Large-Scale Intelligent Microservices
This work addresses the problem of integrating ML into databases for users dealing with varied computational footprints and database technologies, though it appears incremental as it builds on existing Apache Spark and micro-service concepts.
The paper tackles the challenge of deploying machine learning algorithms within databases by introducing an Apache Spark-based micro-service orchestration framework that extends database operations with web service primitives, enabling integration of intelligent services into any datastore with a Spark connector and demonstrating competitive performance on benchmarks.
Deploying Machine Learning (ML) algorithms within databases is a challenge due to the varied computational footprints of modern ML algorithms and the myriad of database technologies each with its own restrictive syntax. We introduce an Apache Spark-based micro-service orchestration framework that extends database operations to include web service primitives. Our system can orchestrate web services across hundreds of machines and takes full advantage of cluster, thread, and asynchronous parallelism. Using this framework, we provide large scale clients for intelligent services such as speech, vision, search, anomaly detection, and text analysis. This allows users to integrate ready-to-use intelligence into any datastore with an Apache Spark connector. To eliminate the majority of overhead from network communication, we also introduce a low-latency containerized version of our architecture. Finally, we demonstrate that the services we investigate are competitive on a variety of benchmarks, and present two applications of this framework to create intelligent search engines, and real-time auto race analytics systems.