Helix Nebula The Science Cloud Bernd Schirpke, T-Systems International, May 2014
http://www.helix-nebula.eu/
– streng vertraulich, vertraulich, intern, öffentlich –
13/05/2014
1
Science Goes Cloud Data Deluge and Globalisation of Science Biology
Physics
Next generation sequencing annual increase of kbases/day almost by factor 10
ATLAS experiment at CERN generates 15 PB of data per year to be analyzed by 3,000 physicians
Earth Observation
Climate Research
ESA will launch 3 Sentinel satellites in 2014 and 2015 which will generate more than 3 PB data p.a.
The climate model intercomparison project of the IPCC generated 2.3 PB in 2012 – 60 times more than in 2004
Bernd Schirpke, T-Systems International
12/05/2014
2
Helix Nebula – The Science Cloud
Big science teams up with big business – A European public-private partnership for cloud
Helix Nebula – The Science Cloud A European Public-Private Partnership
Strategic Plan Establish multi-tenant, multi-provider cloud infrastructure Identify and adopt policies for trust, security
To support the computing capacity needs for the ATLAS experiment
Setting up a new service to simplify analysis of large genomes, for a deeper insight into evolution and biodiversity
To create an Earth Observation platform, focusing on earthquake and volcano research
To improve the speed and quality of research for finding surrogate biomarkers based on brain images
Suppliers
and privacy Create governance structure
Adopters
Define funding schemes
Bernd Schirpke, T-Systems International
12/05/2014
4
Helix Nebula – The Science Cloud Vision and Key Objectives Vision
In 2020, all scientists of all disciplines will choose the Helix Nebula Infrastructure as their first option to store, access, process & analyse data It will contain vast quantities of data, open source tools, and a literally infinite amount of computing power accessible and usable from any kind of computer, smart phone or tablet device. Science will make significant progresses by applying data sharing and interdisciplinary research using this infrastructure as the fundamental tool. This infrastructure will have such a reliability and worldwide recognition for its implemented security and privacy scheme that also commercial companies will be using this "high security area" to derive patents.
Objectives
A platform capable of development through PPP into a scalable science cloud A flexible governance structure capable of growing alongside the infrastructure itself Representations of functional and non‐functional requirements including policies for trust, security and privacy Agreements regarding inter‐operability with other, existing e‐infrastructures Three flagships based at CERN, EMBL and ESA, selected as ‘stretch’ targets highlighting extreme cases of the requirements of the ERA Sustainable business models adhering to and supporting European‐level policies A roadmap and development plan for addressing issues on the road to 2020 Bernd Schirpke, T-Systems International
12/05/2014
5
Helix Nebula – The Science Cloud Timeline Set-up
2011
Pilot phase
Towards an open market for Science
2012-2013
2014 …
Common Strategy
Deploy flagships
More applications
Agree on the Partnership
More services
Select flagships use cases
Analysis of functionality, performance & financial model
Define governance model
Success Stories
More service providers
More users
co-funded by EC under grant 312301 with 1.8M€ Bernd Schirpke, T-Systems International
12/05/2014
6
Helix Nebula – Use Cases
Helix Nebula – Use Cases EMBL: Next Generation DNA Sequencing EMBL European Molecular Biology Laboratory
THE CUSTOMER
“EMBL is at the forefront of innovation in life sciences research, technology development and transfer, and provides outstanding training and services to the scientific community in its member states.“ (EMBL Website)
Intergovernmental Research Organization
Supported by 20 Member States
1500 staff, 70+ nationalities
Five locations in Germany, UK, France and Italy
Bernd Schirpke, T-Systems International
12/05/2014
8
Helix Nebula – Use Cases EMBL: Next Generation DNA Sequencing
Source: Rupert Lück, EMBL Bernd Schirpke, T-Systems International
12/05/2014
9
Helix Nebula – Use Cases EMBL: Next Generation DNA Sequencing
Source: Rupert Lück, EMBL Bernd Schirpke, T-Systems International
12/05/2014
10
Helix Nebula – Use Cases EMBL: Next Generation DNA Sequencing Bases Sequenced / Sample / Run @ EMBL (Illumina) 35.000.000.000
4 x Ilumina
30.000.000.000
HiSeq2000 25.000.000.000
1 x MySeq 20.000.000.000
15.000.000.000
1 x Ion Torrent
10.000.000.000
5.000.000.000
August 11
May 11
Feb 11
Nov 10
Aug 10
May 10
Feb 10
Nov 09
Aug 09
May 09
Feb 09
Nov 08
Aug 08
May 08
Feb 08
0
NGS generates 30+ TB data each week Source: Rupert Lück, EMBL
Bernd Schirpke, T-Systems International
12/05/2014
11
Helix Nebula – Use Cases Why EMBL Involves in Cloud Computing key challenges in life sciences
Enabling real-time use of information embedded in DNA and molecules Supporting individual and improved medication for patients e.g. in cancer treatment Better understanding and treatment of complex diseases e.g. Alzheimer Systematic analysis and documentation of biological information to support life science research and its translation to medicine and the environment, the bio-industries and society (ELIXIRProject). Bernd Schirpke, T-Systems International
12/05/2014
12
Helix Nebula – Use Cases CERN: AtLAS Experiment on the LHC CERN European Organization for Nuclear Research
THE CUSTOMER
“What is the universe made of? How did it start? Physicists at CERN are seeking answers, using some of the world's most powerful particle accelerators .” (CERN Website)
20 Member States
2300 staff, 790 other paid personnal
> 10,000 users in 50+ countries
1.2 billion CHF budget (2012)
Experiments are producing 15 PB p.a., requiring 100,000 fast CPUs to process data
