SlideShare ist ein Scribd-Unternehmen logo
1 von 27
Downloaden Sie, um offline zu lesen
Personal Research Overview
for the KU-NAIST Research Meeting
Chawanat Nakasan
Laboratory for Software Design and Analysis (NAIST) (Enr. 2013, Grad. 2018)
High Performance Computing and Networking Center (KU) Alum. (CPE23/KU69)
2018-02-15
2018-02-15 Research Overview for KU-NAIST Meeting 1
Agenda
• Self-Re-Introduction
• Where I left off at Kasetsart
• Projects and Activities while at NAIST
• Achievements
• Career Plans and Current Employment Status (Confidential & Removed from Online Edition)
2018-02-15 Research Overview for KU-NAIST Meeting 2
Self-Re-Introduction
2018-02-15 Research Overview for KU-NAIST Meeting 3
2013-2018
Master/Doctor of Engineering
Interests:
Software Defined Networking
Multipath Networking
2009-2013
Bachelor of Engineering
Interests:
Virtual Machine Infrastructure
Cloud Computing
Academic History
(Undergraduate Studies)
Bachelor of Engineering (Computer Engineering) with First Class Honours
High-Performance Computing and Networking Center
Kasetsart University
Additional Electives, Competitive Experience, Activities:
• Operating System Concepts and Architectures
• TCP/IP and Network Configuration (familiar with Cisco devices)
• Programming in Python and C++
• Network Security
• Co-Founder, Japanese Pop Culture Activity Group
42018-02-15 Research Overview for KU-NAIST Meeting
Academic History
(Graduate Studies)
Expected to Graduate with Doctor of Engineering Degree in 2018 March
Laboratory for Software Design and Analysis
Nara Institute of Science and Technology
Specializations:
• Software-Defined Networking
• Multipath Networking Technologies, especially Multipath TCP
• IT-Triadic Program: Additional Specializations in OS/Software Verification
• GEIOT (Entrepreneurship/IoT) Program
• Specific coursework on information security
52018-02-15 Research Overview for KU-NAIST Meeting
Where I left off at Kasetsart
2018-02-15 Research Overview for KU-NAIST Meeting 6
Overview of
Undergraduate Research
7
Source Cloud Dedicated Client Node
Different brands.
<= No migration capability =>
Stream the VM binary directly and reconfigure as needed
Developed tools for ease of migration and monitoring.
2018-02-15 Research Overview for KU-NAIST Meeting
At NAIST:
8
Optimization of Multipath TCP Performance
using Software-Defined Network
2018-02-15 Research Overview for KU-NAIST Meeting
Use Software-Defined Network to choose
better paths for Multipath TCP
9
3 Hops
4 Hops
6 Hops
OpenFlow
Controller
2018-02-15 Research Overview for KU-NAIST Meeting
Approach for Controller
10
MPTCP
Subflows
Step 1: Identify
Subflow Groups
Grouped Subflows
Step 2: Find Path Sets &
Map Subflows
Grouped Subflows
Subflows assigned to network paths
2018-02-15 Research Overview for KU-NAIST Meeting
MPTCP Subflow Group Identification
11
MPTCP Flow A
END HOSTS
Fully knows MPTCP subflow grouping
INTERMEDIATE NETWORK
Does not know MPTCP subflow groups
Only knows IP/Port of each subflow
This is our situation.
Subflow
A1
Subflow
A2
Subflow
A3
MPTCP Flow B
Subflow
B1
Subflow
B2
Subflow
B3
Subflow
Subflow
Subflow
Subflow
Subflow
Subflow
Step 1
2018-02-15 Research Overview for KU-NAIST Meeting
Reading the MPTCP
Handshake to identify flow groups
12
Step 1
A1 B1A2 B2
SYN + MP_CAPABLE + A_Key
SYN ACK + MP_CAPABLE + B_Key
ACK + MP_CAPABLE + A_Key + B_Key
SYN + MP_JOIN + B_Key + A_Nonce + etc.
ACK + MP_JOIN + B_HMAC + B_Nonce + etc.
ACK
ACK
1st connection
nth connection
2018-02-15 Research Overview for KU-NAIST Meeting
Path Set Algorithm:
Least-conflict shortest-paths algorithm
13
AltPath #1
(0 shares, length 3)
AltPath #2
(1 share, length 3)
The shortest path (length 2)
The algorithm and controller were originally developed as part of the Master’s Thesis.
Step 2
2018-02-15 Research Overview for KU-NAIST Meeting
Controller Experiment Setup
2018-02-15 Research Overview for KU-NAIST Meeting 14
POX Core
spanning tree
other POX
modules
Overseer
housekeeping
modules
subflow
management
path calculation
statistics and
logging
networkx
Simple Multipath OpenFlow Controller (smoc)
Evaluation Outline
2018-02-15 Research Overview for KU-NAIST Meeting 15
MPTCP & smoc Performance Evaluation
Simple performance test with iperf
Virtual Testbed (NAIST)
Real-World Testbed
(PRAGMA-ENT)
1: MPTCP baseline test
2: smoc test in NAIST 3: smoc test in PRAGMA-ENT
Performance test with Ceph DSS
Virtual Testbed (NAIST)
4: Performance of smoc vs POX
