The Internet of Things isn’t just enabling large scale monitoring and data collection – it’s also enabling intelligent, automated systems through Machine-to-Machine or M2M communication. In this article, we’re going to be discussing the use of time-sensitive networking for M2M communication in IoT; from what it is, the benefits it brings, all the way to hardware that can support TSN effectively.
Introduction to M2M Communication
M2M communication is a form of direct communication between electronic devices, and is often used to allow different, independent industrial systems to work more seamlessly with one another without human intervention. This allows for a variety of applications in which machines can leverage an increasingly prevalent IoT interconnectivity to work together in a more cohesive and effective manner.
For example, M2M communication is enabling industrial automation on a larger scale as previously separate systems can communicate with one another. In addition, it can help to improve industrial safety by employing failsafes and enforcing operating procedures.
Naturally, such new opportunities also come with their own set of challenges. For effective M2M communication to occur, one important factor to consider is none other than timing. When should devices expect incoming communications? How much time should subsequent devices in a communication chain have to process data? How do we ensure that devices receive communications on time?
Apart from timely communications, IoT networks must also have the flexibility and scalability to support communications between small devices and large servers as they increase in scale. Fortunately, this is precisely where Time Sensitive Networking comes in.
What is Time-Sensitive Networking?
Time-Sensitive Networking (TSN), is a set of IEEE 802 standards for Ethernet that aims to make it deterministic by design. This enables it to support time-sensitive applications with features like precision time synchronisation, data delivery timelines and traffic scheduling.
What does it mean to be deterministic? Well, in networking, determinism refers to when data exchange in communications occurs with a defined latency. Although Ethernet has made rapid advances over the years to deliver faster speeds and greater bandwidth, it works on the “best effort” principle, which means that unforeseen circumstances could cause momentary spikes in latency that are detrimental to industrial applications, such as control systems that require high levels of precision and coordination.
TSN operates on Layer 2 of the OSI Model, and adds specifications to enforce determinism in Ethernet communications. While additional standards may be added or adapted over time, some present Ethernet TSN standards include:
- IEEE 802.1AS – Generalized Precision Time Protocol
- IEEE 802.1Qbv – Time-aware Shaper
- IEEE 802.1Qav – Credit-based Shaper
- IEEE 802.1Qbu – Frame Preemption
Benefits of Time-Sensitive Networking
TSN was originally developed to improve the reliability of and reduce latencies in Ethernet communication through time-bounded latency. However, TSN also aims to solve other problems by including several key benefits, such as:
- Secure and Reliable Delivery of Data – Precise timing and communication distributed across various computing components
- Converged Networks – Coordinated network traffic across infrastructures save Operating Costs
- Simplified System Configuration and Operation – Conveniently deploy devices through software-defined networking (SDN)
- Open Ecosystem – Transparent & accessible development with interoperability among different hardware and devices
- Future Proof – Adaptable over time with support for up to 400Gbps
Thus, employing TSN helps you not only achieve reliable, low-latency M2M communications in industrial systems, but also standardise communication interfaces for efficient development and future scalability. This creates a reliable backbone on which you can confidently build your IoT applications, including for operation-critical scenarios in industries!
What Applications Benefit from TSN?
Here are some applications that stand to benefit from time sensitive networking.
Especially in IoT, many measurement applications combine sensor readings from multiple inputs or even devices. For accurate analysis, it is important that each of these sensor readings are taken at the same point in time, which introduces time sensitivity to this application. For example, testing the structural integrity of a building may require multiple readings from strain gauges that are distributed around the subject. In the same manner, metrics of machine health such as flows or vibrations have to be time synchronised from different sensors in order to allow for accurate analysis and in turn effective preventative or predictive maintenance.
Industrial control systems are required to process information from sensors or human inputs in real time in order to produce a response – the lower the latency, the more effective the resulting action will be. In particular, it is important to have controlled and thus predictable network delays in order to achieve low-jitter inputs and outputs to achieve an effective control system.
Though we do not see it, our vehicles are equipped with interconnected components to offer important functions such as heads up displays, assistive braking and even autonomous driving. To provide accurate real-time information to drivers and to respond effectively to dynamic road conditions, many manufacturers use TSN Ethernet to ensure timely delivery of data packets between vehicle components.
While not targeted at IoT, media networking, namely streaming services, require strict timing to deliver content smoothly while avoiding losses or artifacting in video or audio. Some other media applications utilise predictable latencies to present audio with predefined phase differences, so as to reduce interference between multiple outputs.
