Why is edge computing important?
Computing tasks require a suitable architecture, and an architecture suitable for one type of computing task may not be suitable for all types of computing tasks. Edge computing has become a viable and important architecture that supports distributed computing to deploy computing and storage resources closer to the data source , preferably in the same physical location as the data source. In summary, the distributed computing model is not new; the concept of remote offices, branch offices, data center co-location and cloud computing has a long and proven track record.
But decentralization can be challenging, requiring high levels of monitoring and control that can easily be overlooked when moving away from traditional centralized computing models. Edge computing becomes relevant because it provides effective solutions to emerging networking problems associated with the vast amounts of data generated and consumed by today's organizations . It's not just a matter of quantity, it's also a matter of timing; applications rely on increasingly time-sensitive processing and responses.
But decentralization can be challenging, requiring high levels of monitoring and control that can easily be overlooked when moving away from traditional centralized computing models. Edge computing becomes relevant because it provides effective solutions to emerging networking problems associated with the vast amounts of data generated and consumed by today's organizations . It's not just a matter of quantity, it's also a matter of timing; applications rely on increasingly time-sensitive processing and responses.
Consider the rise of self-driving cars. They will rely on smart traffic control signals. Automotive and traffic control require instantaneous generation, analysis and exchange of data. Multiply this demand by a large number of autonomous vehicles, and the scope of the potential problems becomes clearer. This requires a fast and responsive network. Edge and fog computing address three major network limitations: bandwidth, latency, and congestion or reliability .
- Bandwidth . Bandwidth is the amount of data a network can transmit over time, usually expressed in bits per second. All networks have limited bandwidth, and wireless communications have even tighter restrictions. This means there is a limit to the amount of data or devices that can be communicated over the network. While network bandwidth can be increased to accommodate more devices and data, the cost can be high, there are still (higher) finite limits, and it doesn't solve other problems.
- Delay . Latency is the time it takes to transmit data between two points on the network. While communications ideally occur at the speed of light, large physical distances coupled with network congestion or outages can delay the movement of data over the network. This delays any analysis and decision-making processes and reduces the system's ability to respond immediately. In the case of self-driving cars, it can even cost lives.
- Clogged . The Internet is basically a global "network of networks." Although it has evolved to provide a good general-purpose data exchange for most everyday computing tasks (such as file exchange or elementary streaming), the amount of data involved in tens of billions of devices could overwhelm the Internet, causing high levels of congestion and Forces time-consuming retransmission of data. In other cases, network outages can increase congestion or even completely cut off communication with some Internet users - rendering the Internet of Things useless during the outage.
By deploying data-generating servers and storage, edge computing can operate many devices on smaller, more efficient LANs, where sufficient bandwidth is used only by local data-generating devices, making latency and congestion virtually impossible. does not exist. Local storage collects and protects the raw data, while local servers can perform the necessary edge analysis —or at least preprocess and reduce the data—to make decisions on the fly before sending the results or just the basic data to the cloud or a central data center.
Edge Budget Application Cases
In principle, edge computing technology is used to collect, filter, process and analyze data "in place" at or near the edge of the network. This is a powerful means of using material that cannot first be moved to a centralized location—usually because the volume of the material would make such movement costly, technically impractical, or might breach compliance obligations such as data sovereignty. This definition has spawned countless real-world examples and use cases :
- Manufacture . An industrial manufacturer deployed edge computing to monitor manufacturing, enabling real-time analytics and machine learning at the edge to detect production errors and improve product manufacturing quality. Edge computing enables the addition of environmental sensors throughout manufacturing plants, providing insights into how each product component is assembled and stored—and how long it has been in stock. Manufacturers can now make faster, more accurate business decisions about their factory facilities and manufacturing operations.
- Farming . Consider a business that grows crops indoors without sunlight, soil, or pesticides. This process reduces growth time by more than 60%. Using sensors allows companies to track water usage, nutrient density, and determine optimal harvests. Collect and analyze data to discover the impact of environmental factors, continuously improve crop growth algorithms, and ensure crops are harvested at their peak.