spanning-tree in Ceph testbed
Evaluation Outline
2018-02-15 Research Overview for KU-NAIST Meeting 16
MPTCP & smoc Performance Evaluation
Simple performance test with iperf
Virtual Testbed (NAIST)
Real-World Testbed (PRAGMA-
ENT)
1: MPTCP baseline test
2: smoc test in NAIST 3: smoc test in PRAGMA-ENT
Performance test with Ceph DSS
Virtual Testbed (NAIST)
4: Performance of smoc vs POX
spanning-tree in Ceph testbed
Target: Distributed Storage Systems (DSS)
2018-02-15 Research Overview for KU-NAIST Meeting 17
Metadata ServerStorage Servers
Client(s)
Ceph Testbed Topology & Communication
Pattern
2018-02-15 Research Overview for KU-NAIST Meeting 18
31
2
4
5
6
Monitor &
Metadata Server Object Storage
Device/Servers
Clients
Client-OSD (get, put, etc.)
Client-MDS (rm, use pools, etc.)
OSD-OSD Communication
(Synchronization, replication, etc.)
MDS-OSD
(heartbeat, map update, etc.)
Results are generally satisfactory! 
• I just presented my dissertation this morning, so please let me take a
little break ^_^
2018-02-15 Research Overview for KU-NAIST Meeting 19
Major Achievements:
• 1+1 International Journal
• Nakasan, C., Ichikawa, K., Iida, H., Uthayopas, P., “A simple multipath OpenFlow controller using topology-based
algorithm for multipath TCP”. In: Concurrency and Computation: Practice and Experience 29.13 (2017), e4134–n/a.
issn: 1532-0634. doi: 10.1002/cpe.4134
• Ichikawa, K., U-Chupala, P., Huang, C., Nakasan, C., Liu, T.-L., Chang, J.-Y., Ku, L.-C., Tsai, W.-F., Haga, J., Yamanaka, H.,
Kawai, E., Kido, Y., Date, S., Shimojo, S., Papadopoulos, P., Tsugawa, M., Collins, M., Jeong, K., Figueiredo, R., Fortes, J.,
“PRAGMA-ENT: An International SDN testbed for cyberinfrastructure in the Pacific Rim”. In: Concurrency and
Computation: Practice and Experience 29.13 (2017). Previously presented at PRAGMA Workshop on International
Clouds for Data Science 2015, Best Paper Award., e4138–n/a. issn: 1532-0634. doi: 10.1002/cpe.4138.
• 0+1 Domestic Journal
• Huang, C., Nakasan, C., Ichikawa, K., Iida, H., A Multipath OpenFlow Controller for Multiple TCP Stream Applications. Tech. rep. 2017.
• 1+2 International Conference
• Nakasan, C., Ichikawa, K., Iida, H., Uthayopas, P., “A Simple Multipath OpenFlow Controller using topology-based algorithm for
Multipath TCP”. In: PRAGMA Workshop on International Clouds for Data Science (PRAGMA-ICDS 2015). Depok, Indonesia. Oct. 2015.
• Huang, C., Nakasan, C., Ichikawa, K., Iida, H., “An SDN-based Multipath GridFTP for High-speed Data Transfer”. In: In 36th IEEE
International Conference on Distributed Computing Systems (June 2016), pp. 763–764.
• Huang, C., Nakasan, C., Ichikawa, K., Iida, H., “A multipath controller for accelerating GridFTP transfer over SDN”. In: (Sept. 2015).
Munich, Germany, pp. 439–447.
2018-02-15 Research Overview for KU-NAIST Meeting 20
Academic Awards
2018-02-15 Research Overview for KU-NAIST Meeting 21
Research Awards
2014/4 Best New Member Talk (PRAGMA 26 Lightning Talk)
2015/10 NFA: Best Paper Award (PRAGMA-ICDS 2015)
2016/9 Best Poster Award (PRAGMA 31 Poster Presentations)
2017/4 NFA: Best Research Award (IPSJ xSIG)
Scholarships
2013 JASSO Honors Scholarship
2014 MEXT Top Global University Project Support Fund
2015 KDDI Foundation Scholarship
2016-2017 SGH Foundation Scholarship
NFA = Not First Author
Current Status:
• About to graduate from NAIST, of
course
• About to graduate from PRAGMA
Students Steering Committee as well.
2018-02-15 Research Overview for KU-NAIST Meeting 22
↑ Hackjob logo designed at the last minute
Current Status:
• Will be moving somewhere within Japan for an
academic career.
• 5-year plan: 5 int’l papers, not counting anything “in
between” such as journals and tech reports.
• Endgame plan: Become assoc prof in Japan, or similar.
• Also: Code for fun, get a Japanese hobby, climb Mt. Fuji,
etc.
2018-02-15 Research Overview for KU-NAIST Meeting 23
Ikoma, Nara
Possible Future Collaboration
2018-02-15 Research Overview for KU-NAIST Meeting 24
Internship Programs? Proliferation of research networks?
(JGN-X, PRAGMA-ENT, etc.)
Possible Future Collaboration
2018-02-15 Research Overview for KU-NAIST Meeting 25
OLD MAN?
Further research on multipath
networking and SDNs?
Collaborate with PRAGMA?
But it’s up to my next job, wherever it happens.
?
(I’ll still try to help. I promise.)
2018-02-15 Research Overview for KU-NAIST Meeting 26
Thank you for these 5 years!
五年間ありがとうございます!
2018-02-15 Research Overview for KU-NAIST Meeting 27