Supplement TSN with Intel Time Coordinated Computing
Intel’s Intel Time Coordinated Computing (Intel TCC) is designed as an integrated solution for time sensitive, highly coordinated applications. Intel TCC-enabled hardware provides features like time synchronisation across hardware clocks and timely internal data packet delivery, and are also compatible with Ethernet controllers operating on TSN standards for cross-system communications.
With Intel Time Synchronization, you can eliminate the need for software-based synchronisation and OS-associated adverse effects. You can also easily coordinate the clocks found in various components of the same system, including the CPU, PCIe, network, audio, etc.
With Intel Timeliness, you can ensure timely delivery of data packets from one component to another within the same system. This can be done by allocating critical resources (eg. CPU cache) for real-time applications, or prioritising I/O such as PCIe traffic.
To summarise, the benefits of Intel Time Coordinated Computing includes:
- Enabling reliable worst-case execution time (WCET) I/O within the compute node.
- Accelerating time to market and reducing total cost of ownership with simple tuning.
- Convenient scaling from Intel Atom® x6000E Series processors and 11th Gen Intel® Core™ processors to next gen with Intel® TCC.
- Maximising efficiency by aggregating time-critical and non-time-constrained applications onto consolidated hardware.
Apart from improved manageability of latencies in real time computing, Intel’s suite of Real-Time products also offers computing platforms that are optimised for real time, low-latency computing, including versions of the latest 11th Gen Tiger Lake UP3 processors that come hardware-ready for time-sensitive applications and integrated TSN-ready Ethernet port(s).
You can also take advantage of software tools like Intel Edge Controls, which can help transform industrial control systems by integrating real-time compute, standards-based connectivity, safety, virtualisation and IT management tools.
Intel is also releasing their Intel Time Coordinated Computing Tools (Intel TCC Tools) platform, which contains APIs, utilities, sample applications, documentations and more to help users make the most of Intel processors’ real-time capabilities. It also includes real-time configuration and optimisations for processor tuning, as well as troubleshooting and debugging tools to make development easier!
Looking for a powerful yet robust and reliable edge solution for time sensitive applications? The reServer is a compact and powerful server that can be used in both edge and cloud computing scenarios. High-performing versions are powered by the latest Intel Core vPro 11th Gen i5 and i7 processors, which are optimised for real-time computing through integration with Intel Time Coordinated Computing. This means that it can be readily used for low-latency industrial-grade applications, with all the benefits that we’ve discussed in this article!
Not only that, reServer comes with diverse network connectivity capabilities, including two high-speed 2.5-Gigabit Ethernet ports and hybrid connectivity with 5G LoRaWAN, BLE and WiFi – as well as integrated cooling and dual SATA III connectors for internally mounting 3.5” SATA hard disk drives. It truly is a complete solution for powerful edge computing applications.
- CPU: Latest 11th Gen Intel® Core™ i3 CPU running up to 4.10GHz (Base)
- Graphics: Intel UHD Graphics Xe G4 48EUs running up to 1.25 GHz
- Rich Peripherals: Dual 2.5-Gigabit Ethernet, USB 3.0 Type-A, USB 2.0 Type-A, HDMI and DP output
- Hybrid connectivity including 5G, LoRa, BLE and WiFi (Additional Modules required for 5G and LoRa)
- Dual SATA III 6.0 Gbps data connectors for 3.5” SATA hard disk drives with sufficient internal enclosure storage space
- M.2 B-Key/ M-Key/ E-Key for expandability with SSDs or 4G and 5G modules
- Compact server design, with an overall dimension of 124mm*132mm*233mm
- Quiet cooling fan with a large VC heat sink for excellent heat dissipation
- Easy to install, upgrade and maintain with ease of access to the internal components
Learn more about reServer on the Seeed Online Store!
We kicked off this article by discussing M2M communication in IoT, followed by the challenges of unbounded latencies in data exchanges. As a result, TSN Ethernet is quickly becoming an industrial standard, offering not only time-bounded low-latency, but also an open standard on which to develop networks in industrial solutions. Coupled with Intel TCC-enabled hardware, we now have a comprehensive solution that both addresses challenges in real time computing and maintains scalability for future developments!
If you’re keen to learn more about TSN, Intel TCC and various edge computing solutions, be sure to check out the following resources!
- Real-Time Computing IoT Technology Resources – Intel
- Tiger Lake UP3 Processors – Intel
- OpenVINO for Intel 11th Gen Tiger Lake Processors
- A Look at the Intel vPro Platform for Edge Computing
- What is an Edge Server? – Edge Computing Embedded Systems