With the rapid rise of the Internet of Things (IoT), we are approaching the point where many organizations will need to process data inputs from millions or even billions of endpoints. Because workloads of that scale will test the limits of today’s centralized data center/cloud model, many leading technologists anticipate a sharp rise in edge computing solutions that move processing power closer to the data sources.
VMware, for example, has signaled a significant shift in its IoT strategy by introducing a range of edge computing solutions designed for specific use cases. The company says these solutions will feature VMware vSAN hyper-converged infrastructure (HCI) software, VMware vSphere and VMware Pulse IoT Center, and will be developed in collaboration with a number of technology partners.
Variously known as cloudlets, micro data centers or fog nodes, these edge resources address some of the challenges created when organizations run increasingly data-heavy workloads in the cloud. These solutions are designed to address both functional limits of the cloud model as well as operational realities of IoT data.
The cloud model transformed computing by centralizing data processing and storage inside large server farms from which organizations can access applications, services and data across Internet links. Cloud service latency — the delay between a client request and a cloud service provider’s response — has always been present, but it has been practically imperceptible for most workloads. The IoT is changing that, however.
With millions of connected devices collecting data at the edge of the network, transferring all that data back and forth to far-flung cloud data centers becomes inefficient, chewing up bandwidth and storage resources. Such inefficiency can ruin an IoT initiative. Because much IoT sensor data such as operational alerts and status reports change rapidly, it has only short-term value. It must be analyzed and acted upon quickly to be very useful.
For these reasons, Gartner predicts that by 2022, 75 percent of enterprise-generated data will be created and processed outside the data center or cloud — up from just 10 percent today. Local analytics offer faster response times, reduced storage costs and an optimum use of bandwidth while also supporting data privacy and compliance requirements.
VMware vSAN HCI and VMware Pulse IoT Center are ideally suited to process and secure sensor data, and the company offers a full ecosystem of server hardware for edge infrastructure or gateway solutions depending on use case, environment and desired rugged ability.
Among the initial applications for VMware’s new solutions are industrial remote IoT applications such as oil well optimization and utility grids, and smart city use cases. All of these require solutions that can reside in ruggedized, disparate, outdoor and oftentimes remote locations with inconsistent network and power. VMware says they are also suitable for manufacturing facilities that require closed networks in ruggedized indoor environments, as well as in branch offices and stores that have unique space and power requirements and must be coordinated across many locations.
With hyper-convergence at the IoT edge, VMware is allowing organizations to take advantage of prebuilt micro data centers, enabling a cost-efficient strategy for moving processing closer to the data sources. That will give organizations better control over their data for faster decision-making and more cost-effective use of bandwidth and storage resources.