Weitere ähnliche Inhalte

Was ist angesagt?

Machine Learning and GraphX
Machine Learning and GraphXMachine Learning and GraphX
Machine Learning and GraphXAndy Petrella
 
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...Spark Summit
 
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark StreamingTiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark StreamingPaco Nathan
 
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...Debraj GuhaThakurta
 
Overview of Apache Flink: Next-Gen Big Data Analytics Framework
Overview of Apache Flink: Next-Gen Big Data Analytics FrameworkOverview of Apache Flink: Next-Gen Big Data Analytics Framework
Overview of Apache Flink: Next-Gen Big Data Analytics FrameworkSlim Baltagi
 
High Performance Data Analytics with Java on Large Multicore HPC Clusters
High Performance Data Analytics with Java on Large Multicore HPC ClustersHigh Performance Data Analytics with Java on Large Multicore HPC Clusters
High Performance Data Analytics with Java on Large Multicore HPC ClustersSaliya Ekanayake
 
BKK16-408B Data Analytics and Machine Learning From Node to Cluster
BKK16-408B Data Analytics and Machine Learning From Node to ClusterBKK16-408B Data Analytics and Machine Learning From Node to Cluster
BKK16-408B Data Analytics and Machine Learning From Node to ClusterLinaro
 
Using spark for timeseries graph analytics
Using spark for timeseries graph analyticsUsing spark for timeseries graph analytics
Using spark for timeseries graph analyticsSigmoid
 
Spark Concepts - Spark SQL, Graphx, Streaming
Spark Concepts - Spark SQL, Graphx, StreamingSpark Concepts - Spark SQL, Graphx, Streaming
Spark Concepts - Spark SQL, Graphx, StreamingPetr Zapletal
 
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...DataWorks Summit
 
RISELab:Enabling Intelligent Real-Time Decisions
RISELab:Enabling Intelligent Real-Time DecisionsRISELab:Enabling Intelligent Real-Time Decisions
RISELab:Enabling Intelligent Real-Time DecisionsJen Aman
 
Evolving from RDBMS to NoSQL + SQL
Evolving from RDBMS to NoSQL + SQLEvolving from RDBMS to NoSQL + SQL
Evolving from RDBMS to NoSQL + SQLMapR Technologies
 
A location based least-cost scheduling for data-intensive applications
A location based least-cost scheduling for data-intensive applicationsA location based least-cost scheduling for data-intensive applications
A location based least-cost scheduling for data-intensive applicationsIAEME Publication
 
A time energy performance analysis of map reduce on heterogeneous systems wit...
A time energy performance analysis of map reduce on heterogeneous systems wit...A time energy performance analysis of map reduce on heterogeneous systems wit...
A time energy performance analysis of map reduce on heterogeneous systems wit...newmooxx
 
