Companies are increasingly generating huge volumes of data at the network edge. Massive volumes of data are flowing from smart meters, Internet of Things (IoT) sensors, autonomous vehicles, health monitors, and industrial automation devices, to name just a few sources.
Many teams want to use data streaming from the edge to better understand their business. Imagine an oil exploration company that aggregates and filters sensor data at the edge, extracting the most critical time-sensitive data points for subsequent processing at a centralized data center. Or a manufacturer that uses a machine learning application to diagnose a potentially failing component or spot a quality issue in a remote location.
However, it’s not practical to transmit these growing data volumes from the edge into a centralized data center for processing or analysis. Some companies manually collect data from the edge onto storage devices and physically transport it to data centers. But this process is time-consuming and cannot yield real-time insights.
Nor is it easy to process data near the location where it is created. Often these edge environments lack space for computer hardware, or using the available space comes with a big opportunity cost. What’s more, processing power at the edge is typically insufficient for huge data volumes, since small-footprint hardware designed for edge computing tends to be smaller than hardware running in data centers. And poor latency caused by network bottlenecks prevents transactions from being processed in a timely manner.
To read more about streaming data from the network edge, get the full special report here: Full Story PDF