Dual-Loop Control in DCVerse: Advancing Reliable Deployment of AI in Data Centers via Digital Twins

TL;DR

This paper presents DLCF, a digital twin-based dual-loop control framework for data centers that enhances energy efficiency, safety, and trustworthiness of DRL deployment through real-time data and pre-evaluation.

Contribution

The introduction of DLCF, a novel digital twin-based architecture with dual-loop control, enabling more reliable and efficient AI deployment in data center management.

Findings

Achieves up to 4.09% energy savings in real data center cooling.

Improves DRL policy safety, generalization, and interpretability.

Validates effectiveness through real-world case studies.

Abstract

The growing scale and complexity of modern data centers present major challenges in balancing energy efficiency with outage risk. Although Deep Reinforcement Learning (DRL) shows strong potential for intelligent control, its deployment in mission-critical systems is limited by data scarcity and the lack of real-time pre-evaluation mechanisms. This paper introduces the Dual-Loop Control Framework (DLCF), a digital twin-based architecture designed to overcome these challenges. The framework comprises three core entities: the physical system, a digital twin, and a policy reservoir of diverse DRL agents. These components interact through a dual-loop mechanism involving real-time data acquisition, data assimilation, DRL policy training, pre-evaluation, and expert verification. Theoretical analysis shows how DLCF can improve sample efficiency, generalization, safety, and optimality. Leveraging DLCF, we implemented the DCVerse platform and validated it through case studies on a real-world data center cooling system. The evaluation shows that our approach achieves up to 4.09% energy savings over conventional control strategies without violating SLA requirements. Additionally, the framework improves policy interpretability and supports more trustworthy DRL deployment. This work provides a foundation for reliable AI-based control in data centers and points toward future extensions for holistic, system-wide optimization.