GIANT: AI- and Digital Twin-Based Framework for Proactive and Energy-Efficient Resource Management in HPC Datacenters
preprint
OA: closed
CC-BY-4.0
Abstract
The High Performance Computing (HPC) sector is driving contemporary technological and scientific innovation. However, the increasing demand for computational power and the advent of the exascale era have underscored the urgent need to address the energy, operational, and environmental implications of such growth. In response, the GIANT framework introduces an intelligent and modular solution for the dynamic management of modern datacenter resources. By integrating Artificial Intelligence (AI) and Digital Twin technologies, GIANT enables real-time monitoring, predictive analytics, and adaptive control of HPC infrastructures. The framework’s layered architecture supports the collection and processing of heterogeneous data, allowing for accurate forecasting of workloads and energy consumption, early detection of anomalies, and proactive system optimization. Furthermore, GIANT incorporates dynamic power capping strategies, shifting the paradigm from traditional reactive approaches to proactive, efficiency-driven management. This transition not only enhances system reliability and performance but also contributes to reducing the environmental impact of high-performance datacenters. The proposed solution is scalable, adaptable, and aligned with the growing demand for sustainable and intelligent computing systems in the exascale era.
My notes (saved in your browser only)
Citation neighborhood (no data yet)
We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.
Source provenance
- europepmc
- last seen: 2026-05-20T01:45:00.602351+00:00
- unpaywall
- last seen: 2026-05-22T02:00:06.705733+00:00
License: CC-BY-4.0