The Cloud-Enabled Space Weather Platform

By Everett Toews

February 14, 2011

Space weather is the result of solar winds interacting with the Earth’s magnetosphere. The most visible effect of space weather is the phenomenon of the Aurora Borealis (i.e. the Northern Lights). Space weather research is diverse in scope and includes, among a host of related questions to explore, the study of the impact of space weather on satellites orbiting Earth. Now more than ever scientists require a scalable, robust platform to study the magnetosphere.

The purpose of the Cloud-Enabled Space Weather Platform (CESWP) project is to bring the power and flexibility of cloud computing to space weather physicists.

The goal is to lower the barriers for the physicists to conduct their science–that is, to make it easier to collaborate with other scientists, develop space weather models, run simulations, produce visualizations and enable provenance. Success of the project is measured by the broad acceptance and use of the platform by the space weather science community.

The community of platform users includes space weather physicists who are developing models to help us better understand space weather and the magnetosphere. The principal investigator for CESWP is Dr. Robert Rankin, Professor in the Department of Physics at the University of Alberta. In addition to the University of Alberta, the institutions that are connected are Peking University, the University of California Los Angeles (UCLA), the University of New Brunswick, and Sharcnet, which is a high performance computing center run out of the University of Windsor. The availability zone at the University of Alberta acts as the CESWP Cloud Controller, initially handling all requests to operate on cloud resources.

The CESWP application itself is running in a virtual machine on a node controller in the CESWP cloud. Users visit the application as they would any normal web site from a web browser on their desktop machine, laptop, tablet or smart phone. Users of the cloud platform are presented with a view that is a simple HTML web page rendered in their browser and interact with the application by submitting requests to the controller from the view. Depending on the nature of the request, the controller may load models from the database or initiate an asynchronous call to the CloudService to perform a cloud-based operation. The results of the request are then passed to a view, which is sent back to the users as the response.

In essence, this project is building a cloud for this international community of physicists and given the nature of cloud computing, infrastructure can be geographically distributed. For the purposes of this project, a wide area network (WAN) is required to carry the traffic. For the Cloud-Enabled Space Weather Platform (CESWP), Canada’s Advanced Research and Innovation Network (CANARIE) fills this role. CANARIE is a dedicated network of high-speed, fiber optic cable that stretches across Canada and links researchers throughout Canada and around the world.

To operate an IaaS cloud you require a software framework on which it will run. For CESWP, Eucalyptus was initially selected as the cloud framework but the Virtual Computing Lab, OpenNebula, Nimbus and Eucalyptus were also considered during the survey of cloud management software at the project outset during the end of 2009.

Ultimately, Eucalyptus was selected based on both technical merits and long-term prospects. Among the technical reasons was its support for the Kernel Virtual Machine (KVM) and the Amazon Web Services (AWS) application programming interface (API). Support for the AWS API was particularly attractive, as the option to operate as a hybrid cloud with AWS was important.

Infrastructure as a Service is a complex issue and, as a consequence, Eucalyptus is a complex piece of software. Eucalyptus provided an environment to experiment with IaaS, however, given that IaaS is still a relatively green field, new prospects, such as OpenStack, did not exist at the time of the initial survey even though they still warrant an evaluation.

The scientists can connect to their virtual machines via secure shell (SSH) or NoMachine.  NoMachine is remote access software with support for a graphical user interface (GUI). This means that researchers can use NoMachine to access their VMs and be presented with a GUI desktop as if they were sitting in front of a physical machine. NoMachine has been of significant value to the CESWP project and for these purposes has been a good choice for connecting to cloud based VMs with a graphical user interface.

To ease the interaction with the CESWP cloud a web application written in Groovy and Grails was developed. Groovy is an open source dynamic language for the Java Virtual Machine that is fully compatible with the Java language itself. Grails is an open source web application framework that applies principles like convention over configuration to improve development productivity.
To develop CESWP, the team followed the principles of Scrum. Scrum is an agile software development methodology focused on the iterative development of a product. Iterations are organized into a three-week “sprint” wherein the team creates a working product increment. That product increment is delivered to the researchers as a demonstration in order to solicit feedback.

Technically speaking, CESWP itself is composed of three distinct parts. First, there is the CESWP cloud.  The cloud is comprised of servers, network and Eucalyptus. These resources combine together to provide the Infrastructure as a Service that the physicists will use to conduct their science.

Second, there is the CESWP toolkit. This toolkit is included on every VM image in the cloud and is comprised of scripts, both bash and Python, which ease interaction with the CESWP cloud.  These scripts perform such functions as running simulations in parallel to perform parameter sweeps, bundling VM images and enabling provenance.

Third, there is the CESWP application. The application is primarily developed with of the Groovy programming language, the Grails web framework and the Scrum agile development methodology. These resources combine together to create a GUI web application with a wizard-based interface that the physicists will use to interact with the CESWP cloud.

The primary motivation of the Cloud-Enabled Space Weather Platform is to lower the barriers for the physicists to conduct their science. There are a number of factors that obstruct the space weather physicists from concentrating on their science. The CESWP cloud paired with the CESWP application and toolkit addresses each of these barriers.

