Adaptive Privacy-Aware Reinforcement Federated Learning  for Real-Time Demand Response Management

Roshini P; Niveditha S

Adaptive Privacy-Aware Reinforcement Federated Learning for Real-Time Demand Response Management

Author(s)	Ms. Roshini P, Dr. Niveditha S
Country	India
Abstract	The artificial Intelligence (AI) and large-scale data centres have been rapidly expanding, the electricity requirements and costs of operations, along with the strain on the grid are increasing at a high pace. Using centralized demand response methods – where operational data is transmitted to centralized servers – poses issues related to privacy, communications, security and scalability. For this purpose, this research proposes an “Adaptive Privacy-Aware Reinforcement Federated Learning” framework (APRFL) to solve “Real-Time Demand Response Management” (DDRM) problem in distributed data centres. The Federated Learning (FL) technology, in collaboration with Reinforcement Learning (RL), adaptive aggregation, and secure communication are used to build the combined framework that allows learning together by doing without centralized data collection. Local agents optimally schedule workloads and allocate power, consolidate servers and utilize use renewable resources based on workload, energy, pricing, battery, and environmental data while maintaining Quality of Service. Model parameters are then adaptively aggregated using encryption to represent continuous learning, energy efficient working, cost, privacy and to show indication of scaling and sustainable grid working.
Keywords	Adaptive Federated Learning, Reinforcement Learning, Data Centre Energy Management, Demand Response, Privacy Preservation, Renewable Energy, Intelligent Workload Scheduling
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 5, September-October 2026
Published On	2026-09-30

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Adaptive Privacy-Aware Reinforcement Federated Learning for Real-Time Demand Response Management

Share this