MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202621082001 A) filed by Symbiosis International Deemed University on July 02, 2026, for Machine Learning Based Predictive Resource Scheduling System And Method For Sla-Aware Cloud Computing.
Inventors include Parambrata Sanyal; and Dr. Bhupesh Kumar Dewangan.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: ABSTRACT MACHINE LEARNING BASED PREDICTIVE RESOURCE SCHEDULING SYSTEM AND METHOD FOR SLA- AWARE CLOUD COMPUTING The present invention discloses a machine learning based predictive resource scheduling system (100) and method for SLA-aware cloud computing. The system (100) comprises a data processing layer (110) that converts raw cluster workload traces into structured time-series data, a machine learning prediction layer (120) employing multi-output Random Forest regression for forecasting CPU and memory demand using sliding window sequences, an integration layer (130) providing a standardized CSV interface for cross-platform modularity, a simulation and scheduling layer (140) implementing an SLA-aware predictive VM activation algorithm based on a composite risk metric combining predicted resource demand signals with arrival rate pressure, and an evaluation layer (150) performing decomposed SLA assessment separating violations into response time and capacity components with QoS-adjusted response time computation. [
Disclaimer: Curated by HT Syndication.
