Low Latency WAN Options

Many companies have added low latency to their list of requirements for WAN (Wide Area Network) connections. Why has latency suddenly gained such importance and how do you get low latency?

Latency is the time it takes for packets to get from one place to another. The latency on your LAN probably isn’t a worry. The latency on your long haul WAN connections may well cause you big problems. For some specific applications, minimizing latency is the holy grail of networking.

Latency and bandwidth aren’t directly related. You can have low speed connections with very minor latency. You can also have screaming Gbps connections with horrible latency. What drives latency is distance, network architecture, and equipment design.

Here’s an example of a network setup where you can’t do much about latency. Consider television remote broadcasts. These are the ones where a van with a satellite dish on top parks at the scene of a news event. It really doesn’t matter where in the world the van and the studio are located. The TV signal is going to have a considerable latency or time delay. You see the effect all the time. If the anchor and the field reporter don’t wait a second before they respond to the conversation, they’ll talk right over the top of each other.

Why is this? It’s because the signal is being sent from the truck dish to a satellite in geosynchronous orbit at 22,236 miles above the Earth (mean sea level) and back down to another dish at the studio or network headquarters. That means the electromagnetic waves have to travel a minimum of 44,472 miles up and then back down. In practice, the distance is longer because the signal isn’t going straight up and down. Now, consider that the speed of all signals in space is 186,000 miles per second and you have at least a quarter second delay one way or a half second round trip. Any equipment in the path or additional landline connections only makes it worse.

This is why satellite broadband works great for one way TV broadcasts but terrible for VoIP conversations. One way streaming is unaffected by latency. Two way anything is definitely affected. Data file transfers aren’t terribly bothered by going through a satellite because the latency is often small compared to the transfer time. But video conferences can be awkward and real time gaming is an exercise in frustration.

The point is that if you worry about latency, stay off geosynchronous satellite connections. Even your landline and undersea connections are affected to the tune of at least a millisecond per 186 miles simply due to the speed of light. Actually, you’d never even get that minimum latency value because light slows down in copper wires and fiber optic cores. The electronics that switch and route your path will also each add a small amount of latency to the total.

So, what differentiates a low latency connection from one that doesn’t concern itself much with latency? What you want is short paths between locations and a minimum of equipment in between. That suggests private networks, not the Internet. The Internet is designed for universal access and self-healing in the event of problems. Latency is an afterthought at best.

Many of today’s top MPLS networks are engineered to minimize latency. There are relatively few label switches to route the traffic and the networks have sufficient bandwidth to prevent congestion that backs up data flow and makes latency worse. You’ll want a network that has fiber runs as direct to your locations as possible to minimize path length. If MPLS will do the job, it has definite cost advantages and can give you mesh network connections so that all sites can easily communicate.

If latency is your number one priority, you’ll do even better with direct private line connections especially designed to minimize latency. These fiber paths are as close to a straight line as you can get and there is little in the way of electronics to slow things down. The one hitch is that these connections are primarily found between major international destinations, especially those like London, Frankfurt, New York and Chicago that are financial trading centers. High speed financial trading is the number one application driving the deployment of ultra low latency fiber optic services.

Do you have a business need for lower latency connections or even a critical need to minimize latency on long haul links? If so, get availability and pricing on Low Latency Fiber Optic Networks to check your domestic and international options.

Low Latency Fiber Routes To Europe and Asia

Many US companies have offices in the UK and Europe. Multinational companies have their operations located worldwide. So, how do you reliably interconnect all of your international business locations including connections to the cloud?

More and more, the answer is low latency fiber routes. Low latency is a term you hardly ever use to hear. It became part of the user vernacular with the switch from circuit switched phone service to VoIP. Before that, latency was a derogatory word used to describe the big delay experienced when communicating through geosynchronous satellite links. Now all the major carriers are touting their new low latency fiber routes to Europe or Asia.

So why the big change? Aren’t fiber routes inherently low latency?

