In a press release today, Virgin Media announced that it will be offering a new 100Mb broadband service to consumers. The roll out will commence by the end of the year, however no pricing has been revealed yet. Virgin say the new service will offer speeds that are on average 24 times faster than competing broadband services.

In less than two years Virgin Media have gone from offering 20Mb to 50Mb and now 100Mbps and the company says it is all down the the flexibility of their fibre optic network that they have sole control over.

According to research conducted by Ofcom in conjunction with SamKnows, the average broadband speed in the UK is a lowly 4.1Mbps, which is well below the advertised speeds that most ISPs now say they offer. However Virgin Media, due to its fibre network can provide it's customers with 84 percent of the speeds advertised, compared to just 58 percent for it's closest competitors which typically use ADSL.

Neil Berkett, Virgin Media's CEO said "There is nothing we can't do with our fibre optic cable network, and the upcoming launch of our flagship 100Mb service will give our customers the ultimate broadband experience."

"The ultimate broadband experience" will however pale in comparision to what Google has planned for the US. Towards the start of the month the search and advertising giant announced plans that it would be entering the ISP market. Google hope to role out affordable broadband to the masses with speeds as lofty as 1Gbps, that's ten times faster than the service Virgin Media are announcing today. Eat that Mr Berkett!

Last year the company rolled out its £38pm 50Mb broadband service which is operated on their new DOCSIS3 network and is not currently subject to bandwidth throttling unlike the other broadband services they provide. The service can be had for a reasonable £28pm if taken out with a Virgin Phone line.

It is unclear at this time how Virgin Media will incorporate the new 100Mb service into its broadband line up. Whether it will stick to offering three broadband services by upgrading it's customers to faster speeds, or adding a fourth service is something I can only speculate on at the moment.

The new 100Mb service will allow customers to download a music album in 5 seconds and a HD movie in just under 7 and a half minutes. Virgin Media are at the moment leading the way to a faster future in the UK. The company is already trialling a 200Mb service in Kent with plans to widen the trial to Coventry.

Since it's creation in the early 1990's, by Sir Tim Berners-Lee, the World Wide Web has operated on top of the HTTP and TCP protocols. Almost everything an average user would do on the net would have these protocols working behind the scenes to request, reply and display a website or page to the user. Over the years we have seen great advances in speeding the web up, from the increasing usage of fibre optics to better programming methods of web sites and servers. The Internet though can only be as fast as the protocols it operates under can provide.

With this in mind Google wants to augment the ageing HTTP protocol with it's own SPDY (pronounced "speedy") protocol, with the aim of reducing latancy and therefore allowing websites to load faster. As Google describe on their blog HTTP is an  "elegantly simple protocol", however as part of it's 'Lets make the web faster' initiative, Google thinks that HTTP has many shortcomings when it comes to providing next generation web services and experiences. As part of their research Google has found that HTTP has the following shortcomings (quoted from chromium.org):

• Single request per connection. Because HTTP can only fetch one resource at a time (HTTP pipelining helps, but still enforces only a FIFO queue), a server delay of 500 ms prevents reuse of the TCP channel for additional requests.  Browsers work around this problem by using multiple connections.  Since 2008, most browsers have finally moved from 2 connections per domain to 6.
• Exclusively client-initiated requests. In HTTP, only the client can initiate a request. Even if the server knows the client needs a resource, it has no mechanism to inform the client and must instead wait to receive a request for the resource from the client.
• Uncompressed request and response headers. Request headers today vary in size from ~200 bytes to over 2KB.  As applications use more cookies and user agents expand features, typical header sizes of 700-800 bytes is common. For modems or ADSL connections, in which the uplink bandwidth is fairly low, this latency can be significant. Reducing the data in headers could directly improve the serialization latency to send requests.  
• Redundant headers. In addition, several headers are repeatedly sent across requests on the same channel. However, headers such as the User-Agent, Host, and Accept* are generally static and do not need to be resent.
• Optional data compression. HTTP uses optional compression encodings for data. Content should always be sent in a compressed format.

Their findings have led them to the development of the SPDY protocol. Initial simulations of the experimental protocol show definite speed increases over HTTP. The company has set up a test that comprises of a typical computer system, running a special version of the Chrome browser that can handle SPDY requests. Google found that after connecting to the top 25 websites on the Internet, over half loaded faster with their protocol. Some sites loaded 64 percent faster over SPDY compared to HTTP.

Google being as collaborative as ever wants help from the outside world and as one of it's goals for SPDY, wants the open source community and industry specialists to help further the development SPDY.

For more information see the SPDY whitepaper.

How many more markets can Google dip it's toes into? Today the Web and Internet powerhouse said that it's planning to build and test an ultra fast fibre based broadband network and trial it in communities around the US that are interested in participating. The service will offer speeds of around 1Gbps, which is 100 times faster than what the average American household has access to. If successful Google will more than likely expand the project further and offer full fibre-to-the-home connections sometime in the future and at a competitive price. This announcement comes after Google previously announced plans to enhance connection speeds by augmenting the ageing HTTP protocol with their own SPDY protocol. Early tests of the new protocol have been encouraging for Google.

Initially Google are after at least 50,000 subscribers but hope that up to 500,000 people will sign up to the service, which Google say is a learning exercise to see how next generation networks can be built and run. Maybe that's too modest a figure as I suspect that many millions of people would find the idea of Google as an ISP intriguing. No doubt there will be a lot of chatter both for and against Google entering the ISP business.

Google wants to experiment with faster Internet access as it has specific agendas that it wants to explore including:

• Next generation apps: We want to see what developers and users can do with ultra high-speeds, whether it's creating new bandwidth-intensive "killer apps" and services, or other uses we can't yet imagine.
• New deployment techniques: We'll test new ways to build fiber networks, and to help inform and support deployments elsewhere, we'll share key lessons learned with the world.
• Openness and choice: We'll operate an "open access" network, giving users the choice of multiple service providers. And consistent with our past advocacy, we'll manage our network in an open, non-discriminatory and transparent way.

Google has put out a request for information to help it identify communities that would be interested in the trial. You have untill March 26^th to register you're interest and they are also encouraging local governments to get in touch with them too. Google will announce later in the year which communities have been selected for the trial. I suspect Google will get more interest than they thought they would because this announcement is potentially game changing. If it's successful, why would Google want to pull out of it and not offer a fully fledged ISP service?