Improving Analytics with Time Series and Vector Databases

Time series analysis plays a crucial role in many fields, particularly in Internet of Things (IoT) devices. With time series data, we can detect patterns and trends over particular periods, enabling us to forecast and analyze future time-dependent events. Common examples of time series use cases include forecasting weather temperatures and stock prices and monitoring sensor data. InfluxDB is a highly optimized time series database for storing vast amounts of time series data. It offers efficient solutions for operations such as aggregations and downsampling. However, relying on time-series databases alone can be challenging, especially if our use case demands us to perform a similarity search. In a recent talk at the Zilliz Unstructured Data Meetup, Zoe Steinkamp, Developer Advocate at InfluxDB, discussed an approach to combining InfluxDB with Milvus to store, query, and perform similarity searches on time-dependent use cases. Milvus is a vector database that stores data in vectors, enabling efficient similarity searches using techniques like cosine similarity or Euclidean distance. By combining the two databases, the strengths of both systems can be fully utilized. As you can see in the example above, time series data from sensors can be stored in InfluxDB, while vector data can be stored in Milvus. This integration allows for advanced use cases like anomaly detection in real-time traffic conditions.