back to article Cell-network content crunch needs new cache designs, say boffins

It's increasingly clear to the telecommunications industry that content distribution is going to need to push further out into networks, to try and relieve congestion on the moderately-constrained backhaul that connects cell towers. Content caching at base stations can help, but as an IEEE Fellow from Hong Kong University of …

  1. Conundrum1885

    Intriguing idea

    Deploy the multi-terabyte SSD array, these days it should be quite low powered and probably solar capable thanks to the new quad junction 38% efficient full spectrum cells.

    I wonder if the phone companies will charge by the MB or by the hour, especially for large files.

    1. msknight

      Re: Intriguing idea

      If they're using Seagate kit then if you can get close enough, you can slurp the content for free :-D

  2. Trollslayer

    Can I be the first

    To point out someone involved with network issues called Ping?

    1. Hans Neeson-Bumpsadese Silver badge

      Re: Can I be the first

      A case of nominative determinism?

  3. Jeff 11

    Worth it?

    Has anyone looked at just how what percentage of backhaul traffic a local cache at the cell level is going to save?

    So much of what we consume on our phones is streaming content, which is difficult or impossible to cache as a third party. And even when you're talking about simple HTTP requests with relatively static responses, is there a great enough proportion of content that's repeatedly requested to substantially affect a large enough proportion of users?

    I don't want to say 'no', but I would imagine this is the case. It sounds to me like a massive amount of investment, maintenance and administrative headaches will be needed for a questionable return...

    1. Robert Carnegie Silver badge

      Re: Worth it?

      A while back I think the BBC wanted to put video servers in ISPs so you'd get video from there instead of across the Internet. This however might breach net neutrality, giving the BBC an advantage. I don't mind because I like the BBC. I think it didn't catch on, ISPs had a different idea - they would charge the BBC a fee for letting the ISP's customers watch BBC video. I think this hasn't caught on either.

      Another catch however is, if I reasonably encrypt everything I do on the Internet then how are you going to cache it?

      Still, if this refers to mobile data and maybe to buying specific videos from my phone company outside my ordinary data allowance, then there may be something in that.

    2. Andrew Hurdle

      Re: Worth it?

      I have deployed content caching in femto cells in test networks and also in specific live user trials. In my view it is far more about active content deployment rather than random cashing of users traffic. There are techniques for holding streamed content locally and these offer real advantages.

      As an example if you take a 2 minute news clip it will take about 90 seconds to buffer over a typical 3G link and still over a minute on 4G. However if it is served locally from an on base station server you can buffer it in 4 seconds. Not only does this give a great user experience, reduce back-haul requirements it also free up the radio resource required while also using less power.

      The further out towards the edge of the network you go - and the smaller the station - then the more intelligent you need to be about deploying the content while the backhaul has capacity.

      Andrew Hurdle - Edge Data

  4. Anonymous Coward
    Anonymous Coward

    I study real mobile traffic in great detail in my day job.

    I see a several problems with this.

    Half of all mobile traffic is video (by volume), and it's mostly YouTube which is encrypted.

    There is little point to stream video much faster than you consume it, plus a bit of buffering, as they might abandon it.

    Typically only have a few hundred users in a cell the chances of them asking for the same content are slim - OK say BBC home page, or all the news, but so what? it takes only a fraction of a second on the backhaul. E.g. everyones Facebook page is different.

    There is already HARQ (Hybrid ARQ) for caching the stuff actually being downloading/looking at the base station.

    Latency, the radio network latency in LTE is insignificant compared to all the other contributors.

    The top 10% users are responsible for >50% of all traffic (usually bit torrenters or something) and in some networks enjoy grandfathered rights (unlimited means unlimited!)... So chances are most of the data volume you see on a site is a handful of people.

    Typically 20% of sites carry 80% of traffic, it isn't evenly spread about (this seems to be a surprise to some people in the industry).

    The cost of backhaul is indeed significant but I think (I have no simulation to back this up) based on real life user activity, the type or traffic, the levels of encryption, the low numbers and low likelihood of users in same cell asking for same content makes bae station caching the whole internet impractical.

    Its Jevon's Paradox for bandwidth - make it faster/cheaper people will use and waste more of it...

    Does anyone know if ISPs (still) cache the some traffic into their own networks?

    1. Kevin McMurtrie Silver badge

      Re: I study real mobile traffic in great detail in my day job.

      ISPs commonly host third party edge cache servers. This greatly speeds up web pages that are heavily loaded with CSS, JS, and static images that block the initial layout. Software updates and streaming video are commonly hosted there too, which takes a big load off the ISP's pipes.

      Getting this to work at or beyond cell towers needs new technology. Heavyweight HTTPS encryption is used to protect static data when all you really want is tamper resistance to stop malware injection. If there was a third option, like a digital signature, then caching would be possible without adding any additional crypto steps. Such caching could use small tower caches or even neighboring cell phones.

    2. xybyrgy

      Re: I study real mobile traffic in great detail in my day job., used by content providers, not ISPs...

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like