Indeed, most fiber optic connections have latencies in the tens of milliseconds or less. That’s enough to ignore for most purposes. Notable exceptions are high speed financial trading, data replication and some cloud services.

Don’t confuse bandwidth and latency. Bandwidth, often referred to a line speed, is how fast you are sending out ones and zeros. This may be limited to the capability of the terminal equipment at either end or, more often, the capacity of the line. You can connect Gigabit Ethernet routers to each end of a T1 line but your packets will transfer no faster than 1.5 Mbps. That’s the T1 line speed.

Latency is a different animal. It describes the time it takes for those ones and zeros to get from one end of the line to the other. Often latency is quoted as the time in milliseconds for a round trip from source to destination and back to source.

Here’s how latency rears its ugly head. Say you are trying to carry on a conversation with someone using VoIP on a connection that has several hundred milliseconds of latency. That sounds like a lot, but it’s not uncommon on the Internet. The two way conversation quickly becomes like using a walkie-talkie. You talk one at a time and then pause for second before you speak when the other person is done. If not, you find yourself talking at the same time, but stepping on each other’s conversations.

More to the point of fiber optic latency, say you and someone else are trading stocks using automated programs. If your algorithms both decide there is a buy opportunity at the exact same moment, they’ll each place a buy order of a certain size based on the price action they are detecting. What happens if your order reaches the exchange 10 or 15 milliseconds after your competitor? It’s entirely possible that they’ll get a better price because the market moved between the trades.

This is what is getting “quant” traders exercised over latency and why there is a substantial market for the lowest latency connections possible. Carriers can reduce the latency of their fiber optic routes by taking the shortest path possible between two locations and minimizing the amount of equipment in that path. Every switch, router and multiplexer takes a small amount of time to do its job. Add them all up and you’ve increased latency.

Ultimately, the speed of light through the glass fiber is the limiting factor. That’s why shorter paths are lower latency. For the ultimate in latency reduction, you want to colocate in the same facility that houses the exchange computers or very near by. In high speed trading, even microseconds now count.

Latency was never that much of a problem when the bulk of traffic was one-way data file transfers. They get there when they get there and TCP/IP makes sure they arrive intact. It’s also no big deal for one-way audio and video streams or downloads. You just have a slight delay before the program starts. You probably won’t notice latency because there is a much larger delay built-in to buffer for jitter caused by congestion and packets taking different paths through the network. Two-way voice (VoIP) and video (teleconferencing and telepresence) are definitely affected by latency, although not to the same extent as financial trading and other very latency sensitive processes.

Does your company need higher performance network links to be more effective? You’ll do well to review the cost/benefit tradeoffs of low latency fiber optic networks, MPLS networks and other options available for your business locations.



Note: World map image courtesy of NOAA on Wikimedia Commons.

More Ultra Low Latency Bandwidth For Europe

If you’ve harbored any hope that the speed of business would slow down to a leisurely pace, consider one of the hottest new technology offerings. It’s the ultra low latency WAN network connection. If you are involved in the financial services industry, you need to keep a keen eye on what your competitors are implementing in the way of higher bandwidth/lower latency connections. If you are involved in any other business field, expect that latency will be important to your business sometime soon.

Level 3 Communications is a leader in the field of low latency transport services. Once of their niche services is fiber optic lines optimized to reduce latency between financial centers. They’ve just added London to Madrid and Frankfort to Madrid routes with circuit speeds up to 10 Gbps. These join the existing routes of Chicago to Washington DC, Chicago to New York, New York to London, and London to Frankfurt. The newly added European connections will improve latency on the Madrid to New York and Madrid to Chicago routes also.

Why is low latency such a hot topic as opposed to, say, bandwidth? Actually both latency and bandwidth are important characteristics of long haul fiber optic networks. What’s given latency the spotlight in recent years is the rise of high speed financial trading. This is a process where computers generate market trades far faster than humans are capable of. With thousands of trades executing in milliseconds, even very small moves in a market can result in huge profits or losses. If your trading platform is running even a fraction of a second behind your competitor’s, you could be on the losing end of those trades.

