Personal tools

5G Edge Computing Infrastructure

[Houston, Texas]


- Overview

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.


- 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 Infrstructure

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.



[More to come ...]






Document Actions