The GOES-R Product Generation architecture

The GOES-R system will substantially improve users' ability to succeed in their work by providing data with significantly enhanced instruments, higher resolution, much shorter relook times, and an increased number and diversity of products. Considerably greater compute and memory resources are necessary to achieve the necessary latency and availability for these products. Over time, new and updated algorithms are expected to be added and old ones removed as science advances and new products are developed.

The GOES-R GS architecture is being planned to maintain functionality so that when such changes are implemented, operational product generation will continue without interruption.

The primary parts of the PG infrastructure are the Service Based Architecture (SBA) and the Data Fabric (DF). SBA is the middleware that encapsulates and manages science algorithms that generate products. It is divided into three parts, the Executive, which manages and configures the algorithm as a service, the Dispatcher, which provides data to the algorithm, and the Strategy, which determines when the algorithm can execute with the available data. SBA is a distributed architecture, with services connected to each other over a compute grid and is highly scalable. This plug-and-play architecture allows algorithms to be added, removed, or updated without affecting any other services or software currently running and producing data. Algorithms require product data from other algorithms, so a scalable and reliable messaging is necessary. The SBA uses the DF to provide this data communication layer between algorithms.

The DF provides an abstract interface over a distributed and persistent multi-layered storage system (e.g., memory based caching above disk-based storage) and an event management system that allows event-driven algorithm services to know when instrument data are available and where they reside. Together, the SBA and the DF provide a flexible, high performance architecture that can meet the needs of product processing now and as they grow in the future.