Networking

How coffee, traffic jams and hotel pools can crash networks

Organisations can do as much network capacity design as they like, but people and events inevitably conspire to create largely unpredictable challenges that put paid to the best-laid plans.

The clustering of people and things naturally mutates into largely unpredictable network challenges in time, scale, location and type. Photo: Shutterstock

Written in my Singapore hotel room and despatched to TechRepublic at 60Mbps over a wired LAN.

We can extrapolate the progress of technology with reasonable accuracy, but we have little idea what people will do with it once it's been deployed.

For example, you only have to look at the rise of texting, instant messaging, social networks and the app culture. No one foresaw their evolution precisely or their unexpectedly adverse impact on networks.

The ideal would be to model people and machine behaviours to predict future traffic patterns, which could then be included in a network design. And while we got close to doing these things successfully in the era of telephony, it's an approach that has not been applied in recent decades.

Even getting the averages correct has become a challenge, and it is the higher-order moments and temporal data that is missing.

So, I think we can safely say that no one understands the internet or mobile networks.

Beyond the traffic characteristics of applications and services being warped by human activities, there are further unknowns associated with machines and inanimate objects that also play a role. A wider perspective goes something like this.

Fixed-line telephone networks were dimensioned for three to four calls per day, each lasting three minutes. But then radio and TV voting and phone-ins took off and this simple design framework was significantly distorted

Similarly, mobile networks were not designed to support text messaging, which started life as an engineering-support facility and not a service.

The mobile 3G network was never designed to support large numbers of people watching movies or interacting continuously on social networking. And then comes the category of unintended consequences.

A morning session at a conference is well attended and there's very little communication on delegates' mobile devices. At 10.30am coffee arrives, and the session breaks. Some 500 people try to make calls and get online, and the network crashes under the load. Coffee has become a strange attractor that crashes networks.

People driving along a stretch of freeway may generate one or two calls every mile. But when an accident occurs, a jam rapidly builds up. With traffic at a standstill, suddenly thousands try to phone or text home and the office in each one-mile section.

A YouTube video goes viral minutes after uploading, and the word spreads by email, text, instant messaging and social networks. Within an hour, millions are trying to view the clip, and of course the net struggles to cope.

The clustering of people and things naturally mutates into largely unpredictable network challenges in time, scale, location and type. Moreover, it seems mostly impossible to predict, and we know this problem is not about to go away.

So here is a new phenomenon to add to my list of network traffic disruptors. I'm in a hotel pool on the 57 floor at over 200m above ground level with a spectacular view over the city. As you might predict, people are posing and taking lots of pictures and making movies. But how about bathers in the water with tablets, Skyping their friends and videoconferencing around the planet?

I have just counted nine people with tablets in the pool at the same time. This sort of activity is unpredictable, and no doubt the wi-fi and 3G network is feeling the strain.

Today, we know a lot about the sociology of people and nothing of the sociology of things. So be prepared for some significant network surprises to come. And the way round these problems? Stop optimising. Instead, waste bandwidth and overprovision everywhere. It is the only viable option.

But the good news is that bandwidth is the lowest cost commodity we can produce and deploy - it costs virtually nothing per Gbit. Once the civil engineering costs are paid and the fibre is in the ground, then it really can be open season on bandwidth.

About

Peter Cochrane is an engineer, scientist, entrepreneur, futurist and consultant. He is the former CTO and head of research at BT, with a career in telecoms and IT spanning more than 40 years.

12 comments
peter
peter

The first time this happened with a vengeance was when the 'Phone in Radio Programmes' started and >500K people decided to vote at the same time. After that it has just got worse...

dblethen
dblethen

The start of the first gulf war came out as an interruption to normal television programming. Shortly after the announcement, the Braintree Massachusetts telephone switching office was brought down on volume. Normally the telephone company can react and throttle calls adequately to prevent overwhelming a switch, but the spike was so fast that it could not be accomplished. There is no military operation out of Braintree, so what was the cause? The interruption to normal programming cut right across the announcement of winning lottery ticket numbers. The Massachusetts lottery offices are in Braintree. I hope this give you all a laugh.

tzemisa
tzemisa

I have been told numerous times that the Internet service to which I have subscribed is a waste of money. The person who made these statements manages a network that has failed a number of times due to increased device numbers and the unpredictable use of them. I agree with the second last paragraph in this article but I don't like the wording "waste bandwidth". My network was ready for the influx of mobile devices and will be ready for BYOD too, heck we may have users who bring a smart phone, tablet, notebook and be actively engaged with all of them....