- Network optimization . Edge computing can help optimize network performance by measuring the performance of users on the Internet and then using analytics to determine the most reliable, low-latency network path for each user's traffic. In effect, edge computing is used to "direct" traffic throughout the network for optimal performance for time-sensitive traffic.
- Workplace safety . Edge computing can combine and analyze data from on-site cameras, employee safety devices, and a variety of other sensors to help companies monitor workplace conditions or ensure employees are following established safety protocols—especially when the workplace is remote or unusually dangerous. , such as a construction site or an oil rig.
- Improve health care . The healthcare industry has dramatically increased the amount of patient data collected from devices, sensors and other medical devices. Such huge amounts of data require edge computing to apply automation and machine learning to access the data, ignore "normal" data and identify problem data so that clinicians can take immediate action to help patients avoid health incidents in real time.
- Transportation . Autonomous vehicles require and produce 5 terabytes to 20 terabytes per day, collecting information about location, speed, vehicle condition, road conditions, traffic conditions and other vehicles. While the vehicle is driving, data must be aggregated and analyzed in real time. This requires a lot of on-board computing - every self-driving car becomes an "edge". Furthermore, this information can help authorities and companies manage their fleets based on actual conditions on the ground.
- Retail . Retail businesses can also generate vast amounts of data from monitoring, inventory tracking, sales data and other real-time business details. Edge computing can help analyze this diverse data and identify business opportunities, such as effective end caps or campaigns, forecast sales and optimize supplier ordering. Since retail operations can vary greatly in local environments, edge computing can be an effective solution for local processing in each store.
What are the benefits of edge computing?
Edge computing solves important infrastructure challenges—such as bandwidth constraints, excess latency, and network congestion—but edge computing has several potential additional benefits that could make the approach attractive in other contexts.
Autonomy . Edge computing is useful when connections are unreliable or bandwidth is limited due to site environmental characteristics . Examples include oil rigs, offshore vessels, remote farms, or other remote locations such as rainforests or deserts. Edge computing performs computational work on-site (sometimes on the edge device itself) , such as water quality sensors on water purifiers in remote villages, and stores data for transmission to a central point only when a connection is available. By processing data locally, the amount of data sent can be significantly reduced, requiring far less bandwidth or connection time than would otherwise be required.
Autonomy . Edge computing is useful when connections are unreliable or bandwidth is limited due to site environmental characteristics . Examples include oil rigs, offshore vessels, remote farms, or other remote locations such as rainforests or deserts. Edge computing performs computational work on-site (sometimes on the edge device itself) , such as water quality sensors on water purifiers in remote villages, and stores data for transmission to a central point only when a connection is available. By processing data locally, the amount of data sent can be significantly reduced, requiring far less bandwidth or connection time than would otherwise be required.
Data Sovereignty . Moving large amounts of data is not just a technical issue. The journey of data across national and regional borders may create additional issues regarding data security, privacy and other legal issues. Edge computing can be used to bring data close to its source and within the scope of current data sovereignty laws, such as the EU’s GDPR, which defines how data is stored, processed and exposed. This can allow raw material to be processed locally, masking or protecting any sensitive material before sending anything to the cloud or master data centers in other jurisdictions.
Edge safety . Finally, edge computing provides additional opportunities to implement and ensure data security . While cloud providers have IoT services and specialize in sophisticated analytics, enterprises are still concerned about the security of data after it leaves the edge and returns to the cloud, or data center. By implementing computing at the edge, any data that travels across the network back to the cloud or data center can be protected through encryption. The edge deployment itself can strengthen attacks against hackers and other malicious activities - even on IoT devices. The security is still limited.
Edge safety . Finally, edge computing provides additional opportunities to implement and ensure data security . While cloud providers have IoT services and specialize in sophisticated analytics, enterprises are still concerned about the security of data after it leaves the edge and returns to the cloud, or data center. By implementing computing at the edge, any data that travels across the network back to the cloud or data center can be protected through encryption. The edge deployment itself can strengthen attacks against hackers and other malicious activities - even on IoT devices. The security is still limited.