignan et al [9] simulate bus network performance, modelling both buses and passenger behaviour. They account for the influence of other traffic on the bus network, but do not account for the influence of public transport on other vehicles, nor do they include traffic signal priority for public transport.…”

Section: Agent-based Traffic Control Strategiesmentioning

confidence: 99%

Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems – An Experimental Evaluation

Dusparić

Cahill

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Large-scale autonomic systems are required to self-optimize with respect to high-level policies, that can differ in terms of their priority, as well as their spatial and temporal scope. Decentralized multiagent systems represent one approach to implementing the required selfoptimization capabilities. However, the presence of multiple heterogeneous policies leads to heterogeneity of the agents that implement them. In this paper we evaluate the use of Reinforcement Learning techniques to support the self-optimization of heterogeneous agents towards multiple policies in decentralized systems. We evaluate these techniques in an Urban Traffic Control simulation and compare two approaches to supporting multiple policies. Our results suggest that approaches based on W-learning, which learn separately for each policy and then select between nominated actions based on current action importance, perform better than combining policies into a single learning process over a single state space. The results also indicate that explicitly supporting multiple policies simultaneously can improve waiting times over policies dedicated to optimizing for a single vehicle type.

show abstract

Section: Agent-based Traffic Control Strategiesmentioning

confidence: 99%

Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems – An Experimental Evaluation

Dusparić

Cahill

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…a) Data Collection Phase: Firstly, we performed a literature review for identifying problem categories addressed by means of agent based simulation approaches. The preliminary results of this research highlighted that agent based simulations are applied to solve problems in the following domains (and not only 1 ): (i) Financial Markets [15], [16] where simulations are used for studying the behavior of individual investors, the dynamics of markets, trading mechanism and so on; (ii) Urban Development [17], [18] that studies models for urban planning, city dynamics, individual residential behaviors; (iii) Traffic and Transportation [19], [20], [21] dealing with simulation models for transportation planning, design and operations; (iv) Crowd Dynamics [22], [23], [24] that studies the behaviors of individuals, groups in several critical scenarios often with the aim of buildings design; (v) Social Networks that studies the evolution and dynamics of networks [25], [26]; (vi) Logistics and Supply Chain Management that studies processes inside different nodes of supply chain or the whole supply chain in order to find the best organizational structure for collaborative companies working together [27], [28], [29]; (vii) Electric Power Engineering [30], [31], [32] deals with the generation, transmission, distribution and utilization of electric power as well as the electrical devices connected to such systems.…”

Section: A Metamodel Building Processmentioning

confidence: 99%

“…So far, we have examined only four problem domains: Traffic and Transportation [19], [20], [21], Crowd Dynamics [22], [23], [24], Electric Power Engineering [30], [31], [32], Logistics and Supply Chain Management [27], [28], [29]. In this preliminary work we selected 12 papers, three for each domain.…”

Section: A Metamodel Building Processmentioning

confidence: 99%

Common and Domain-specific Metamodel Elements for Problem Description in Simulation Problems

Ribino¹,

Seidita²,

Lodato³

et al. 2014

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-It is well known that the multi-agent system paradigm is well suited for modelling and developing simulations of complex systems belonging to several application domains. Simulation study aims at developing simulation models useful for representing, studying and analyzing entities and their behavior in a system according to specific purposes. With our work we are trying to understand what are the right elements to be considered and included in the description of a simulation problem. In order to root our resulting metamodel in the state of the art of multi-agent simulations we started from the study of twelve papers dealing with four different application domains: Crowd Dynamics, Traffic and Transportation, Electricity Power Engineering and Supply Chain and Logistic. From this study we obtained a metamodel that may be used by an analyst as a guideline and concept repository for facing a new system design. The metamodel is the result of a well defined approach that is described together with the obtained results consisting in one core metamodel containing elements that are common to all the four application domains and some domain extension contents. These latter contain the elements that are specific of each of the studied domains and are not present in the others.

show abstract

“…Busse interagieren somit nicht mit dem Verkehr und passen ihre Geschwindigkeit an makroskopische Durchflussgeschwindigkeiten an. Fußgänger können an Bushaltestellen zu-und aussteigen [Meignan et al, 2006, Meignan et al, 2007. Die hierfür benötigten Zeiten hängen hauptsächlich von der Anzahl an zu-und aussteigenden Fahrgästen ab [Rajbhandari et al, 2003, Dueker et al, 2004.…”

Section: Sonstigesunclassified

Akteursorientierte multimodale Straßenverkehrssimulation

Dallmeyer

2014

Simulation Des Straßenverkehrs in Der Großstadt

View full text Add to dashboard Cite

Simulation and evaluation of urban bus-networks using a multiagent approach

Cited by 91 publications

References 12 publications

Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems – An Experimental Evaluation

Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems – An Experimental Evaluation

Common and Domain-specific Metamodel Elements for Problem Description in Simulation Problems

Akteursorientierte multimodale Straßenverkehrssimulation

Contact Info

Product

Resources

About