Distributed edge computing is increasingly becoming the standard architecture for many uses cases. Distributed edge computing processes typically process workloads closer to where data originates, as opposed to cloud computing, which typically processes workloads in remote data centers. In some instances, such as for deployments in which data is to be aggregated across a large number of sources located in poorly connected environments, data generated at the sources can be sent opportunistically to the cloud for further processing. However, since the data cannot be streamed continuously to the cloud, the data may arrive out of order and/or late with respect to the clock time of an aggregator in the cloud. Techniques are introduced herein that improve edge-cloud data reporting through the use of a time-series database (TSDB)-based architecture that can adjust for network load, while still ensuring efficient storage and querying capabilities.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.