Abstract

In an Internet of Things (IoT) environment, large IoT processing pipelines can potentially receive events from a very large number of devices and, in some instances, can receive abnormal bursts of events that can degrade overall operations service level agreements (SLAs) if not handled properly. Such abnormal bursts may be caused by one or more rogue devices, or by malicious external actors, but can be difficult to detect and protect against due to the potentially very large number of devices (up to ~100 million or more) that may be present in an environment. To address such issues, techniques are proposed herein that provide for the ability to detect anomalies in the flow of events and protect SLAs and operations in an automated manner and at very large scale. The techniques proposed herein can be applied to any type of IoT event streams, such as charging data records (CDRs), security and audit logs, and/or the like.

Creative Commons License

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

Share

COinS