NETWORKING

  • 09/23/2014
    7:00 AM
  • Rating: 
    0 votes
    +
    Vote up!
    -
    Vote down!

IoT: Beyond SDN

The Internet of Things will require more scale, simplicity, and higher levels of abstraction than what software-defined networking is designed to provide.

Cloud computing and web-scale computing require data center operations at unprecedented levels of scale and speed. This has created the need for new levels of abstraction, agility and automation. SDN arose from the need to automate networking at scale when cloud data centers started serving millions of users.

Unfortunately, the Internet of Things (IoT) is about billions of users. The transformation driven by SDN, such as network virtualization, was not developed with billions of users in mind. IoT will require mass-market levels of scale and simplicity. Automation will not be limited to the needs of a few sophisticated cloud architects and data center managers, but will need to address mass-market consumers.

The need for real-time array processing architectures for machine learning will drive high-bandwidth, non-blocking, full- or partial-mesh fabric architectures in networking. This will drive a need for higher level of abstraction than that available through overlay network virtualization.

Let's take a closer look at the networking requirements for IoT and how they go beyond what SDN provides.

First off, administration of the network is different for IoT. While SDN currently addresses automation and self-service through abstraction and automation, it assumes a fair degree of sophistication by its user. In contrast, IoT will require a much higher level of abstraction and simplicity. It is unrealistic to expect someone to update a Python script to get his self-driving car to pick a different route to work.

SDN is largely focused on providing automation and agility for large, centralized data centers. Similar to data caching, which optimizes storage location based on usage, IoT will require "application" caches running applications closer to the customer.

Business intelligence and analytics workloads are generally housed in large data centers running data mining technologies such as Hadoop in batch mode. The IoT, on the other hand, requires data centers closer to the user because of real-time needs. Smaller, distributed data centers will be necessary to provide capabilities such as offering real-time promotions based on customer location and activity.

Finally, as business intelligence (BI) evolves from reactive to predictive, computing styles will change. Clustered file systems and batch mode processing technologies such as Hadoop were sufficient for reactive BI analytics. Predictive analytics, however, require complex technologies such as machine learning.

Machine learning (ML) is a branch of artificial intelligence that deals with outcome prediction. It processes vast amounts of data to "learn." Most, if not all, of this data will be streaming real time from sensors. Imagine a jet engine with a hundred sensors streaming data real time to its airline, or other applications like remote health monitoring.

ML will require networks to connect streaming patterns of data in real time. Streaming data analytics, unlike traditional big data analytics, does not require centralized storage and retrieval. In many cases, the value of stored data actually diminishes with time.

One such network architecture is artificial neural networks (ANN). While in the past, ANNs have been used in niche applications, ML is likely to encourage wider adoption. Today's network architecture has for the most part transitioned from hierarchical connectivity to spine-leaf or CLOS fabrics. But the need for real-time stream processing, coupled with a desire to run applications closer to users, will drive full- or partial-mesh fabric architectures in networking.

Mesh-fabric architectures will call into question the benefit of overlay network virtualization, which is the leading manifestation for SDN. Overlay network virtualization implements tunnel overlays providing abstraction, automation and agility for micro segmentation on physical network fabrics.

The need for mesh fabric connectivity will cause overlays to merely replicate the underlay with no additional abstraction. Some other mechanism will be required to provide abstraction, automation and agility in mesh-fabric networks.


Comments

Addressing Mass Market

"IoT will require mass-market levels of scale and simplicity. Automation will not be limited to the needs of a few sophisticated cloud architects and data center managers, but will need to address mass-market consumers."

Menon, you are right. It has to be generalized, so that it can address mass market. The ultimate aim is a Technology driven market for large mass.

Re: Addressing Mass Market

The trouble with the whole concept of the Internet of Things seems to confuse a lot of people, its similar to "Cloud Computing" how many consumers actually think that data is being stored somehow in the sky above us? So when a service provider speaks of the Internet of Things are we talking about the connected world, smart devices or something else? You can see how confusing this could be.

But having said that, the consumer these days is very receptive these days to new ideas and concepts and cloud technology is the future of the connected world where automation is at the heart of it.

Re: Addressing Mass Market

I think you're right about confusion around the concept, @david_allen. Cisco's own terminology (the Internet of Everything) probably doesn't help.

Re: Addressing Mass Market

As internet access continues to take on more prominent roles in our lives, how long before it reaches the same status that the government has granted to other public services?  High quality national highways have a direct impact on GDP.  The same can be said of high quality network infrastructure.

Re: Addressing Mass Market

Interesting point @AbeG. Right now, the government seems intent on taking a laissez-faire stance.

Re: Addressing Mass Market

If an economy moves beyond the service economy and a major portion of its GDP is created by the information economy then in many ways connectivity becomes more important than highways.

Insurance firms and smart cars are a good example, these firms use data from smart cars to offer customers that are safer drivers on the road a lower premium.

Re: Addressing Mass Market

"As internet access continues to take on more prominent roles in our lives, how long before it reaches the same status that the government has granted to other public services?  High quality national highways have a direct impact on GDP.  The same can be said of high quality network infrastructure."

AbeG, there is no doubt that IoT is going to play a prominent role. Th only thing is they have to install a self talking module to the existing infrastructure.

 

Re: Addressing Mass Market

"As internet access continues to take on more prominent roles in our lives, how long before it reaches the same status that the government has granted to other public services?  High quality national highways have a direct impact on GDP.  The same can be said of high quality network infrastructure."

AbeG, there is no doubt that IoT is going to play a prominent role. Th only thing is they have to install a self talking module to the existing infrastructure.

 

Re: Addressing Mass Market

I absolutely agree to you, IoT is indeed confusing to me as well when compared with cloud.

With cloud we get almost everything while SDN is a technology to automate infrastructure provisioning.

 

Re: Addressing Mass Market

I believe with IoT, Data analysis shall turn more complex as this will help in understanding customer, wherein cloud shall reap the benefit from its new offerings.

Re: Addressing Mass Market

How are we differentiating Internet of Things versus Cloud?

Re: IoT Beyond SDN

Thanks for this in-depth look. Indeed, networking (and technology in general) is often a sea of buzzwords, and as much as we all love to talk about the upcoming trends, it's not so often that we stop and take a look at the specific developments that need to be made to get us there - after all, we're the ones that are going to have to develop them! Networking is a tough game, with all differing levels of develop - folks developing one technology have no idea what's going on somewhere else, and it's common for different areas to move at different speeds.

As for IoT, SDN, and the networking technologies therein... yeah, we have a ways to go. It depends how broad your definition is (some may say devices that are already in most homes constitute IoT), but when you throw analytics and smart functions into the mix, yes, we need a backbone for these devices that doesn't exist yet - which is interesting, because some of the devices do! As you say, Mr. Menon, the average consumer has no idea about all this, and more than all these other trends, IoT target them! We're asking for trouble if we're planning on putting the devices to market before everyhing is in place!

Re: IoT Beyond SDN

Agreed, the customer does not consider the type of internet connection that is required for a certain device. Different IoT devices require different capabilities from the internet. Some devices connect to the internet just to share data across devices while other devices connect to the internet to gain access to cloud resources.

I feel, SDN will evolve over time to meet the needs of the market. Automation is in current demand in the market. However, virtual security (enabled by SDN) and Software Defined Mesh Networks that can create cost efficient networks in location where providing traditional connectivity would prohibit deployment to move forward, is also building up market demand.