Looking down the LAN road, the Terabit Ethernet milestone is now in sight. While 3.2Tbit/s and 6.4Tbit/s speeds were demonstrated in test environments by Siemens/WorldCom and NEC/Nortel respectively starting in 2001, the first set of viable solutions are just now taking shape.
A recent issue of Optics Express included a paper detailing the efforts of researchers from Australia, Denmark and China who joined forces to demonstrate the feasibility of a Terabit Ethernet over regular fibre-optic cables. Terabit speeds bring us to the times-one-million improvement in speed from when Ethernet appeared in 1976.
By focusing on materials research related to fibre-optic circuits, Australia's Centre for Ultra-high bandwidth Device for Optical Systems (CUDOS) achieved a breakthrough with the introduction of an exotic compound called "Chalcogenide", which could make commercialising Terabit circuits practical. Although CUDOS Research Director Ben Eggleton says it will take years to reach production readiness, this does coincide with internet pioneer Bob Metcalfe's prediction that we may start seeing the first commercial use of Terabit Ethernets by 2015.
Currently the industry is focused on shorter-term goals. The IEEE 802.3ba is working on 40GbE and 100GbE standards, with NTT being the first company to announce a reliable 100GbE circuit. But many network vendors are focusing on 10GbE, in particular, development of cost-effective 10GbE interfaces for copper, so buyers don't have to upgrade to fibre-optics.
From their debut in 2001, 10GbE switches have indeed become more affordable, dropping from about US$40,000 to $4,000. Industry analysts expect 10GbE adoption to jump 30% this year.
Most campus LANs are getting by with speeds of 100Mbps, but there are examples of 1GbE and 10GbE switches at the server and backbone layers, and also the use of fibre-optics between servers. And most laptops ship with an Ethernet card capable of handling 1Gbps or even 10Gbps. What's more, wireless LAN speeds are slowly catching up with wired LANs.
What will we possibly do with all the new bandwidth? That sounds like a legitimate question, but Microsoft co-founders Bill Gates and Paul Allen had to deal with a similar question when they dreamed of putting a computer on every corporate desk and in every home.
If immediate needs were technology's guiding lights, we would all still be in the Stone Age. Sometimes necessity is indeed the mother of invention, but inventions can create newer necessities and propel needs to newer heights.
Metcalfe's dream for Ethernet was driven by the belief that if you build it, they will come. And that includes the needs themselves. Last year Metcalfe said he wanted to "help shape a road map" to Terabit Ethernet, because "we're going to get there anyway."
As we move further into the paradigm of cloud computing, where computing power and storage will gradually move to the centre of the network, it becomes necessary for the network to be fast enough to meet the needs of this new, highly distributed model. The aspiration of "the network being the computer" can only become real if the network is as fast as the computer, if not faster.
The possibilities are endless for applications that Terabit Ethernet would influence, with one obvious example being high-definition web/video conferencing tools from the desktop.
It would also open the door for vertical application areas that tend to be document/image centric such as healthcare (electronic health records), patient care (diagnostics, medicine, surgery), research (pure sciences and pharmaceuticals), insurance (claims processing), education and training, manufacturing (design, engineering, service, sales), retail (next-generation e-commerce including advancements in Second-Life), media, communications, entertainment, defense, real estate, tourism and so on.
One theme that cuts across these areas is an applied technology we will be hearing more about called Augmented Reality (AR). It puts a new twist on virtual reality by complementing real-life video/audio with virtual (or pre-recorded) video/audio.
AR opens up a number of of possibilities across industry verticals, but consider this example: surgical care. With AR and robotics a doctor can perform a complex life-saving surgery with the benefit of 3D images of documented symptoms, which are augmented with the actual condition of the patient as captured by real-life 3D video images coming from multiple camera angles and sensors.
The advancements in science and technology have never been so much about "why" as they have been about "why not" and "how far". The march toward Terabit Ethernet will clearly lead to many of the advances discussed here and most likely many others that today we cannot even fathom.