The Time Series Analytics microservice is a powerful, flexible solution for real-time analysis of time series data. It supports advanced analytics through User-Defined Functions (UDFs) written in Python. By leveraging the Intel® Extension for Scikit-learn*, you can accelerate machine learning workloads within their UDFs, unlocking high-performance anomaly detection, predictive maintenance, and other sophisticated analytics.
The key features include:
- Use your own data sets and Python-based analytics for custom analysis.
- Automatically save results in InfluxDB for easy management and visualization.
- Detect anomalies, send alerts, and advanced analytics in various settings.
To see the system requirements and other installation, see the following guides:
- System Requirements: Hardware and software requirements for running the microservice.
- Get Started: Step-by-step guide to getting started with the docker compose deployment of the microservice.
The Time Series Analytics microservice can take input data from Input payload and configuration management via REST APIs and UDF deployment package. The high-level architecture diagram is as follows:
The default flow consists of using a temperature simulator to generate data in JSON format, which is then analyzed by a custom function within a time series analytics service to identify and log any temperature anomalies.
For more details on Architecture, see Architecture.
- Overview: A high-level introduction to the Time Series Analytics Microservice.
- Docker compose deployment: Instructions for deploying the microservice using docker compose.
- Helm deployment: Instructions for deploying the microservice using helm.
- Configuration: Instructions for advanced configuration.
- API reference: Instructions to exercise REST APIs
- Release Notes: Information on the latest updates, improvements, and bug fixes.
Follow the steps to run the unit tests.
git clone https://github.com/open-edge-platform/edge-ai-libraries
cd edge-ai-libraries/microservices/time-series-analytics
echo "Running unit tests"
./tests/run_tests.shFollow the steps to run the functional tests.
git clone https://github.com/open-edge-platform/edge-ai-libraries
cd edge-ai-libraries/microservices/time-series-analytics/tests-functional
echo "Running functional tests"
pip3 install -r requirements.txt
pytest -q -vv --self-contained-html --html=./test_report/report.html .