Three Considerations When Deploying Edge Computing

This portion of a  new special report from Data Center Frontier takes readers through three key considerations when deploying edge computing solutions for their data centers, including defining the use case, lack of expertise and concerns around data management. 

Deploying edge computing infrastructure can be challenging for end users, who must adapt their models and processes for a smaller, denser environment to process more services and user data (often with a specific use case in mind).

There are three common challenges reported by end users working with edge designs: Defining the use case, inexperience with edge deployments and data management concerns.

Defining the Use Case

This is actually a major stopping point for edge projects. There may be a great idea or concept but defining the use case reaches a barrier. This usually happens when there’s misalignment between IT, operations technology (OT) requirements and management. In these situations, it’s important to take a step back and look at the long-term strategy of your own organization. Are you growing? Will you be supporting remote users? Are you trying to deliver new types of connected services? If you see that edge is a fit, take the next steps to write up a solid business plan and technology strategy to support it. You don’t have to be an edge expert to clearly define your own use-case. Furthermore, there are providers who can help you on this journey. However, it’s important to align infrastructure and business to ensure that your strategy can succeed. From there, it’s key to work with the right people who can bring that vision to life. Which brings us to the next point.

Lack of Expertise

Even if an organization is able to define a use case, they might get stuck when it comes to working with partners who can help them implement the vision. Edge deployments come with different considerations around space, density, power, management, connectivity and redundancy than a traditional data center. Identifying experienced partners is essential, and there are a growing number of organizations, partners and data center providers that can help with edge solutions.

Software-defined solutions allow you to integrate with core data center systems and support powerful data locality policies, which are critical requirements for industries like pharma, health care, and other regulated organizations.

Concerns Around Data Management

End users will need to take extra time to define data requirements and management policies. Is the data transient or will it be stored at the edge? What type of data is being processed? What is the connectivity control method around the data? All of this will need to be defined and integrated into an effective edge solution. Compliance and regulation can be built into an edge architecture, but this requires extra precautions to ensure data security and control. Although there isn’t a defined standard on edge computing yet, it’s important to consider the location of the edge, storage systems at the edge, how the data will be processed, and who will have access to it. Software-defined solutions allow you to integrate with core data center systems and support powerful data locality policies, which are critical requirements for industries like pharma, health care, and other regulated organizations.

Deployments, Designs and Form Factors

All these ambitions must be secured and powered by enclosures suitable to the environment and business case. Edge computing will rely upon modular enclosures in a range of form factors to support the scope of envisioned implementations and use cases.

Early players have developed modules sized by power capacity, ranging from 48 kW to about 300 kW of power capacity. Most companies are using a repeatable “building block” approach that can be used to deploy standardized infrastructure in multiple sites, as well as multiple modules at single sites that require expansion.

Network infrastructure will lead the first wave of edge infrastructure, with compute to follow. This will guide the evolution of edge design to support more power capacity over time.

Monitoring and alert systems will be important components of remote management systems, both for physical security and the ability to respond to weather damage.

Many edge facilities will be unstaffed remote sites, and enclosure designs will need to incorporate the security and reliability features to support unstaffed
operation, including cameras and sophisticated access control. Monitoring and alert systems will be important components of remote management systems, both for physical security and the ability to respond to weather damage.

For edge computing to be deployed everywhere at scale, it will need to be compact, cheaper and take the network to new places. This is an area where existing designs and technology will be adapted to meet specific customer needs, and the emerging economics of the edge computing business.

See here for a comprehensive list of the significant players in the edge computing industry key to the colocation and data center business.

And download the full report, courtesy of Chatsworth Products, “Edge Computing: A New Architecture for a Hyperconnected World,” that explores the possibilities of the edge data center and how edge computing is changing the colocation and data landscape of today.