The Next Big Thing
Posts about next generation technologies and their effect on business.

SDN: Software Defined Networks

sdn thumb.gifI recently facilitated a discussion where we deliberated the business value of Software Defined Networking. This was an interesting exercise, since I was trying to get those involved to move beyond the technology and give examples of why SDN is important to the business itself. In preparation for that discussion, I reviewed the book SDN: Software Defined Networks by Thomas D. Nadeau & Ken Gray among a number of other sources.


I found the material in the book to be a useful orientation to the current state of the SDN market as well as develop a contextual understanding of the flexibility provided and the approaches needed to build value through an SDN. One point made clear through reading the material is that one of the key benefits is flexibility. You’ll only internalize what that means to your organization through experimentation and using SDN. This is best summed up through the following sentence from the last chapter.

“Though it’s too early to pick a winning technology, or even a winning definition of SDN, one thing remains true—the explorations into SDN will change our present method of operation.”


This book facilitates developing that contextual understanding of what the possibilities could be so that you can plan the approach that works best for you. There is no one right answer.


One of the areas I thought could have been brought out a bit more is the strategic implications of SDN on enterprise service functionality and architecture. It appeared the assumption was that there are no real implications on the applications (that generate business value) themselves. It is all about data packets as network traffic being routed more flexibly.


There are business value generation areas to be explored that are enabled by SDN allowing network operations unique to data on the move. This is somewhat like the revolution that took place when object-oriented approaches (of the mid to late 80s) shifted how we viewed data class and instance unique processing, while at rest. Data-on-the-move specific processing may be a bit too esoteric for the target audience of this book though.


It is clear that the SDN market is at the early stages and there remain many opportunities to understand and address. I thought this book was a worthwhile addition to increase understanding.

SDN - the foundation for the agile enterprise

I recently facilitated a discussion between several technical leaders in HP on the topic of SDN - and you can listen to it on-line. Much of the conversation centered on the differences between the relatively inflexible view of networking that everyone has been so successful with and the more dynamic possibly with SDN.


SDN and flexibility.png


Software define networks are a relatively recent, yet foundational technology innovation, changing how organizations should think about the value possibilities of networks and even networking. The role of SDN in an agile organization does not seem to be nearly as well understood as I thought it should be.


We’re used to talking about software-defined data centers, allowing for the dynamic reconfiguration of computing elements, turning processors off or reapplying them elsewhere when they are no longer needed. The networks to date have not been up to this dynamic level but SDN can address this.


When I consider of some of the innovations possible with SDN, I think back to the 1980s when organizations were first starting to embrace object-oriented programming. The thought that data and processing could be integrated was quite radical. Yet, quite common today. Object oriented techniques are only applied to data at rest, essentially when it was sitting within a system.


With SDN there is the possibility to integrate data on the move with processing – a quite different set of possibilities exist, but only if we grasp the potential and plan around the possibilities.




Networking and thoughts on systems of action

Odecisions.pngne of the major shifts underway whose implications are poorly understood by most organizations is the move to software defined networks. These networks are not like the traditional hard wired communications path we’re used to or even the autonomic systems of the human body, relying on rules that are predefined. They are more cognitive systems that enable and even make decisions based on experience.


The difference can be explained with the following example. When you are playing catch, you reach for the ball flying towards you. You position your hand based on previous experiences rather than calculations or rules. If you catch the ball, it reinforces your experiences, making you better. If you drop it, you change your behavior the next time. This approach is a foundational change what I include in my definition of systems of action.


We don’t know how to do this with software perfectly yet, but as computing capabilities increase and the algorithms improve, the application of these techniques is well within reach. Networking is one area where we’ll see it early, creating an Internet that is responsive to the changing needs of the day. Eventually expanding out to most business processes. The flexibility of SDN will impact how applications are written in much the same way that hybrid cloud and IaaS should influence the architecture of applications today.


Searching and sentiment analysis are other areas where we’re seeing these techniques applied today. Learning algorithms attempt to derive intent, moving to a negative response time where organizations can influence decisions and actions can be taken before the decision is made.


One of the major drivers for this adoption is the scarcity of attention in business today. These approaches will allow us to focus attention more effectively and filter through the torrent of information and more importantly the choices flooding us today.

Network Fabric for Cloud

Flexfabric.pngToday, HP Launches Industry’s Most Complete Software-defined Network Fabric for Cloud. This network fabric is built on HP FlexNetwork architecture, enabling business agility for clients by delivering two times greater scalability and 75 percent less complexity over current network fabrics while reducing network provisioning time from months to minutes.


This is possible by:

  • Improving IT productivity by unifying the virtual and physical fabric with new HP FlexFabric Virtual Switch 5900v software, which, in conjunction with the HP FlexFabric 5900 physical switch, delivers advanced networking functionalities such as policies and quality of service to a VMware environment. Integrated Virtual Ethernet Port Aggregator (VEPA) technology provides clear separation between server and network administrations to deliver operational simplicity.
  • Reducing data center footprint with the HP Virtualized Services Router (VSR), which allows services to be delivered on a virtual machine (VM), eliminating unnecessary hardware, by leveraging the industry's first carrier-class software-based Network Function Virtualization (NFV).

As organizations move to software defined networks, some fundamental changes in the approach will be required and these products are a start down that path. Here is a video with a bit more high level discussion and some details:


Do you need a technical bucket list?

list.pngI wrote a post about what a technologists can do to be relevant a while back and at the time I thought that a list like this would be relatively transient. It turns out that unlike buzzwords, the underlying technologies are usually here for the long haul -- just ask a COBOL programmer. The half-life of the experience is likely much longer than I thought.


I was in a discussion today where we talked about a list of experiences a technologist needs to have in order to talk with some degree of authority about the next big thing in an enterprise context. Naturally, a person can’t know everything to the same level of depth, but there is a basic, useful level for every strategic technologist to have.

Some of the obvious ones I’ve mentioned before were:

  • Install a public cloud-based virtual machine and use it for something
  • Write an application for a mobile device and get the app listed in the app store
  • Take an on-line class (or maybe a couple every year) through a tool like coursera

A couple of those items would have been as applicable 2-3 years ago as they are today. Some have changed quite radically in their capability in that timeframe. I’ve done each of them at least twice for one reason or another and each time I learned something new.


If I were to add a new one that I haven’t touched in a very long time, it would likely be something to do analytics. There is a bit of a problem with this one though, since having enough data to do something useful and interesting may be tough.


I mentioned I was going to experiment with 3D printing. I now need to find something in the Internet-of-Things space as well.


I’ve probably looked at all these things enough to understand what their good for, but actually tackling a project brings that perspective to a whole other level. The hands-on experience doesn’t need to be production ready quality, since the goal is as much generating the exposure to the issues and ideas as it is solving a particular problem.


What other areas should a technologist tackle? And how? I haven’t even mentioned anything in the networking space. Anyone who has looked under the covers of Software Defined Networks probably knows the depth of impact changes in this space will have for the future.


The book Outliers talked about spending 10,000 hours on an area to become great. I wonder how tackling 400 technology domain experiences allows you to be successful - that’s 10 a year for 40 years.

Follow Us
About the Author(s)
  • Steve Simske is an HP Fellow and Director in the Printing and Content Delivery Lab in Hewlett-Packard Labs, and is the Director and Chief Technologist for the HP Labs Security Printing and Imaging program.