Latency can be minimized, but not eliminated. That’s because latency is nothing more than the length of time that elapses between when a signal is sent and when it is received. The fastest that an optical or electrical signal can propagate is set by the speed of light at 186,000 miles per second or 300,000 kilometers per second. If two locations are separated by 186 miles, you’ll never get below 1 millisecond of latency. A 1,860 mile route can do no better than 10 milliseconds. However, it can be much, much worse.

What sort of characteristics can slow down a speeding laser pulse? The mere fact that the data modulated light beam is traveling through a glass fiber rather than the vacuum of space will slow it down. According to Level 3, the propagation delay in optical networks is approximately 4.9 microseconds per kilometer. In free space the delay would be about 3.3 microseconds. That 4.9 microseconds can be degraded further by electronics that can’t keep up with the speed of the traffic. In other words, any bandwidth limitation will manifest itself as an additional delay as packets queue up in a buffer chip. Even with the fastest electronics, fiber routes must be as straight as possible. Any meandering through the countryside or to pick up other cities adds fiber length and, thus, latency.

Global trading has been increasing in volume at the rate of 30 to 50% annually. It is expected that automated trading will soon account for fully two-thirds of equity trades. Level 3 Communications has carved out a position as a key provider of high bandwidth ultra low latency connections to serve the financial industry. Unprotected Ethernet Private Line services are available at 100 Mbps. Unprotected Wavelength services are available at 1 GigE, 2.5 Gbps, 10 Gbps, 10 GigE and 40 Gbps. They can also provide customized global latency solutions for specific physical routing and diversity.

Are you in need of ultra low latency connections or merely low latency for time sensitive applications? If so, you should check out the availability and pricing of latency sensitive high bandwidth connections for your needs.



Note: Map of Spain graphic courtesy of Wikimedia Commons.

Low Latency Connections Bridge The Atlantic

Nothing says that we are part of a global marketplace like the terabytes of data that zip back and forth constantly through the world’s fiber optic trunk lines. Intercontinental cables have been in place for decades. But now there’s a new service gaining importance. It’s low latency networks.

What’s driving the demand for low latency right now is high speed financial trading. Increased use of automated trading programs has created a competition for getting trades placed first. First may mean milliseconds or even microseconds ahead of other traders. Certainly this is beyond the capability of the fastest human traders manually entering data. But it’s also so fast that path between traders and exchanges influences performance. The time delay in that path is called latency.

What’s needed for low latency connections is minimizing the distance between source and destination and minimizing the processing time of the electronics in the network. When microseconds make a difference, the speed of light comes into play. The fastest a signal can go is about 186 miles per millisecond. That’s the speed of light in a vacuum. In a physical wire or fiber optic strand, that speed is even less.

In the United States, low latency network services have taken two forms. One is a fiber optic cable running in as straight a line as possible between trading centers, say Chicago and New York. The amount of equipment on that line is minimized and engineered to pass signals as fast as possible.

Another approach is colocation. Companies move into a colocation facility, such as the ones offered by Telx, to be as close to the electronic trading floors as possible. It’s possible to save tens of milliseconds by just being physically next door.

Level 3 Communications has now established low latency connections that span the Atlantic from Europe to North America. They’ve also established direct connectivity with BATS Europe, a European Multilateral Trading Facility.

Financial services are a leading application driving the construction of low latency networks worldwide. There are other applications that are latency sensitive as well. It’s well known that VoIP telephony works best if latency is minimized. Long delays in voice packets cause “clipping” of conversations and may even result in dropped calls. Two-way video conferencing is also affected by high latencies. In fact, any interactive application requires some limitations on latency to function properly. As companies commit more of their business processes to cloud computing, latency issues that were once non-existant will become painfully apparent.

Has your company or organization developed a need for low latency communications linking locations in North or South America, Europe, Asia, Australia or Africa? Find out what services are available to meet your requirements for international high bandwidth low latency network connections. With multiple providers, prices are competitive.