Telemetry-based anomaly detection
A system for predicting and/or capturing data relating to anomalies in a networking device is provided. In one example, a networking device receives telemetry data, stores the telemetry data in a cyclic buffer, detects an anomaly, and outputs the telemetry data from the cyclic buffer. The telemetry data from the cyclic buffer may be used for training a prediction model. In another example, a trained prediction model analyzes telemetry data sampled at a first rate, predicts a future anomaly, and in response to the prediction of the future anomaly, triggers sampling of the telemetry at a second rate, faster than the first rate.
1 . A system comprising one or more circuits to:
sample a stream of telemetry data received via a network at a first rate;
process the sampled stream of telemetry data using an artificial intelligence system to predict one or more trigger conditions; and
in response to predicting the one or more trigger conditions, initiate sampling of the stream of telemetry data at a second rate.
2 . The system of claim 1 , wherein sampling the telemetry data is performed by a first sampler, and initiating the sampling of the stream of telemetry data is performed by a second sampler.
3 . The system of claim 2 , wherein processing the data comprises executing a neural network.
4 . The system of claim 3 , wherein the neural network outputs, in response to identifying one or more trigger conditions, instructions to the second sampler.
5 . The system of claim 1 , wherein the stream of telemetry data is received via a software development kit (SDK) hardware interface.
6 . The system of claim 1 , wherein sampling the telemetry data is performed at a first rate, and initiating the sampling of the stream of telemetry data is performed at a second rate, wherein the second rate is faster than the first rate.
7 . The system of claim 1 , wherein the artificial intelligence system is trained to predict the one or more trigger conditions by processing a set of telemetry data received via the network.
8 . The system of claim 7 , wherein the set of telemetry data is stored in a cyclic buffer and processing the sampled stream of telemetry data comprises processing contents of the cyclic buffer.
9 . The system of claim 8 , wherein the contents of the cyclic buffer comprises data received for a time period before and after a second one or more trigger conditions.
10 . A network device comprising one or more circuits to:
sample a stream of telemetry data received via a network at a first rate;
process the sampled stream of telemetry data using an artificial intelligence system to predict one or more trigger conditions; and
in response to predicting the one or more trigger conditions, initiate sampling of the stream of telemetry data at a second rate.
11 . The network device of claim 10 , wherein sampling the telemetry data is performed by a first sampler, and initiating the sampling of the stream of telemetry data is performed by a second sampler.
12 . The network device of claim 11 , wherein processing the data comprises executing a neural network.
13 . The network device of claim 12 , wherein the neural network outputs, in response to identifying one or more trigger conditions, instructions to the second sampler.
14 . The network device of claim 10 , wherein the stream of telemetry data is received via a software development kit (SDK) hardware interface.
15 . The network device of claim 10 , wherein sampling the telemetry data is performed at a first rate, and initiating the sampling of the stream of telemetry data is performed at a second rate, wherein the second rate is faster than the first rate.
16 . The network device of claim 10 , wherein the artificial intelligence system is trained to predict the one or more trigger conditions by processing a set of telemetry data received via the network.
17 . The system of claim 16 , wherein the set of telemetry data is stored in a cyclic buffer and processing the sampled stream of telemetry data comprises processing contents of the cyclic buffer.
18 . The system of claim 17 , wherein the contents of the cyclic buffer comprise data received for a time period before and after a second one or more trigger conditions.
19 . A system, comprising:
a processor; and
a computer-readable storage medium coupled with the processor, wherein the computer-readable storage medium comprises instructions stored thereon that, when executed by the processor, enable the processor to:
sample a stream of telemetry data received via a network at a first rate;
process the sampled stream of telemetry data using an artificial intelligence system to predict one or more trigger conditions; and
in response to predicting the one or more trigger conditions, initiate sampling of the stream of telemetry data at a second rate.
20 . The system of claim 19 , wherein the sampling of the stream of telemetry data at the first rate is performed by a first sampler, and the sampling of the stream of telemetry data at the second rate is performed by a second sampler.