First, the specification and acquisition of hardware is consolidated in the CESWP cloud. Instead of specifying and purchasing desktop or server hardware for individual researchers on a piecemeal basis, the purchasing can be done in bulk for the benefit of the entire group. The procurement of this bulk hardware could still take weeks or months but is done only once per period as opposed to multiplying this effort for every researcher whenever the need arises.

Second, the maintenance of the hardware is consolidated in the CESWP cloud. Naturally, the scientists will always require hardware with which to access the cloud resources. However, there will no longer be a need for each researcher to have a laptop on which to develop their models and a high-powered desktop machine on which to run their simulations. The cloud effectively replaces the need for each researcher to maintain separate sets of hardware.

Third, the CESWP cloud has currently limited the selection of operating systems to Ubuntu and CentOS on the virtual machine images. This prevents a proliferation of operating systems and enables the cloud administrator to focus support effort on these two. In our experience, the physicists do not particularly care what operating system they are running, as long as it comes with the precompiled and preconfigured software that they prefer to use so we tailored the operating system VM images built for our community of users.

Fourth, one of the most time consuming aspects of the scientists work is getting code to compile properly. Be it their code when they have moved to a new machine or the code of a framework or tool they would like to use. The CESWP cloud can reduce the amount of time consumed in both cases. Once a researcher has compiled their own code in a VM, they can then bundle that VM into another VM image. The new image can be instantiated any number of times without having to recompile the code.  Likewise, once a framework (e.g. the Space Weather Modeling Framework) or tool has been compiled on a VM, it to can be bundled and made available to all of the physicists without recompilation.

Fifth, when a researcher’s model has reached a certain level of maturity he may want to run that model as a simulation on a grid or cluster to take advantage of high performance computing.  This is of great benefit to the researchers as their code can be processed many times more quickly than on their local machine. However, grid resources are in high demand and, therefore, scientists often must submit their jobs to a queue in order to be processed. The wait time can be hours to weeks. Instead, utilizing the CESWP toolkit, the researchers can run their simulations on the CESWP cloud now. If the CESWP cloud is low on resources the researchers can burst onto the Amazon Web Services (AWS) cloud, for a price.

In addition to lowering barriers CESWP also enables global access to a researcher’s virtual machine and access to their VM from a variety of devices. By default the virtual machines are globally accessible via secure channels. The VMs can be secured with either usernames and passwords or usernames and private keys. All traffic to and from the VM is encrypted. This global access can come from a variety of devices such as smart phones, tablets, laptops, netbooks or desktops.  Global access also enables collaboration as the researcher’s colleagues can be invited to access the VM to share data and collaborate on model development.

The space weather physics community is internationally distributed. Having cloud computing resources geographically close to its users lowers latency. This improves their experience interacting with the cloud. In addition, having all of the researchers using a single internationally distributed cloud will make it easier to share resources and collaborate.

Provenance is also enabled in the CESWP cloud. When a VM is bundled for provenance, using the CESWP toolkit, all of a physicist’s model code and data are bundled along with it. That is, the virtual machine’s file system is saved into another VM image. Also, a snapshot is taken of all of the virtual machine’s attached storage.Thus the preserved instance becomes a reproducible record of the scientists work. It is exact, complete, and unambiguous.

Work continues on Cloud-Enabled Space Weather Platform. The CESWP application is at the prototype stage and requires further refinement for production usage. The CESWP toolkit has only begun and scripts are routinely being added to enhance its utility. Naturally, we would like to expand the CESWP cloud by adding compute and storage capacity. The projected date for putting the Cloud-Enabled Space Weather Platform into production is June 2011.

Although this is the Cloud-Enabled Space Weather Platform, what we are building is not necessarily specific to space weather. Ultimately, we hope to build a platform that could potentially be used by other scientific disciplines.

About the Author

Everett Toews received his Bachelor of Science in Computing Science from the University of Alberta and has been working in the software development industry for the past decade. 

Everett has been working at Cybera for the past year and a half where he is building a cloud for use by space weather physicists at the University of Alberta on a project that goes by the name CESWP.

More available about Cybera can be found here.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitive computing, memory-centric computing, high-speed communicat Read more…

By John Russell

US Seeks to Automate Video Analysis

January 16, 2018

U.S. military and intelligence agencies continue to look for new ways to use artificial intelligence to sift through huge amounts of video imagery in hopes of freeing analysts to identify threats and otherwise put their Read more…

By George Leopold

URISC@SC17 and the #LongestLastMile

January 11, 2018

A multinational delegation recently attended the Understanding Risk in Shared CyberEcosystems workshop, or URISC@SC17, in Denver, Colorado. URISC participants and presenters from 11 countries, including eight African nations, 12 U.S. states, Canada, India and Nepal, also attended SC17, the annual international conference for high performance computing, networking, storage and analysis that drew nearly 13,000 attendees. Read more…

By Elizabeth Leake, STEM-Trek Nonprofit

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitiv Read more…

By John Russell

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

The @hpcnotes Predictions for HPC in 2018

January 4, 2018

I’m not averse to making predictions about the world of High Performance Computing (and Supercomputing, Cloud, etc.) in person at conferences, meetings, causa Read more…

By Andrew Jones

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Nvidia, Partners Announce Several V100 Servers

September 27, 2017

Here come the Volta 100-based servers. Nvidia today announced an impressive line-up of servers from major partners – Dell EMC, Hewlett Packard Enterprise, IBM Read more…

By John Russell

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This