P149: Federated analytics across heterogeneous stores: Google Cloud study

Abstract

Federated analytics across heterogeneous stores: Google Cloud study Author: Sonu Kumar Singh (Senior Consultant — Cloud & AI Solutions Architecture, Capgemini US LLC) Professional Credential: Member, IEEE (Membership # 102728576) | ORCID: 0009-0002-9180-4946 Abstract Cloud data platforms are no longer used only for reporting. They now feed machine-learning systems, retrieval pipelines, generative models, and automated agents. In that setting, federated analytics across heterogeneous stores becomes an architectural question rather than a product-selection exercise. This study considers Google Cloud and asks how the design can remain understandable, governable, and testable as the surrounding services evolve. The study narrows federated analytics across heterogeneous stores to a small set of observable concerns rather than treating the topic as an umbrella term. The analysis identifies the design decisions that can be tested in an implementation, the assumptions that must be documented, and the failure modes that would invalidate an otherwise attractive architecture. This makes the research question concrete enough to support engineering evidence rather than opinion. Rather than declaring a winner, this study offers a repeatable way to reason about the problem. The method—design-science prototype and validation—is used to identify comparable responsibilities, likely trade-offs, and the evidence needed for validation. That distinction matters because managed cloud services change quickly, and a strong paper should make clear which statements come from documentation and which come from observed measurements. Architectural Research Scope Research Domain / Theme: Lakehouse & Analytics Architectural Scope: Google Cloud Core Research Question: How should federated analytics across heterogeneous stores be designed, governed, and empirically evaluated for Google Cloud? Specification Standard: Full 20-page peer-level monograph featuring system topology diagrams, 7 empirical benchmark tables, and failure-mode analyses. Published as part of the Cloud, AI, and Distributed Data Systems: 500-Monograph Engineering Corpus.