TPU Inference Servers for Efficient Edge Data Centers - DOWNLOAD

Staying ahead of the edge: Managing the hidden costs of edge computing

Categories Edge Computing News  |  Guest Posts
Staying ahead of the edge: Managing the hidden costs of edge computing

By Ziv Koren, Chief Product Officer, Telco Systems

Edge computing is transforming industries, enabling decision-makers to benefit from on-prem data processing in real-time, leading to better business decisions and competitive outcomes. However, implementing efficient edge computing across numerous sites is complex and challenging. Consider the diversity of devices, the variety of applications, the spectrum of sites, and the sheer immense scale of the edge. Then throw multiple vendors into the mix, add some connectivity integration and an assortment of network connection types, and hey presto — complexity galore.

This complexity should be addressed holistically, taking into account key factors, such as the deployment of hardware and software, remote operation and management, automation and orchestration, security, and connectivity. Companies looking to implement Edge deployments need to build their architecture from day one around the concepts of simplified asset management and operations in order to reduce those hidden costs that have a tendency to appear around day two.

Everything from remote

Managing and operating a large number of geo-distributed edge sites, to maintain a high level of productivity is a challenge without qualified technical staff at each site. A chain store, for example, operates many stores and warehouses and uses hundreds or even thousands of edge devices, each running applications like smart queue management, anti-shoplifting, in-store pattern analysis, smart inventory, and more.

Achieving the goal of as little technical staff on site as possible requires the capacity for remote deployment, remote operations and remote end-to-end lifecycle management. Moreover, ensuring the system’s health by remotely monitoring the performance of all applications and connected devices and highlighting potential issues before they escalate, is critical to maintaining high operational efficiency in a geographically distributed infrastructure with site diversity.

In energy production, for example, malfunctions can be detected in solar panels or wind turbines, requiring a maintenance technician. Remote troubleshooting supports a high level of productivity by significantly reducing the number of truck rolls required to provide a service or the time it takes to troubleshoot a problem, and decreases the Mean Time To Repair (MTR).

Automation and orchestration of workloads

Seamless automatic deployment of devices and applications is vital in a distributed-site environment. In telecommunications, the cost of manually deploying thousands of routers, switches, and other edge devices, on top of the operational cost of sending technical staff to each site to install a new service, upgrade, or update applications is prohibitive.

Zero Touch Provisioning (ZTP) for instance, automates the installation and initial configuration of even very large-scale edge deployments. But any ZTP failure means manual labor that adds to the operational cost. For example, a 1% failure rate of deploying 100,000 edge devices requires a manual deployment of 1,000 devices. Let’s assume that manual deployment of a single device requires 1 hour at $250 per hour; this translates into an additional cost of $250,000. That cost drops to only $2,500 with an outstanding ZTP success rate of six nines (failure rate of 0.01%) as only 10 devices will require manual deployment.

But even more than that — operators are looking to drastically reduce the amount of time and effort they spend simplifying setting up workloads. Above all they’re searching for the right tools to remotely operate and orchestrate any number of edge devices, running complex workloads, across diverse site environments. And if they can do all that through one single management system – all the better.

Openness and future-proofing

Across a wide array of industries, providers operate a seemingly endless variety of devices and applications. A healthcare provider will often operate a range of devices, such as wearable monitors, imaging, and ECG machinery in addition to telemedicine and other medical services applications — all from different vendors. Ensuring that all are connected seamlessly to create a workload requires careful planning and implementation, which only adds to the complexity.

Furthermore, digital transformation and market forces sometimes mean scaling up to tens (or hundreds) of thousands of devices and locations. Regardless of vendor choice, this requires easy and remote onboarding of services. More than ever, providers will search for the freedom of choice in creating any combination of device, application, network and location that works for their needs — now and tomorrow.

Secure and reliable connectivity

Connectivity is critical for edge computing as it enables data to be exchanged and transmitted locally at a stand-alone site and to other sites or data centers.

For example, a logistics enterprise operating multiple warehouses, as well as a transportation fleet, generates vast amounts of data that need to be processed in real-time. Providing connectivity means investing in additional networking equipment and edge devices, such as routers, switches, and wireless access points. This significantly increases the Total Cost of Ownership (TCO), without even going into the nightmare of operating and managing all of these additional devices, when one device could just as easily handle all these connectivity functions.

Making your edge work for you

Choosing the right edge computing system is essential for ensuring the success of its implementation, and guarantees meeting business needs more efficiently in a competitive environment. While edge computing improves operational efficiency and, ultimately, the bottom line, it’s still not devoid of challenges.

Make your edge work for you by ensuring that you’re streamlining your asset management and that you’re integrating your basic connectivity needs. Enable remote deployment and remote troubleshooting of your devices and services, and ensure automation and orchestration of workloads. These are the first steps toward mitigating the hidden costs of edge computing.

About the author

Ziv Koren is Chief Product Officer for Telco Systems — the makers of Edgility — a platform that brings the cloud experience to the edge, enabling ISVs, SIs and IT to easily deploy, update and monitor business apps on the edge, bringing them closer to consumers, data and sensors.

DISCLAIMER: Guest posts are submitted content. The views expressed in this post are that of the author, and don’t necessarily reflect the views of Edge Industry Review (EdgeIR.com).

Article Topics

 |   |   |   |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Featured Edge Computing Company

Edge Ecosystem Videos

Latest News