The Internet of Things in recent years has aroused considerable interest in the topic of edge computing.
The fact is, edge computing has high hopes of unlocking the potential of the ever-growing volume of data produced by IoT devices. By 2025, this volume is expected to reach a staggering 73.1 ZB, but to extract value from it, data streams need to be competently allocated, managed and analyzed. Edge devices might be useful here.
Statistics show that edge computing is already used in most IoT applications in one way or another. Going beyond routers and firewalls, edge computing allows you to perform intelligent automation and predictive maintenance, optimize the data lifecycle and, therefore, reduce costs. While the intelligent edge is a new application, you can already take a closer look at how it has manifested itself within industrial, transportation, healthcare, and other common enterprise IoT solutions to get the most out of it. In this article, PSA discovers which environments require edge computing, which IoT + edge tandem cases are most promising, and how to competently distribute workloads across the IoT ecosystem.
The place of edge devices within enterprise IoT solutions
The traditional architecture of Enterprise IoT solutions assumes that data is collected from things, such as products on a conveyor belt or equipment in a shop floor; then it is transferred to the cloud for further processing and analysis. In such a system, edge devices are traditionally used to distribute data over the network and control network traffic. Routers, firewalls, multiplexers and switches are among the devices where the latter allows the company to connect to the industrial devices. In general, they enable IoT to be established enterprise-wide, regardless of its location.
For IoT automation solutions, ideas generated by AI in the cloud are sent back to the field to prompt action. Certainly, this approach suffers from a lack of speed and throughput, which becomes critical with a widely distributed architecture and large amounts of data that need to be processed. This is where intelligent edge devices come into play, all about processing, analytics and action. Their advantage is revealed through their proximity to the data source which allows them to reduce latency by delegating some basic decision credentials to them.
- End Devices. Smart sensors and actuators, wearables, cameras, and other sensing-enabled devices are located as close to things as possible. Their computing capabilities are limited by their compact size.
- IoT gatewaysallow only potentially valuable information to reach the cloud. This is a bridge between things and the cloud: do the aggregation, preprocess, filter the data, verify its authenticity and clean the raw data. They also provide field device management, ensuring automated distributed architectures.
- Edge serversis a generic name for environments where extensive processing is taking place at the edge. A physical server, laptop, embedded system, or system-on-chip can perform this function. This category has attracted particular attention in recent times as it allows the redistribution of computational loads throughout the system and the introduction of Artificial Intelligence (AI).
Therefore, when placing certain loads on the edge, the system saves time on communicating with the cloud, which allows for a quick response to the situation in the field. Additionally, increased availability and reliability are provided, as well as security as data does not go beyond local storage. To make this setup cost-effective, it’s crucial that you don’t overload the cloud.
The most promising edge computing applications for enterprise IoT solutions
Hybrid Cloud + Edge
Since the core value of a hybrid cloud lies in the opportunity to move workloads between various environments, extending that infrastructure to edge solutions seems as natural as possible. By connecting edge devices, more options appear for how to optimize workloads. This allows for cost-effective scalability and increased resilience in the event of system failure. In hybrid environments, the edge component provides additional flexibility to the entire system, while the cloud component increases consistency across distributed resources.
When it comes to excessive amounts of data circulating in the IoT ecosystem, get more value by putting real-time computing at the edge, leaving the deep analytics of cloud computing behind. At the same time, the cloud can be used as a management center providing transparency for the entire system. Since you won’t be calling a specialist for each node if something goes wrong, the Hybrid Cloud + Edge tandem allows you to increase controllability. Open source projects like Micro Shift help extend mission-critical platforms like Kubernetes to the edge and keep them consistent.
Edge Computing + AI/ML
Bringing AI to the edge is gaining popularity as Edge can exceed the speed limits imposed on the cloud. Sometimes it is the only way to implement the AI-enabled IoT ecosystem, as an internet connection may not be available or in case of increased data security. In any case, it expands the possibilities of processing raw data in the field, indispensable for time-critical automation solutions and for highly distributed systems. Including the Cloud in this chain becomes not only time-consuming, but expensive, as it requires significant resources in the form of Internet channel bandwidth, traffic, additional energy, etc. For example, processing information from sensors at an oil refinery generates more than 1TB of raw data per day, requiring excessive resources to process.
AI algorithms applied to edge devices bring new use cases, such as remote monitoring, predictive maintenance and advanced automation. Computer vision implemented at the edge also continues to gain momentum. Either way, implementing AI in the IoT ecosystem requires cooperation between the cloud and the edge. AI training still takes place in the cloud, as this requires too much computing power, while deployment is set at the edge. The growing success of this model allows us to talk about AIoT (Artificial Internet of Things).
Edge Computing + 5G
The combination of edge and 5G promises to enhance the core benefit of edge computing that performs operations as close to real time as possible. So far we can’t talk about the desired 1 millisecond response, but 5G is already 16 times faster than LTE1. This speed makes it easy to deploy various applications in the cloud, such as real-time monitoring of robots, control of drones, automated vehicles, and even MRP services and remote surgeries. The maximum data transfer rate of 20 Gbps allows you to create augmented reality applications and work with data-heavy, such as 4K video.
In general, 5G allows the enterprise to deploy lower power edge devices while providing higher processing capabilities. The bandwidth of such a network allows you to connect up to 100 times more devices than with 4G or LTE technologies! Such capabilities pave the way for the most incredible applications of the Internet of Things, such as dark factories.
Energy harvesting on edge computing
As Enterprise IoT solutions expand, the question of device power arises, as sensors and other edge devices can operate outside the coverage area of wireless or mesh networks to cover the entire monitored surface. Fortunately, energy harvesting technologies are advancing, offering different energy harvesting technologies for different IoT applications, which will significantly extend the battery life of low-power devices. For example, energy harvesting systems based on solar or vibration energy are applied for the integrated devices in cars for self-infrastructure communications, while the energy harvesting sources of light or heat energy sensors are successfully used for the workplace automation. Among the latest developments, we can distinguish an autonomous NB-IoT module that uses the energy of ambient light. The solution is based on solar cells and PMICs with MPPT function.
Recommendations for introducing edge computing into enterprise IoT solutions
– The edge infrastructure is already mature enough to build complex IoT applications with a balanced distribution of computing power between the cloud and the edge.
– Extending cloud infrastructures to the edge makes sense for real-time operations as it minimizes latency. Cloud servers in such an infrastructure increase transparency and increase control over resources.
– When creating Enterprise IoT solutions, it is important to foresee the edge components from the beginning, in order to then be able to increase their benefits, also with the help of AI.
– Training models require heavy-duty hardware, so it’s best to train AI in the cloud and deploy the finished model at the edge.
– Expanding IoT infrastructure requires optimizing edge resources. The introduction of energy harvesting technologies could be beneficial in this case.
About the author
Julia Mitchell is responsible for business operations at Professional Software Associates, Inc.. Julia is eager to solve customers’ business challenges in building full-fledged IoT ecosystems. With over 8 years of experience in the EIoT development industry, she is involved in projects for the automotive, energy, logistics and other industries.
Featured image: iaremenko
#Leverage #Edge #Computing #Enterprise #IoT #Solutions #TechNative
Image Source : technative.io