CityFlow: Supporting Spatial-Temporal Edge Computing for Urban Machine Learning Applications

Kawano, Mahiru; Yonezawa, Takeshi; Tanimura, Tomoki; Giang, Nam Ky; Broadbent, Matthew; Lea, Rodger; Nakazawa, Jin

doi:10.1007/978-3-030-28925-6_1

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…Our DNR platform allows the city developers to quickly build and deploy such application on top of the fleet and associated city infrastructure. While we are still in the data collection and experimentation phase, the details of the application and system architecture have been published in the work of Kawano et al 14 Lastly, while our work addresses a number of critical issues in the design and development of large scale applications, there are several that are outwith the scope of our work. One of these issues is the physical communication layer that interconnects devices and software components together.…”

Section: Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Developing applications in large scale, dynamic fog computing: A case study

2019

Self Cite

View full text Add to dashboard Cite

Summary In recent years, fog computing has emerged as a new distributed system model for a large class of applications that are data‐intensive or delay‐sensitive. By exploiting widely distributed computing infrastructure that is located closer to the network edge, communication cost and service response time can be significantly reduced. However, developing this class of applications is not straightforward and requires addressing three key challenges, ie, supporting the dynamic nature of the edge network, managing the context‐dependent characteristics of application logic, and dealing with the large scale of the system. In this paper, we present a case study in building fog computing applications using our open source platform Distributed Node‐RED (DNR). In particular, we show how applications can be decomposed and deployed to a geographically distributed infrastructure using DNR, and how existing software components can be adapted and reused to participate in fog applications. We present a lab‐based implementation of a fog application built using DNR that addresses the first two of the issues highlighted earlier. To validate that our approach also deals with large scale, we augment our live trial with a large scale simulation of the application model, conducted in Omnet++, which shows the scalability of the model and how it supports the dynamic nature of fog applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Limitationsmentioning

confidence: 99%

Developing applications in large scale, dynamic fog computing: A case study

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, in [8], the authors deployed a smart city application where cameras are mounted on city's garbage trucks, and the captured video streams are used to identify the road markers that need to be repainted. In this application, the city might only want to do the road marker classification in specific regions within the city.…”

Section: Application Scopementioning

confidence: 99%

Taxonomy of an Application Model

Giang

Leung

Lea

2019

Proceedings of the 9th ACM Symposium on Design and Analysis of Intelligent Vehicular Networks and Applications

Self Cite

View full text Add to dashboard Cite

With the advent of advanced computing systems beyond personal computing, such as mobile computing, cloud computing or recently, vehicular ad-hoc network, it is crucial that we understand the application development process of each type of these systems. Better understanding of how applications are built in different environment allows us to design better application models and system supports for developers. This paper studies the taxonomy of application models and defines its consisting aspects, namely application scope, application abstraction level, application structure, communication model and programming model. With the better understanding of the application models in general, we lay out the requirements for developing a class of large scale connected vehicle applications.

show abstract

CityFlow: Supporting Spatial-Temporal Edge Computing for Urban Machine Learning Applications

Cited by 2 publications

References 14 publications

Developing applications in large scale, dynamic fog computing: A case study

Developing applications in large scale, dynamic fog computing: A case study

Taxonomy of an Application Model

Contact Info

Product

Resources

About