Network carriers are continually dealing with the challenges of bandwidth. Because of COVID-19, network traffic increased at an astounding rate in 2020—and it is expected to continue. For example, AT&T reports that it expects its network traffic to increase five-fold in the next five years, with customers devouring an average of 4.5TB (Terabyte) of data per person.
This exponential traffic growth is driven by more and more video streaming, cloud computing, data centers, artificial intelligence (AI), machine learning (ML), the ever-increasing amount of IoT devices, etc.
This is where 400G fits into the equation.
What is 400G Ethernet?
400G (400 Gigabit Ethernet) is the latest generation of cloud infrastructure and is four times faster than the previous standard of 100G. Also called 400 Gigabit, 400GbE, 400Gb/s, and Terabit Ethernet, this technology is defined as follows:
Terabit Ethernet is Ethernet transmission at one trillion bits per second (1 Tbps). True Terabit Ethernet is a future technology; however, in the meantime, Terabit Ethernet generally refers to Ethernet above 100 Gpbs. The IEEE 802.3bs task force has defined 200 Gigabit (200BASE) and 400 Gigabit Ethernet (400BASE), which are expected to be commonly deployed by carriers and large enterprises by 2020.
The Evolution of Ethernet Standards
The pace of Ethernet development has increased steadily over the past 24 years. Following is a list of the milestones of this technology:
- 1 Gigabit Ethernet (1G) is ratified by the Institute of Electrical and Electronics Engineers (IEEE) in 1997.
- 10 Gigabit Ethernet (10G) is introduced in 2004.
- By 2010, 100 Gigabit Ethernet (100G) becomes the standard.
- The current 802.3bs standard of 200/400 Gigabit (200G/400G) was ratified by the IEEE on December 6, 2017.Image source: ethernetalliance.org
The Objectives of the 400G Solution
In an IEEE report entitled IEEE 802.3 Industry Connections Ethernet Bandwidth Assessment Part II, they state there is a “bandwidth explosion,” and they forecast that “device connections will grow from 18 billion [in 2017] to 28.5 billion devices [by 2022].” And the number of internet users will soar “from 3.4 billion in 2017 to 4.8 billion in 2022.”
In an earlier report dated November 2013, the IEEE 400 Gb/s Ethernet Study Group laid out their objectives for this latest standard, which are as follows:
- Support a MAC data rate of 400 Gb/s
- Support full-duplex operation only
- Preserve the Ethernet frame utilizing the Ethernet MAC
- Preserve minimum and maximum FramSize of current Ethernet standard
- Provide appropriate support for OTN
- Speedy optional Energy Efficient Ethernet (EEE) capability for 400Gb/s PHYs
- Support optional 400Gb/s Attachment Unit Interfaces for chip-to-chip and chip-to-module applications
How 400G Works
First of all, the actual line rate of a 400G Ethernet link is actually 425 Gbps. The IEEE 802.3bs standard is designed to be 400G; however, it also establishes a forward error connection (FEC) procedure that detects and corrects transmission errors; the additional 25 bits are for this FEC mechanism.
But what makes 400G transmission possible?
Exfo, a company that designs and manufactures test instruments and service assurance for telecommunications networks, provides this brief technical deep dive:
It’s the adoption of 4-level pulse amplitude modulation (PAM4). Using PAM4, operators implement 8 lanes of 50G or 4 lanes of 100G for different form factors (i.e., OSFP and QSFP-DD). This novel optical transceiver architecture supports transmission of up to 400 Gbit/s Ethernet data over either multiwavelength or parallel fibers.
However, multilevel modulation creates higher analysis complexity, so we need advanced tools such as PAM4 eye diagram histograms and pre-emphasis and equalization capabilities to manage this complexity.
The chart below details the distance, fiber mode, designation, and number of fibers specifications for both 200G and 400G.
The Benefits of 400G
The 400G solution has a lot going for it. 400 Gigabit Ethernet:
- Is perfect for high-traffic volume telecommunications service providers (TSPs), large data centers, and other enterprises experiencing relentless traffic growth.
- Delivers the power, efficiency, and density required for cutting-edge technologies such as 5G, augmented reality (AR), virtual reality (VR), and 4K video streaming.
- Not only supplies data transfer speeds that are four times faster than 100G, it provides greater efficiency because its larger pipes are easier to manage and they transmit bits at a lower power percentage.
- Costs less: A single 400G port on a router is cheaper than four individual 100G ports.
- Consumes less power: A single 400G port uses less power than four individual 100G ports.
- Speeds support scale-up and scale-out architectures by providing low cost-per-bit, high density, and reliable throughput.
So, where does the technology stand now?
400G optical transceivers are one of the hottest networking trends for 2021. According to a report by Orbis Research, the optical transceiver market will reach $22.6 billion by 2023. Things like global internet adoption, social networking, online commerce, streaming video, cloud services, and software as a service (SaaS) will all play into this trend, as will the availability and cost-effectiveness of 100G and 400G devices.
Although we are still in the first stages of deploying the 400G standard, the need for more bandwidth is on such a rise that experts feel 800G and 1600G are not too far in our future.
2021 is the cloud era. Our network infrastructures need to be:
400G solutions are designed to help us meet these goals—and they do it fast!
Versa Technologies is a US-based provider of last-mile IT networking technology and one of the largest suppliers of Power over Ethernet (PoE) switch technology globally. Visit our PoE page to find out more about our IT networking solutions.