Performance Characterization and Optimization of In-Memory Data Analytics on ...
Performance Characterization and Optimization of In-Memory Data Analytics on ...Performance Characterization and Optimization of In-Memory Data Analytics on ...
Performance Characterization and Optimization of In-Memory Data Analytics on ...Ahsan Javed Awan
 
BigDataEurope @BDVA Summit2016 2: Societal Pilots
BigDataEurope @BDVA Summit2016 2: Societal PilotsBigDataEurope @BDVA Summit2016 2: Societal Pilots
BigDataEurope @BDVA Summit2016 2: Societal PilotsBigData_Europe
 
High Performance Processing of Streaming Data
High Performance Processing of Streaming DataHigh Performance Processing of Streaming Data
High Performance Processing of Streaming DataGeoffrey Fox
 
LarKC Tutorial at ISWC 2009 - Urban Computing
LarKC Tutorial at ISWC 2009 - Urban ComputingLarKC Tutorial at ISWC 2009 - Urban Computing
LarKC Tutorial at ISWC 2009 - Urban ComputingLarKC
 

Was ist angesagt? (19)

Machine Learning and GraphX
Machine Learning and GraphXMachine Learning and GraphX
Machine Learning and GraphX
 
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...
High Resolution Energy Modeling that Scales with Apache Spark 2.0 Spark Summi...
 
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark StreamingTiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
 
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...
TWDI Accelerate Seattle, Oct 16, 2017: Distributed and In-Database Analytics ...
 
Overview of Apache Flink: Next-Gen Big Data Analytics Framework
Overview of Apache Flink: Next-Gen Big Data Analytics FrameworkOverview of Apache Flink: Next-Gen Big Data Analytics Framework
Overview of Apache Flink: Next-Gen Big Data Analytics Framework
 
High Performance Data Analytics with Java on Large Multicore HPC Clusters
High Performance Data Analytics with Java on Large Multicore HPC ClustersHigh Performance Data Analytics with Java on Large Multicore HPC Clusters
High Performance Data Analytics with Java on Large Multicore HPC Clusters
 
BKK16-408B Data Analytics and Machine Learning From Node to Cluster
BKK16-408B Data Analytics and Machine Learning From Node to ClusterBKK16-408B Data Analytics and Machine Learning From Node to Cluster
BKK16-408B Data Analytics and Machine Learning From Node to Cluster
 
Using spark for timeseries graph analytics
Using spark for timeseries graph analyticsUsing spark for timeseries graph analytics
Using spark for timeseries graph analytics
 
Spark Concepts - Spark SQL, Graphx, Streaming
Spark Concepts - Spark SQL, Graphx, StreamingSpark Concepts - Spark SQL, Graphx, Streaming
Spark Concepts - Spark SQL, Graphx, Streaming
 
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
 
RISELab:Enabling Intelligent Real-Time Decisions
RISELab:Enabling Intelligent Real-Time DecisionsRISELab:Enabling Intelligent Real-Time Decisions
RISELab:Enabling Intelligent Real-Time Decisions
 
Evolving from RDBMS to NoSQL + SQL
Evolving from RDBMS to NoSQL + SQLEvolving from RDBMS to NoSQL + SQL
Evolving from RDBMS to NoSQL + SQL
 
A location based least-cost scheduling for data-intensive applications
A location based least-cost scheduling for data-intensive applicationsA location based least-cost scheduling for data-intensive applications
A location based least-cost scheduling for data-intensive applications
 
A time energy performance analysis of map reduce on heterogeneous systems wit...
A time energy performance analysis of map reduce on heterogeneous systems wit...A time energy performance analysis of map reduce on heterogeneous systems wit...
A time energy performance analysis of map reduce on heterogeneous systems wit...
 
Performance Characterization and Optimization of In-Memory Data Analytics on ...
Performance Characterization and Optimization of In-Memory Data Analytics on ...Performance Characterization and Optimization of In-Memory Data Analytics on ...
Performance Characterization and Optimization of In-Memory Data Analytics on ...
 
BigDataEurope @BDVA Summit2016 2: Societal Pilots
BigDataEurope @BDVA Summit2016 2: Societal PilotsBigDataEurope @BDVA Summit2016 2: Societal Pilots
BigDataEurope @BDVA Summit2016 2: Societal Pilots
 
Icbai 2018 ver_1
Icbai 2018 ver_1Icbai 2018 ver_1
Icbai 2018 ver_1
 
High Performance Processing of Streaming Data
High Performance Processing of Streaming DataHigh Performance Processing of Streaming Data
High Performance Processing of Streaming Data
 
LarKC Tutorial at ISWC 2009 - Urban Computing
LarKC Tutorial at ISWC 2009 - Urban ComputingLarKC Tutorial at ISWC 2009 - Urban Computing
LarKC Tutorial at ISWC 2009 - Urban Computing
 

Ähnlich wie Personal Research Overview presented at the KU-NAIST Research Meeting

Pioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSCPioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSCinside-BigData.com
 
Major Report on ADIAN
Major Report on ADIANMajor Report on ADIAN
Major Report on ADIANsmittal121
 
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...Pradeeban Kathiravelu, Ph.D.
 