The_Real_BSAFH
The_Real_BSAFH

Other than the cell towers that may or may not have generators, one problem sorta cures the other.

peter
peter

I was in Hong Kong recently where 1Gbit/s both ways is the norm and many buildings have three fibre networks vying to get your business - and the customers complain bit rates drop to 700Mbit/s. I was getting over 100Mbit/s wifi for free :-) In Singapore last week I experiences wired access at over 100Mbit's both ways whilst in Korea and Japan it seemed faster. But all three had vastly different mobile network and philosophies. In Japan for instance you see a lot of VoD movie watching on the Metro in a morning and evening - and that takes bandwidth and connectivity. In the EU you have to visit/live in Jersey (Channel Islands) to see 1Gbit/s as the standard for business now being rolled out to all homes with open wifi and 3G at every termination. And as you travel you see countries dominated by mobiles for internet access, whilst others have a big population of Tablets and Pads or laptops. For sure the PC is on the wane! Oh - and wireless can only do it if there is a dense optical fibre network down to the last/first km :-)

gevander
gevander

(Let the [b]reader[/b] beware) [quote]But the good news is that bandwidth ... costs virtually nothing per Gbit. [b]Once the civil engineering costs are paid[/b] and the fibre is in the ground, The bad news is, the civil engineering costs are [i]never[/b] paid, at least not in the US. This is at least one of the reasons why bandwidth is so expensive in the US and why most of the major carriers offer only plans that throttle your data after 'x' amount. In the US, when telephone service was monopolized by AT&T and the Bells (all subsidiaries of AT&T), service was relatively cheap, but nobody could enter the market because nobody could match AT&T's prices. After the break up, prices rose and competition increased for a time. Now we are back at a tipping point where there are several large companies and no company has a real competitive advantage over any others (excluding the VoIP-only companies). In cellular communication, we have another version of that situation: Several large corporations dominate the market and use cartel-like activities (price fixing/coordinating/matching, etc) to keep new competition out of the market. They "have no money" for infrastructure upgrades (or to pay their Level 1 & 2 service techs), but millions to spend on executive compensation. Because of their profiteering activities, the US is a first world country with a third world data pipe. A couple ideas to restructure the system: Break up the big companies, like was done with AT&T; have the government own the backbone of the system and be responsible for its upgrades/maintenance (tax the companies on a per user basis to fund the backbone). There are probably many other possibilities as well.

pceasies
pceasies

Bandwidth just doesn't seem to be there. You start out with fiber and super low latency, but by the time it reaches the hotel it is already down to less than 100Mbps which is quickly consumed by users online. Come night when everyone relaxes and gets online (especially HD video streaming) the bandwidth is quickly consumed by >20 people. Even with a dedicated caching server and equipment to distribute bandwidth, it still is gone fast. A Proxim Wireless G access point connected to the LAN by gigabit is quickly overloaded when 20 clients try and access network files at the same time. For a place like a hotel, massive amounts of equipment are needed to handle such huge demands. This article helps convey how huge of a setup is needed to support masses of uses at the same time: http://arstechnica.com/features/2012/08/why-your-smart-device-cant-get-wifi-in-the-home-teams-stadium/

platteriver33
platteriver33

Does anyone remember the electrical power grid failure in 1997, half the western US was effected. Chaos!

garry
garry

They need to start developing networks to be more "on demand" like the power grid. However, unlike the power grid, it does have to have storage ability. Not the network as a whole, but the areas that do store information need to be as flexible as the grid. I can't imagine what the models for this would be like.

Marc Jellinek
Marc Jellinek

"have the government own the backbone of the system and be responsible for its upgrades/maintenance" So they can do as good a job with our telecommunications infrastructure as they do with the roads? Get the government OUT of telecommunications at all. The regulatory costs and hurdles of entering the telecom market are so insanely high that they artificially keep competitors out of the market. One WiMAX node can easily cover 4-5 miles, providing wireless internet, voice and video service. Clearwire (a WiMAX based carrier) planned on a node every 1.5 miles to maintain quality of service. The cost to provide internet, voice and video to the same population using wired or 4G services is many times higher. Why doesn't Clearwire rule the telecom markets? The regulatory burdens are HUGE and the embedded carriers do everything they can to keep them out. Government isn't the answer, it's the problem.

dblethen
dblethen

Without some form of regulation, large, embedded corporations take advantage of market power to keep smaller competitors and innovations out (or buy them out). Oligopoly and monopoly power should not be underestimated. Government law is what ended the AT&T monopoly. So you want to encourage smaller companies and innovation while giving large embedded carriers free reign to control their market? The problem isn't that there is regulation, it is that the regulations are too complex or favor the embedded players - the result of pitched political battles, and sold out principles. Do you want to make a regulation ineffective? - make it as complex as you possibly can and then blame the regulation. When it comes to the telecommunications backbone, the United States is partially the victim of its own success. Our embedded capital investments include millions of miles of copper and older fiber optic lines. I cannot imagine the government owning "the backbone" - the capital behind that is in the billions (trillions?). But I can't imagine letting the large carries have unregulated oligopolies either.

NickNielsen
NickNielsen

who complain about the competence of government while also not wanting to pay for competence in government. Not saying. Just sayin'.

Editor's Picks