Intellectual Property India Publishes Patent Application for A System And Method For Machine Learning-Based Predictive Maintenance Of Distributed Computing Systems

MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641091431 A) filed by Pragati Engineering College on July 28, 2026, for A System And Method For Machine Learning-Based Predictive Maintenance Of Distributed Computing Systems.

Inventors include Mr. M Sunil Raj; Mr. Akella Yeswanth; Marukurthi Chaitanya Prakash; Palacharla Mahesh Sidhardha; and Pasagadugula Naga Satya Suresh Kumar.

The application for the patent was published on July 31, 2026, under issue no. 31/2026.

Abstract: ABSTRACT A System and Method for Machine Learning-Based Predictive Maintenance of Distributed Computing Systems The present disclosure relates to a system and method for performing predictive maintenance for distributed computing systems with machine learning. The system includes one or more processors, a memory, and functional modules including a distributed multi-source data acquisition module, an adaptive feature evolution engine, a distributed degradation correlation engine, a hierarchical causal degradation reasoning engine, a multi-level prediction confidence evaluation module, a dynamic threshold self-calibration module, an autonomous prediction validation module, a resource-aware incremental learning module, an intelligent maintenance opportunity optimization module, an adaptive maintenance policy generation module, a distributed federated knowledge exchange module, a maintenance feedback reinforcement engine, and an autonomous maintenance orchestration controller. The disclosed system continuously collects synchronized operational data, identifies degradation relationships, determines causal degradation sources, validates prediction reliability, dynamically optimizes maintenance schedules, incrementally updates prediction models and continuously improves predictive performance using maintenance feedback. The invention provides improved prediction accuracy, reduced false maintenance alerts and computational overhead, optimization of resource usage, minimization of system downtime and enhancement of operational reliability, scalability and availability of distributed computing infrastructures.

Disclaimer: Curated by HT Syndication.