Requirements for an ubiquitous computing simulation and emulation environment

Reynolds, Vinny; Cahill, Vinny; Senart, Aline

doi:10.1145/1142680.1142682

Cited by 26 publications

(30 citation statements)

References 17 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments we use an urban traffic simulator developed in Trinity College Dublin [15]. The simulator uses a microscopic traffic simulation approach, and can simulate traffic over any road network defined by a map provided in an XML format.…”

Section: Utc Simulation Platformmentioning

confidence: 99%

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

Dusparić

Cahill

2009

Lecture Notes in Computer Science

Self Cite

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: Utc Simulation Platformmentioning

confidence: 99%

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

Dusparić

Cahill

2009

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The UTC simulator [48] that we use follows a microscopic model. Its input is a set of XML files describing the road network to be simulated and the valid phases for each signalized junction.…”

Section: Discussionmentioning

confidence: 99%

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

Salkham

Cahill

2010

13th International IEEE Conference on Intelligent Transportation Systems

Self Cite

View full text Add to dashboard Cite

Abstract-Increasing traffic congestion is a major problem in urban areas, which incurs heavy economic and environmental costs in both developing and developed countries. Efficient urban traffic control (UTC) can help reduce traffic congestion. However, the increasing volume and the dynamic nature of urban traffic pose particular challenges to UTC. Reinforcement Learning (RL) has been shown to be a promising approach to efficient UTC. Dublin's inner city centre. Results from using our scheme show an approximate 35% -43% and 40% -54% better performance in terms of average vehicle waiting time and average number of vehicle stops respectively against the best baseline performance in our simulation.

show abstract

“…Morla and Davis use existing simulators to rapidly and cost effectively evaluate healthcare applications in terms of their networking performance and ability to process GPS information. Reynolds et al [12] address the issue of ubicomp system design from the ground up. Their work focuses on an automated approach to simulation and successfully models four abstractions of ubiquitous computing scenarios: the environment, sensors, actuators and applications.…”

Section: Simulationmentioning

confidence: 99%

Application development using modeling and dynamical systems analysis

O'Neill

McGlinn

Lewis

et al. 2009

Proceedings of the 1st International Workshop on Context-Aware Middleware and Services: Affiliated With the 4th International C

View full text Add to dashboard Cite

Research on context aware systems is handicapped by the lack of readily available large scale data sets, as well as by the lack of tools by which researchers can interact effectively with such data sets across a range of scales and granularities. We show how virtual reality combined with a dynamical systems analysis approach can start to address these gaps. Simulation allows for generation of simulated sensor data at runtime and actuations of entities in the virtual world. The ease of sensor deployment and configurations in a simulated environment allows for rapid reconfigurations enabling generation of the required large scale data sets for analysis. Using these data sets, dynamical systems analysis can determine if a given application is functioning in a manner that is deemed to be correct.

show abstract

Requirements for an ubiquitous computing simulation and emulation environment

Cited by 26 publications

References 17 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

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

Application development using modeling and dynamical systems analysis

Contact Info

Product

Resources

About