Walking on AI/ML for Networking
Walking on AI/ML for NetworkingWalking on AI/ML for Networking
Walking on AI/ML for NetworkingOscar Caicedo
 
Iciic 2010 114
Iciic 2010 114Iciic 2010 114
Iciic 2010 114hanums1
 
Private Network Project for Colleges
Private Network Project for CollegesPrivate Network Project for Colleges
Private Network Project for CollegesAditya Jain
 
Panel: NRP Science Impacts​
Panel: NRP Science Impacts​Panel: NRP Science Impacts​
Panel: NRP Science Impacts​Larry Smarr
 
Christian Kreuzfeld – Static vs Dynamic Stream Processing
Christian Kreuzfeld – Static vs Dynamic Stream ProcessingChristian Kreuzfeld – Static vs Dynamic Stream Processing
Christian Kreuzfeld – Static vs Dynamic Stream ProcessingFlink Forward
 
Iccsit2010 paper2
Iccsit2010 paper2Iccsit2010 paper2
Iccsit2010 paper2hanums1
 
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)Spark Summit
 
Splunk App for Stream
Splunk App for StreamSplunk App for Stream
Splunk App for StreamSplunk
 
Data Science at Scale on MPP databases - Use Cases & Open Source Tools
Data Science at Scale on MPP databases - Use Cases & Open Source ToolsData Science at Scale on MPP databases - Use Cases & Open Source Tools
Data Science at Scale on MPP databases - Use Cases & Open Source ToolsEsther Vasiete
 
Real-Time Anomaly Detection with Spark MLlib, Akka and Cassandra
Real-Time Anomaly Detection  with Spark MLlib, Akka and  CassandraReal-Time Anomaly Detection  with Spark MLlib, Akka and  Cassandra
Real-Time Anomaly Detection with Spark MLlib, Akka and CassandraNatalino Busa
 
Accelerating TensorFlow with RDMA for high-performance deep learning
Accelerating TensorFlow with RDMA for high-performance deep learningAccelerating TensorFlow with RDMA for high-performance deep learning
Accelerating TensorFlow with RDMA for high-performance deep learningDataWorks Summit
 

Ähnlich wie Personal Research Overview presented at the KU-NAIST Research Meeting (20)

Netsoft19 Keynote: Fluid Network Planes
Netsoft19 Keynote: Fluid Network PlanesNetsoft19 Keynote: Fluid Network Planes
Netsoft19 Keynote: Fluid Network Planes
 
Pioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSCPioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSC
 
Major Report on ADIAN
Major Report on ADIANMajor Report on ADIAN
Major Report on ADIAN
 
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...
SDN-Based Enhancements to QoS and Data Quality in Multi-Tenanted Data Center ...
 
Walking on AI/ML for Networking
Walking on AI/ML for NetworkingWalking on AI/ML for Networking
Walking on AI/ML for Networking
 
Iciic 2010 114
Iciic 2010 114Iciic 2010 114
Iciic 2010 114
 
Private Network Project for Colleges
Private Network Project for CollegesPrivate Network Project for Colleges
Private Network Project for Colleges
 
Panel: NRP Science Impacts​
Panel: NRP Science Impacts​Panel: NRP Science Impacts​
Panel: NRP Science Impacts​
 
HPC in higher education
HPC in higher educationHPC in higher education
HPC in higher education
 
Christian Kreuzfeld – Static vs Dynamic Stream Processing
Christian Kreuzfeld – Static vs Dynamic Stream ProcessingChristian Kreuzfeld – Static vs Dynamic Stream Processing
Christian Kreuzfeld – Static vs Dynamic Stream Processing
 
2015 - 2016 ieee ns2 project titles
2015 - 2016 ieee ns2 project titles2015 - 2016 ieee ns2 project titles
2015 - 2016 ieee ns2 project titles
 
Ganesh machavarapu resume
Ganesh  machavarapu resumeGanesh  machavarapu resume
Ganesh machavarapu resume
 