Bernd Schirpke, T-Systems International
12/05/2014
13
Helix Nebula – Use Cases CERN: AtLAS Experiment on the LHC
Source: Bob Jones, CERN Bernd Schirpke, T-Systems International
12/05/2014
14
Helix Nebula – Use Cases ESA: Geohazard Supersites ESA The European Space Agency
THE CUSTOMER
“To provide for and promote, for exclusively peaceful purposes, cooperation among European states in space research and technology and their space applications.” (ESA Convention)
20 Member States
Five establishments in Europe, about 2200 staff
4 billion Euro budget (2012)
Over 70 satellites designed, tested and operated in flight, thereof 17 scientific satellites in operation
Bernd Schirpke, T-Systems International
12/05/2014
15
Helix Nebula – Use Cases ESA: Geohazard Supersites SUPERSITE EXPLOITATION PLATFORM
Transition to cloud in 2012
Multi-cloud On-Demand SAR processing tested and verified
performance equal or better than local
87.000 SAR products accessible
Data Catalogue extensions being tested/planned:
FedEO (US products)
GÉANT (Iceland SS, CEMS, TSX GEO)
Japan ERI
Downstream projects starting (ECMWF, DORIS)
Bernd Schirpke, T-Systems International
12/05/2014
16
Helix Nebula – business models
Helix Nebula – Business Models Business Model Development Example: Information as a Service
Bernd Schirpke, T-Systems International
12/05/2014
18
Helix Nebula – Business Models Business Model Evaluation Information as a Service
Ease of Implementation
3,5
Collaboration & Communication Platform for Science & Education Application Crowd
Generic Cloud Computing for European Big Science Versioned Cloud Computing for Science & Education
3,0
Brand Management Worldwide All-In-One Enterprise Cloud
2,5 2,5
3,0
3,5
Impact of Option
4,0
Bernd Schirpke, T-Systems International
4,5
12/05/2014
19
Helix Nebula – The Science Cloud data Security and Privacy European Data Security and Privacy
International Standards
All participating cloud providers have to be certified according to relevant international security standards, e.g. ISO 27000.
European Law
Customer Requirements
All participating cloud providers have to be compliant to European and national data protection laws and regulations.
Cloud providers have to fulfil special security and privacy requirements of research organisations if they want to offer cloud services to these customers e.g., regarding management of satellite or DNA data.
Bernd Schirpke, T-Systems International
12/05/2014
20
Helix Nebula – Cloud Federation and Marketplace
Helix Nebula – The Science Cloud Federated Cloud Services for Data Intensive Science Science
Other Sectors
Blue Box On-Premise Clouds
Commercial Clouds
THE CHALLENGE Large amounts of resources: >10,000 fat VMs No single cloud provider can meet the demands and manage the business risks Co-opetition with other European cloud providers Technical solution and governance model for cloud service management and brokering Limited budgets available through FP7 The SOLUTION Multi-cloud solution with “Blue Box” cloud manager Federation of on-premise and commercial clouds for open source and commercial cloud stacks T-Systems with strong position in Project Management Team, contribution of several technologies and responsible for Governance of Helix Nebula Bernd Schirpke, T-Systems International
12/05/2014
22
HNX – Helix Nebula Marketplace Commercial Marketplace for Federated Cloud Infrastructure Services (IaaS) Builds upon the work undertaken as part of the EC funding project and overall initiative Support by European cloud providers and integration with existing e-Infrastructures, a hybrid cloud Computing Market Place and open for new Cloud Providers Trusted cloud services through compliance with EU regulations and legislation Simplified procurement process for multiple cloud services Offered to the global scientific community, for both publicly-funded and commercial Research and Technology Organizations, offering large-scale and HPC-type deployments from the start. A focus on transparency and impartiality of the brokerage function. Trust is important.
Bernd Schirpke, T-Systems International
12/05/2014
23
HNX – Helix Nebula Marketplace Commercial Marketplace for Federated Cloud Infrastructure Services (IaaS) Initially four
commercial cloud providers integrated Amazon EC2 Bridge for compatibility with third party tools, such as StarCluster or any EC2-compatible tool Integration with the EGI FedCloud on our roadmap for 2014
Bernd Schirpke, T-Systems International
12/05/2014
24
Helix Nebula – The Science Cloud Inter-Operability with exiting e-Infrastructures DANTE offering
free IP connectivity in GÉANT for research traffic during the pilot phase NRENs have different commercial agreements (usually they apply a fee)
Bernd Schirpke, T-Systems International
12/05/2014
25
Helix Nebula – Progress Beyond
Helix Nebula – The Science Cloud Progress Beyond
Bernd Schirpke, T-Systems International
12/05/2014
27
XZELCloud Cloud Advanced Services on large-scale Federated Infrastructures
Bernd Schirpke, T-Systems International
12/05/2014
28
Helix Nebula – The Science Cloud A European Public-Private Partnership
Strategic Plan Establish multi-tenant, multi-provider cloud infrastructure Identify and adopt policies for trust, security
To support the computing capacity needs for the ATLAS experiment
Setting up a new service to simplify analysis of large genomes, for a deeper insight into evolution and biodiversity
To create an Earth Observation platform, focusing on earthquake and volcano research
To improve the speed and quality of research for finding surrogate biomarkers based on brain images
Suppliers
and privacy Create governance structure
Adopters
Define funding schemes
Bernd Schirpke, T-Systems International
12/05/2014
30
THANK YOU! Dr. Bernd Schirpke T-Systems International Emerging Products & Innovation Dachauer Straße 651, 80995 München +49 170 7949813
[email protected]