So it happens.

As the website states, it works by:

• Sending your page requests through Google machines dedicated to handling Google Web Accelerator traffic.
• Storing copies of frequently looked at pages to make them quickly accessible.
  Downloading only the updates if a web page has changed slightly since you last viewed it.
• Prefetching certain pages onto your computer in advance.
• Managing your Internet connection to reduce delays.
• Compressing data before sending it to your computer.

Basically, the possibility of acceleration is based on the facts that:

• Web data can be compressed.
• Binary (or text) deltas are essentially small enough.
• Most data don’t change often.

This reminds that my idea on GridDistribute that:

• Distribute data in a way that is “Lookup”-able, say, with an data identifier, you can easily find who that have the data.
• To distribute data in a Peer-to-Peer manner, so the load of the central server is drastically reduced.
• Self-Controlled data flow, where a scheduler is not necessary for most operations.

These ideas might be used by Google’s web accelerator later. Let’s see.