MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115387 A) filed by Sri Eshwar College Of Engineering on September 24, 2026, for Ai-Enabled Predictive Energy-Aware Network Management System For Dynamic Activation And Deactivation Of Network Resources.
Inventor includes Pl. Rajarajeswari.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: An AI-enabled predictive energy-aware network management system, method, and computer-readable medium are disclosed for dynamically orchestrating the power states of physical and virtual network elements. The system includes a distributed telemetry ingestion engine that continuously aggregates multi-dimensional network metrics across multiple infrastructure layers. A predictive intelligence core utilizes a trained spatio-temporal graph neural network architecture to process the aggregated telemetry and generate a time-indexed, multi-step traffic demand forecast tensor over a future prediction horizon. A dynamic resource optimization engine maps the traffic demand forecast tensor against a multi-state hardware operational matrix and executes a mixed-integer optimization function to calculate an optimized resource state orchestration schedule. The optimization function minimizes cumulative infrastructure energy consumption while satisfying a minimum Quality of Service (QoS) capacity boundary and mitigating hardware-specific state transition latency penalties. An automated network orchestrator interface translates the calculated schedule into machine-executable control commands and proactively dispatches them to the target network elements at a look-ahead time offset equal to or greater than the hardware wake-up latency penalty, thereby dynamically activating or deactivating network elements ahead of predicted traffic variations to eliminate wake-up latency service degradation and suppress ping-pong state oscillations.
Disclaimer: Curated by HT Syndication.