Ganesh machavarapu resume
Ganesh  machavarapu resumeGanesh  machavarapu resume
Ganesh machavarapu resume
 
Iccsit2010 paper2
Iccsit2010 paper2Iccsit2010 paper2
Iccsit2010 paper2
 
Vivek Kesharwani
Vivek KesharwaniVivek Kesharwani
Vivek Kesharwani
 
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)
Spark at NASA/JPL-(Chris Mattmann, NASA/JPL)
 
Splunk App for Stream
Splunk App for StreamSplunk App for Stream
Splunk App for Stream
 
Data Science at Scale on MPP databases - Use Cases & Open Source Tools
Data Science at Scale on MPP databases - Use Cases & Open Source ToolsData Science at Scale on MPP databases - Use Cases & Open Source Tools
Data Science at Scale on MPP databases - Use Cases & Open Source Tools
 
Real-Time Anomaly Detection with Spark MLlib, Akka and Cassandra
Real-Time Anomaly Detection  with Spark MLlib, Akka and  CassandraReal-Time Anomaly Detection  with Spark MLlib, Akka and  Cassandra
Real-Time Anomaly Detection with Spark MLlib, Akka and Cassandra
 
Accelerating TensorFlow with RDMA for high-performance deep learning
Accelerating TensorFlow with RDMA for high-performance deep learningAccelerating TensorFlow with RDMA for high-performance deep learning
Accelerating TensorFlow with RDMA for high-performance deep learning
 

Mehr von Chawanat Nakasan

Mehr von Chawanat Nakasan (7)

Grad Life in Japan
Grad Life in JapanGrad Life in Japan
Grad Life in Japan
 
Gfarm presentation and thesis topic introduction
Gfarm presentation and thesis topic introductionGfarm presentation and thesis topic introduction
Gfarm presentation and thesis topic introduction
 
The Noodles of Japan
The Noodles of JapanThe Noodles of Japan
The Noodles of Japan
 
VM Migration and Monitoring Software *SDLAB
VM Migration and Monitoring Software *SDLABVM Migration and Monitoring Software *SDLAB
VM Migration and Monitoring Software *SDLAB
 
Top asian universities
Top asian universitiesTop asian universities
Top asian universities
 
d12 or 2d6
d12 or 2d6d12 or 2d6
d12 or 2d6
 
Methods of Payment
Methods of PaymentMethods of Payment
Methods of Payment
 

Kürzlich hochgeladen

Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfAyushMahapatra5
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationnomboosow
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Disha Kariya
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingTeacherCyreneCayanan
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...christianmathematics
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDThiyagu K
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAssociation for Project Management
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
social pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajansocial pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajanpragatimahajan3
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfagholdier
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...fonyou31
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdfQucHHunhnh
 

Kürzlich hochgeladen (20)

Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
social pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajansocial pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajan
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Advance Mobile Application Development class 07
Advance Mobile Application Development class 07Advance Mobile Application Development class 07
Advance Mobile Application Development class 07
 

