The wireless service providers provide nationwide service using a very distributed network. The service locations tend to be closer to the customer than the cloud datacenters. When these locations are multi-purposed to provide wireless services and host edge computing services, it becomes a unique model for edge computing and has distinct advantages. In the mobile edge computing model, computing resources are deployed in service access point (SAP) locations or other locations in the core. Applications running on these edge computing servers can be accessed from mobile endpoints through 4G or 5G connections.
To further understand the benefits of mobile edge computing, we will use latency as a benchmark and review how it influences the 5 C’s of latency (connection, closeness, capacity, contention, and consistency). Concerning connection and closeness, not only is this edge closer than the cloud regions, but it also inherits the benefits from the transport characteristics of 5G and the savings from the direct path from the wireless devices bypassing the internet to the computing resources. Capacity is another crucial differentiator against many of the other edge computing models. With the ability to host various compute instances such as Graphical Processing Units, the mobile edge provides a scalable edge infrastructure. By processing and filtering many requests right at the mobile edge, the mobile edge can reduce the contention at the backend servers. Bypassing the internet and providing a shorter direct path also influences the consistency of the experience.
While some of the other edge models can be closer than the mobile edge, when you consider the overall benefits, the mobile edge strikes the right balance. In many of the other models, the hardware is located in the customer site, and hence additional effort is needed to handle power, space, cooling, management, and physical safety. Mobile edge computing allows users to consume applications as services, making it easier for customers to access low latency applications without deploying hardware in their networks.
In summary, each of the edge computing models has a sweet spot segment and associated challenges. Our recommendation is to start with the customer’s application needs and evaluate the best edge computing model.
To learn more about how Verizon professional services can help you build the ideal edge architecture to help meet your business needs.