Written by Simon Kenny, Head of Strategy in Hoptroph
Digital transformation and automation are changing the way all industries operate, but with recent large increases in microchip computing power, falling chip manufacturing costs, and the rapid acceleration of artificial intelligence, machine learning (ML), and cloud-based IoT applications, the pace of change is set to accelerate.
Over the next few years, we will see the decentralization of data processing from cloud centers to a few edge computing centers. From there, AI and machine learning applications can interact with customers independently, transferring only small amounts of data to a central cloud so that the explosion of new data coming from Internet of Things (IoT) devices on 5G networks does not cause congestion. telecommunications and storage capacity. In the future of smart cities, communities can improve energy distribution, optimize garbage collection, reduce road congestion and improve air quality with IoT.
Every location, mobile device, and IoT device must have the same accurate time as the data centers they serve if data quality and AI and ML efficiency are to be optimized for various industries at the edge. If they don’t, the time sequences in the data records will be inconsistent and unreliable for applications to use. To prevent this, you need standardized timelines, but the standards required and the benefits to be gained will vary from industry to industry. Take, for example, IoT, 5G, autonomous cars, the metaverse and the intelligent network of connected objects and machines. Each of these industries will make major contributions to an automated smart city, but their time synchronization needs will be different.
Accurate and precise time synchronization in 5G networks
5G telecommunications need a level of accuracy of 1 µs (one microsecond) that will be maintained throughout the network to manage bandwidth and ensure that different data streams in the network remain separate from each other. It is not a choice; this is a technical necessity to ensure the efficient operation of the network. Without it, calls will be lost and data streams will fail. To achieve this very high standard, the network requires synchronization of GPS and local clocks, which must be deployed and maintained throughout the network.
5G and IoT networks are critical to realizing the smart city vision. They provide reliable and cyber-secure hardware and connectivity to keep these systems of connected objects and machines functioning. The advantage for 5G and its customers of investing in the infrastructure to support such a strict standard is that 5G can handle a very wide range of bandwidth, providing high reliability, low latency and the ability to support new areas such as industrial automation. This is something that 4G could not serve in the past. For businesses and consumers to reap the benefits of 5G, and for smart city operators to get the most out of 5G networks, the investment in accurate and precise time synchronization and the associated ROI are undeniable.
Getting the most out of IoT device data
In IoT, the importance of accurate time is not so accepted. If connected traffic lights, autonomous cars, and smart buildings don’t all use the same time or can’t prove their time is correct, that doesn’t stop them from performing their functions. However, this reduces the quality and usefulness of the data they provide about their own functions and how their data can integrate with data from other devices.
If you needed to prove a sequence of events from IoT data records of various devices, such as a door being opened at a specific time using an ID card, then that the same person was captured on a remote CCTV camera, and then later when a smart camera If a traffic officer has caught the same person speeding in a different location, you will need all devices to have the same time.
If they don’t, the timestamps can tell you that the person driving the car couldn’t have opened the door because the timestamp on the traffic camera shows they were miles away from you at the same time. The difference between the hours undermines your ability to prove the sequence of events. However, if all devices are combined into a common time verified by a primary time source, you can use all your IoT data as a reference point without the need for additional verification.
Accurate time may not be necessary for all IoT functions, but it is important if you want to take full advantage of the data that IoT generates. The 10 millisecond standard covers the functionality of most IoT devices, but you need a regular comparison system with a reliable time source so you can verify that the time is correct and keep records to prove it later if necessary.
The growth of a smart city requires precise and accurate time synchronization
Smart cities need accurate time because it is essential to their operations and because they need to be able to track and report events.
In order for autonomous vehicles, including automated, unmanned and robocars, to operate safely in a smart city, precision timing as high as that of telecommunications at one microsecond is essential. The internal components of autonomous cars must use the same timing, autonomous cars must be synchronized with connected sensors in the external environment, and they must be synchronized with other autonomous cars, smart street lights and connected traffic cameras.
The The Law Commissions of England and Wales and Scotland recently recommended that manufacturers should be held responsible for accidents that occur when self-driving capabilities are under control. If this recommendation becomes law, it is vital that autonomous vehicles keep verifiable time-stamped records of their automated actions so that in the event of an accident, insurers can assess what happened and assign liability accordingly.
Accurate and precise time synchronization is a necessity for increased automation
As automation takes on more responsibility for direct interaction with the public, whether as a 5G, smart IoT device, or as a component of a smart city such as an autonomous vehicle, smart street lights or connected traffic cameras, it will also need to accept more accountability. Some automated functions may not need accurate time to continue to operate effectively, but all automations need accurate time to ensure they have data records of sufficient quality to explain/justify the machine’s actions after an event.
Accuracy and reporting standards don’t have to be the same for all businesses, online delivery times will meet many needs, but industries that want to get the most out of automation and build maximum trust with their customers will embrace intelligent and accurate enterprise-wide time synchronization without the need for input any regulator. A reasonable time would simply be good business practice.