Personal Research Overview presented at the KU-NAIST Research Meeting

  • 1. Personal Research Overview for the KU-NAIST Research Meeting Chawanat Nakasan Laboratory for Software Design and Analysis (NAIST) (Enr. 2013, Grad. 2018) High Performance Computing and Networking Center (KU) Alum. (CPE23/KU69) 2018-02-15 2018-02-15 Research Overview for KU-NAIST Meeting 1
  • 2. Agenda • Self-Re-Introduction • Where I left off at Kasetsart • Projects and Activities while at NAIST • Achievements • Career Plans and Current Employment Status (Confidential & Removed from Online Edition) 2018-02-15 Research Overview for KU-NAIST Meeting 2
  • 3. Self-Re-Introduction 2018-02-15 Research Overview for KU-NAIST Meeting 3 2013-2018 Master/Doctor of Engineering Interests: Software Defined Networking Multipath Networking 2009-2013 Bachelor of Engineering Interests: Virtual Machine Infrastructure Cloud Computing
  • 4. Academic History (Undergraduate Studies) Bachelor of Engineering (Computer Engineering) with First Class Honours High-Performance Computing and Networking Center Kasetsart University Additional Electives, Competitive Experience, Activities: • Operating System Concepts and Architectures • TCP/IP and Network Configuration (familiar with Cisco devices) • Programming in Python and C++ • Network Security • Co-Founder, Japanese Pop Culture Activity Group 42018-02-15 Research Overview for KU-NAIST Meeting
  • 5. Academic History (Graduate Studies) Expected to Graduate with Doctor of Engineering Degree in 2018 March Laboratory for Software Design and Analysis Nara Institute of Science and Technology Specializations: • Software-Defined Networking • Multipath Networking Technologies, especially Multipath TCP • IT-Triadic Program: Additional Specializations in OS/Software Verification • GEIOT (Entrepreneurship/IoT) Program • Specific coursework on information security 52018-02-15 Research Overview for KU-NAIST Meeting
  • 6. Where I left off at Kasetsart 2018-02-15 Research Overview for KU-NAIST Meeting 6
  • 7. Overview of Undergraduate Research 7 Source Cloud Dedicated Client Node Different brands. <= No migration capability => Stream the VM binary directly and reconfigure as needed Developed tools for ease of migration and monitoring. 2018-02-15 Research Overview for KU-NAIST Meeting
  • 8. At NAIST: 8 Optimization of Multipath TCP Performance using Software-Defined Network 2018-02-15 Research Overview for KU-NAIST Meeting
  • 9. Use Software-Defined Network to choose better paths for Multipath TCP 9 3 Hops 4 Hops 6 Hops OpenFlow Controller 2018-02-15 Research Overview for KU-NAIST Meeting
  • 10. Approach for Controller 10 MPTCP Subflows Step 1: Identify Subflow Groups Grouped Subflows Step 2: Find Path Sets & Map Subflows Grouped Subflows Subflows assigned to network paths 2018-02-15 Research Overview for KU-NAIST Meeting
  • 11. MPTCP Subflow Group Identification 11 MPTCP Flow A END HOSTS Fully knows MPTCP subflow grouping INTERMEDIATE NETWORK Does not know MPTCP subflow groups Only knows IP/Port of each subflow This is our situation. Subflow A1 Subflow A2 Subflow A3 MPTCP Flow B Subflow B1 Subflow B2 Subflow B3 Subflow Subflow Subflow Subflow Subflow Subflow Step 1 2018-02-15 Research Overview for KU-NAIST Meeting
  • 12. Reading the MPTCP Handshake to identify flow groups 12 Step 1 A1 B1A2 B2 SYN + MP_CAPABLE + A_Key SYN ACK + MP_CAPABLE + B_Key ACK + MP_CAPABLE + A_Key + B_Key SYN + MP_JOIN + B_Key + A_Nonce + etc. ACK + MP_JOIN + B_HMAC + B_Nonce + etc. ACK ACK 1st connection nth connection 2018-02-15 Research Overview for KU-NAIST Meeting
  • 13. Path Set Algorithm: Least-conflict shortest-paths algorithm 13 AltPath #1 (0 shares, length 3) AltPath #2 (1 share, length 3) The shortest path (length 2) The algorithm and controller were originally developed as part of the Master’s Thesis. Step 2 2018-02-15 Research Overview for KU-NAIST Meeting
  • 14. Controller Experiment Setup 2018-02-15 Research Overview for KU-NAIST Meeting 14 POX Core spanning tree other POX modules Overseer housekeeping modules subflow management path calculation statistics and logging networkx Simple Multipath OpenFlow Controller (smoc)
  • 15. Evaluation Outline 2018-02-15 Research Overview for KU-NAIST Meeting 15 MPTCP & smoc Performance Evaluation Simple performance test with iperf Virtual Testbed (NAIST) Real-World Testbed (PRAGMA-ENT) 1: MPTCP baseline test 2: smoc test in NAIST 3: smoc test in PRAGMA-ENT Performance test with Ceph DSS Virtual Testbed (NAIST) 4: Performance of smoc vs POX spanning-tree in Ceph testbed
