RICC-RIEC workshop 2019

Regional Inter-Cloud sub-Committee (RICC) which is one of the sub-committee of Internet Technology 163th Research Committee (ITRC) in Japan Society for the Promotion of Science (JSPS) will convene a joint workshop with Research Institute of Electrical Communication in Tohoku University (RIEC) on December. RICC-RIEC workshop have been organized since 2015 supported by RIEC collaborative project. The technical program includes one keynote address and several research presentations.

information

• Date: Mon. 16 Dec. 2019 10:00~ (UTC+0900)
• Venue: Research Institute of Electrical Communication, Tohoku University (map) 3F Seminar Room (M331)
• Fee: Free (exclude banquet)
• Registration: [TBD]
• Sponsor: RICC, ITRC, JSPS, RIEC, Tohoku University
• Contact: sec [at] ricc.itrc.net

program

• 9:00 - 10:00 Breakfast meeting
• 10:00 - 11:30 General Session 1
  • Hiroki Kashiwazaki (National Institute of Informatics): A proposal of quantitative approaches to evaluate a resilience of wide-area distributed sysmtems.
    abstract: A wide-area distributed application is affected by network failure due to natural disasters because the servers on which the application operates are distributed geographically in a wide area. Failure Injection Testing (FIT) is a method for verifying fault tolerance of widely distributed applications. In this paper, by limiting network failures only to the connection line, whole FIT scenarios are generated, and exhaustive evaluation of fault tolerance is performed. The authors propose a method to omit the evaluations from the aspect of topological constraint conditions. And they evaluate the visualization method of performance data obtained from this evaluation and the reduction of the fault tolerance evaluation cost by the proposed method.
  • Kohei Ichikawa (NAIST), Atsuko Takefusa (NII), Yasuhiro Watashiba, Yoshiyuki Kido, Susumu Date (Osaka Univ.): Deployment of NFV environment on an international SDN testbed
    abstract: We have been developing a large scale international software-defined networking (SDN) testbed, PRAGMA-ENT, which integrates multiple national academic networks and connects various organizations in the world. PRAGMA-ENT provides a sharable network cyberinfrastructure for researchers to develop, experiment and evaluate their new research ideas. We are currently working on the development of network function virtualization (NFV) testbed on PRAGMA-ENT. In this talk, we will introduce our tool that automates the deployment of virtual machine resources together with SDN interfaces and provides NFV environment for users.
• 11:30 - 12:30 Lunch
• 12:30 - 13:30 Invited Talk
  • JongWon Kim (AI Graduate School, Gwangju Institute of Science and Technology, Korea): Container-leveraged Service Realization Challenges for Cloud-native Computing
    abstract: Cloud-native computing, employing container-based microservices architecture, is accelerating its adoption for agile and scalable service deployment over worldwide multi-cloud infrastructure. In order to transparently enable diversified inter-connections for container-based cloud-native computing, by leveraging SDN/NFV technology, we need to tie distributed IoT things through multi-site edge clouds to hyper-scale core clouds. Thus, in this talk, we first attempt to relate the open-source-driven development for CNI (Container Networking Interface) and CSI (Container Storage Interface) to the required container-enabled cloud-native computing/storage with end-to-end (i.e., IoT--SDN/NFV--Cloud) inter-connections. Then, selected container-leveraged service realization challenges such as multi-tenant/multi-cluster Kubernetes orchestration, pvc(physical+virtual+containerized) harmonization, kernel-friendly accelerated and secured networking, and network-aware service meshes will be briefly discussed.
• 13:30 - 13:45 Coffee break
• 13:45 - 15:15 General Session 2 (RIEC)
  • Shao Xun (Kitami Insitute of Technology): Online Optimization of Orchestration for Distributed Edge Cloud Network
    abstract: In this work, we identify and analyze the complicated interaction of computing resource allocation and data placement for distributed edge cloud networks, and present a joint optimization framework that works with online manner. The proposed method achieves provable performance without knowing any future knowledge of the system.
  • Gen Kitagata (Tohoku University): Autopoiesis computing: agent-based service generation for IoT.
    abstract: Autopoiesis is a concept that a component self-organizes and creates itself and it can function alone and also cooperate with other components. As the next-generation computing platform for IoT, we aim to establish basic technology for autopoiesis computing in which various IoT devices autonomously compose services. We are promoting research and development of autopoiesis computing infrastructure that will be a software platform.
  • AMRIZAL, Muhammad Alfian (Tohoku University): A Markov Model-based Optimization Method of Data Transfer Rate for Faulty Wireless Sensor Networks.
    abstract: Wireless Sensor Networks typically consist of failure-prone sensor nodes (SN) and more reliable sink nodes (SK). To prevent data loss due to hardware failures, the data stored in SNs' memory must be regularly transferred to SKs. Since data transfer is generally a power-hungry activity, it is crucial to adjust the data transfer rate carefully. In this work, we propose a method to optimize the data transfer rate based on a Markov Model and discuss its optimality under various failure scenarios.
• 15:15 - 15:30 Wrap up