Personal tools

5G Edge Computing Infrastructure

Houston_Texas_061222A
[Houston, Texas]

 

- Overview

Edge computing is a technology that combines 5G networks with data storage and processing closer to the source. Edge infrastructure is made up of small data center sites that are close to the communities they serve. 5G increases the speed of data transfer, while edge computing reduces the amount of traffic between the data center and the cloud.

When combined, 5G and edge computing can: 

  • Improve performance
  • Support data security
  • Enable continuous operations in every industry
  • Enhance digital experiences
  • Reduce energy consumption
  • Improve public safety
  • Help optimize traffic flow


5G's low latency and high bandwidth capabilities can help reduce the time it takes for edge servers and IoT devices to communicate with each other. This allows for real-time data processing at the edge. 

Edge computers typically support both wired and wireless connectivity. This allows computers to connect to the internet to transmit data if connecting wirelessly is not an option at a remote commercial site. 

By delegating greater autonomy and decision-making power to the middle layer, edge computing reduces the response time of mission-critical applications, allowing them to operate in real time. The cloud is used as the storage unit for data storage, and data processing is performed on peripheral nodes as much as possible, which also improves data security and sensitivity.

Edge computing technology allows you to significantly expand the range of possible applications and services thanks to the ability to support AI locally rather than relying on AI in the cloud. 

This approach is particularly suitable for applications such as Industry 4.0, smart manufacturing, 5G, Internet of Things, autonomous vehicles, smart cities, smart hospitals, robotics, machine vision, etc.

 

- Edge Computing and Micro-Data Centers (EMDCs)

Edge computing and micro-data centers (EMDCs) are two separate concepts that can co-exist in deployed areas: 

  • Edge computing: A distributed architecture that moves data processing closer to where it's generated, such as the edge of a network. This means that businesses don't have to rely as much on centralized data centers.
  • EMDCs: A data center design that implements edge computing for organizations. EMDCs are small-footprint data centers that can be as small as one traditional server rack or cabinet. They can be deployed at the edge of a network and are often used for edge computing applications.


EMDCs are scalable, compact systems that can support embedded applications with a high degree of autonomy and decision-making capacity. They can reduce costs and deployment times while increasing resilience and scalability.

 

- Distributed Grid of Micro-Data Centers (EMDCs)

Edge computing requires compact and power-efficient solutions that can operate even in harsh, space-constrained environments, placing computing power as close as possible to sensors and other data sources. From a hardware perspective, an efficient power supply system with high power density and small size is required.

Since human contact with edge devices and sensors is ubiquitous, it is necessary to implement the supporting edge infrastructure as a distributed grid of edge micro-data centers (EMDCs) and edge servers, even in the most remote and challenging locations. The same is true for environmental conditions and confined spaces. 

This brings computer resources as close as possible to data producers and users, resulting in very compact form factors and previously unheard of high power densities, posing new technical challenges for energy efficiency, electrical signal integrity and high reliability.


- A Micro-Data Centers (EMDCs) Example

Hardware design and technology selection targeted three areas of EMDC: thermal management, small form factor, and power conversion.

EMDC hardware's solution is a scalable and compact edge computing system that can operate even in a closed environment or even outdoors. EMDC can be configured with any type and number of custom combinations of CPU, GPU, FPGA and NVMe (Non-Volatile Memory Express) media in a compact package. 

EDMC hardware includes a dual switch fabric (PCIe and Ethernet), creating high bandwidth and configuration flexibility. The switch fabric also supports the creation of large clusters of FPGAs, GPUs, and NVMes connected to a single CPU. Made entirely of solid-state components, these platforms require little maintenance and require no active cooling systems.


- 5G Edge Computing Infrastructure

Edge computing is a network architecture model that brings technology resources, including computing and related infrastructure, closer to end users or where data is generated. Instead of housing these critical resources in big data centers that may be hundreds or even thousands of miles from where the data is ultimately delivered, this new architecture moves it closer to the end user, right at the edge of the data center. network.

It is a distributed cloud computing extension of cellular and non-cellular networks, where data is processed and stored at the edge, and only critical information is transmitted back to the centralized cloud for backend service support.

Multi-access edge computing (MEC) is a type of edge computing that extends the capabilities of networks, including 5G networks, with enhanced capabilities.

As a transformational complement to 5G, it provides IT service environments and cloud computing capabilities at the edge of mobile networks, within the radio access network (RAN) and near mobile users.

 

- Multi-Access Edge Computing (MEC): A Revolution at the Mobile Edge

Scalability, flexibility, and cost-effectiveness make cloud computing the platform of choice for application development and delivery. However, most of the data generated by end users and connected devices may never reach the cloud due to privacy requirements, latency constraints, and the high costs associated with pushing large amounts of data to the cloud. 

IoT applications benefit from access to "native cloud services" running near the connection By analyzing telemetry data at the edge of the cloud, minimizing latency for time-critical applications, "sensitive" information is protected locally with as little data to push as cloud.

By processing data locally - MEC applications significantly reduce the amount of data pushed to the cloud, thereby significantly reducing associated cloud storage and processing costs.

Multi-access edge computing (MEC) transforms the 5G mobile communication network into a distributed cloud computing platform running at the edge of the mobile access network. MEC's proximity to end users and connected devices enables mobile operators to open their networks to new differentiated services, while providing application developers and content providers with access to the benefits of the edge cloud.

 

 

[More to come ...]

 

 

 

 

 

Document Actions