  • 16. Evaluation Outline 2018-02-15 Research Overview for KU-NAIST Meeting 16 MPTCP & smoc Performance Evaluation Simple performance test with iperf Virtual Testbed (NAIST) Real-World Testbed (PRAGMA- ENT) 1: MPTCP baseline test 2: smoc test in NAIST 3: smoc test in PRAGMA-ENT Performance test with Ceph DSS Virtual Testbed (NAIST) 4: Performance of smoc vs POX spanning-tree in Ceph testbed
  • 17. Target: Distributed Storage Systems (DSS) 2018-02-15 Research Overview for KU-NAIST Meeting 17 Metadata ServerStorage Servers Client(s)
  • 18. Ceph Testbed Topology & Communication Pattern 2018-02-15 Research Overview for KU-NAIST Meeting 18 31 2 4 5 6 Monitor & Metadata Server Object Storage Device/Servers Clients Client-OSD (get, put, etc.) Client-MDS (rm, use pools, etc.) OSD-OSD Communication (Synchronization, replication, etc.) MDS-OSD (heartbeat, map update, etc.)
  • 19. Results are generally satisfactory!  • I just presented my dissertation this morning, so please let me take a little break ^_^ 2018-02-15 Research Overview for KU-NAIST Meeting 19
  • 20. Major Achievements: • 1+1 International Journal • Nakasan, C., Ichikawa, K., Iida, H., Uthayopas, P., “A simple multipath OpenFlow controller using topology-based algorithm for multipath TCP”. In: Concurrency and Computation: Practice and Experience 29.13 (2017), e4134–n/a. issn: 1532-0634. doi: 10.1002/cpe.4134 • Ichikawa, K., U-Chupala, P., Huang, C., Nakasan, C., Liu, T.-L., Chang, J.-Y., Ku, L.-C., Tsai, W.-F., Haga, J., Yamanaka, H., Kawai, E., Kido, Y., Date, S., Shimojo, S., Papadopoulos, P., Tsugawa, M., Collins, M., Jeong, K., Figueiredo, R., Fortes, J., “PRAGMA-ENT: An International SDN testbed for cyberinfrastructure in the Pacific Rim”. In: Concurrency and Computation: Practice and Experience 29.13 (2017). Previously presented at PRAGMA Workshop on International Clouds for Data Science 2015, Best Paper Award., e4138–n/a. issn: 1532-0634. doi: 10.1002/cpe.4138. • 0+1 Domestic Journal • Huang, C., Nakasan, C., Ichikawa, K., Iida, H., A Multipath OpenFlow Controller for Multiple TCP Stream Applications. Tech. rep. 2017. • 1+2 International Conference • Nakasan, C., Ichikawa, K., Iida, H., Uthayopas, P., “A Simple Multipath OpenFlow Controller using topology-based algorithm for Multipath TCP”. In: PRAGMA Workshop on International Clouds for Data Science (PRAGMA-ICDS 2015). Depok, Indonesia. Oct. 2015. • Huang, C., Nakasan, C., Ichikawa, K., Iida, H., “An SDN-based Multipath GridFTP for High-speed Data Transfer”. In: In 36th IEEE International Conference on Distributed Computing Systems (June 2016), pp. 763–764. • Huang, C., Nakasan, C., Ichikawa, K., Iida, H., “A multipath controller for accelerating GridFTP transfer over SDN”. In: (Sept. 2015). Munich, Germany, pp. 439–447. 2018-02-15 Research Overview for KU-NAIST Meeting 20
  • 21. Academic Awards 2018-02-15 Research Overview for KU-NAIST Meeting 21 Research Awards 2014/4 Best New Member Talk (PRAGMA 26 Lightning Talk) 2015/10 NFA: Best Paper Award (PRAGMA-ICDS 2015) 2016/9 Best Poster Award (PRAGMA 31 Poster Presentations) 2017/4 NFA: Best Research Award (IPSJ xSIG) Scholarships 2013 JASSO Honors Scholarship 2014 MEXT Top Global University Project Support Fund 2015 KDDI Foundation Scholarship 2016-2017 SGH Foundation Scholarship NFA = Not First Author
  • 22. Current Status: • About to graduate from NAIST, of course • About to graduate from PRAGMA Students Steering Committee as well. 2018-02-15 Research Overview for KU-NAIST Meeting 22 ↑ Hackjob logo designed at the last minute
  • 23. Current Status: • Will be moving somewhere within Japan for an academic career. • 5-year plan: 5 int’l papers, not counting anything “in between” such as journals and tech reports. • Endgame plan: Become assoc prof in Japan, or similar. • Also: Code for fun, get a Japanese hobby, climb Mt. Fuji, etc. 2018-02-15 Research Overview for KU-NAIST Meeting 23 Ikoma, Nara
  • 24. Possible Future Collaboration 2018-02-15 Research Overview for KU-NAIST Meeting 24 Internship Programs? Proliferation of research networks? (JGN-X, PRAGMA-ENT, etc.)
  • 25. Possible Future Collaboration 2018-02-15 Research Overview for KU-NAIST Meeting 25 OLD MAN? Further research on multipath networking and SDNs? Collaborate with PRAGMA?
  • 26. But it’s up to my next job, wherever it happens. ? (I’ll still try to help. I promise.) 2018-02-15 Research Overview for KU-NAIST Meeting 26
  • 27. Thank you for these 5 years! 五年間ありがとうございます! 2018-02-15 Research Overview for KU-NAIST Meeting 27