Cracking the Code of Network Outage Prevention

By Zachary Meath
Zachary Meath, Sophomore, Marist College, Computer Science Major
Zachary Meath,
Sophomore, Marist College, Computer Science Major

Voice and data communication networks are part of the foundation of our schools, homes, businesses and daily lives. Yet, with data volumes soaring, new mobile devices proliferating, and demand for network access mounting daily, there’s still much to be solved when it comes to the world of network management.

One solution in particular that my fellow students, Marist faculty and I are collaborating with IBM on is the invention of an agile optical network that is automated and easily managed. It sounds simple enough, but in order to accomplish this feat, our team needed to create a new way to reprovision a network in a matter of minutes, not days or weeks, which is currently the norm.

We started with what we knew because we had experience with software defined networking—a technology that enables data center operators to use software to efficiently control network resources—and we knew that it could provide network agility. We also needed a flexible and easy-to-configure controller. So, we decided to use the versatile open standard based OpenFlow protocol and Floodlight controller to manage our network. In order to test the agility of our application, we created an infrastructure test bed at Marist with Openflow switches in a multi-datacenter environment.

Marist College student, Zachary Meath, demonstrates an invention that enables IT professionals to quickly move network communications resources via a wireless phone or tablet.

Marist College student, Zachary Meath, demonstrates an invention that enables IT professionals to quickly move network communications resources via a wireless phone or tablet.
Marist College student, Zachary Meath, demonstrates an invention that enables IT professionals to quickly move network communications resources via a wireless phone or tablet.

For re-provisioning the network, we developed an application that reads various statistics on the network, then makes a call to the Openflow controller in order to make the necessary changes that our application deems necessary. The application we  created is smart enough to dynamically make changes to the network based on data it receives from the network. Sometimes, for example, an administrator may not be able to predict how much bandwidth is needed, but the network will know when to precisely add or remove bandwidth.

Another application we have written is a web-based graphical user interface called Avior that can manage a network from anywhere, on any browser. Avior enables a network administrator to add, delete or modify flows on the network—no matter where they are located. And because it is web-based, the network administrator can use Avior on a mobile phone or tablet.

One optimal use for this invention is network outage prevention. Let’s say that there is a virtual machine in a data center in New York City that is streaming a sports event to TV viewers and suddenly a natural disaster, such as a hurricane or flood, is headed towards that data center. With our invention, a network administrator could immediately and remotely migrate the virtual machine to another data center in New Jersey, which is safe because it is outside the potential disaster area.

The network administrator also can opt to provide extra bandwidth between the data centers to accommodate the virtual machine migration and reprovision optical links between the data centers to add bandwidth. Then, when the migration is complete, the software will automatically remove the unnecessary bandwidth. As all of this happens, a fan watching the game won’t even notice that anything has changed.

Another potential use of the invention relates to “cloud bursting,” which happens when a private cloud or data center suddenly “bursts” its workload demand onto a public cloud. When a cloud computing provider receives a burst from their customer, they need to have enough bandwidth active to accommodate the unexpected spike in traffic on their network. To make sure they can accommodate bursts, network providers need access to extra bandwidth at all times.

Our invention can automatically and dynamically reprovision bandwidth to accommodate sudden spikes in the network traffic. Also, when there is no traffic on that part of the network, all of the extra bandwidth links are automatically removed, saving money for both the customer and network service provider.

We’re proud to be collaborating with IBM and other research partners on a challenging project than can enhance and potentially transform the capabilities of the voice and data communications networks that we rely on each day.
___________________________

This post first appeared on asmarterplanet.com

 

Comments

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s