Energy savings in data centers: A framework for modelling and control of servers’ cooling

Lucchese, Riccardo; Olsson, Jesper; Ljung, Anna‐Lena; Garcia-Gabin, Winston; Varagnolo, Damiano

doi:10.1016/j.ifacol.2017.08.1624

Cited by 11 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lucchese et al [13] propose a control-oriented, non-linear, thermal model of individual servers and identify model parameters by CFD simulations of an idealized server set-up. Further simulations are then used to (in silico) both validate the model and test a Receding Horizon Control (RHC) strategy, aiming to keep IT component temperatures below thermal bounds while minimizing fan energy use.…”

Section: Related Workmentioning

confidence: 99%

Modular and Transferable Machine Learning for Heat Management and Reuse in Edge Data Centers

2023

View full text Add to dashboard Cite

This study investigates the use of transfer learning and modular design for adapting a pre-trained model to optimize energy efficiency and heat reuse in edge data centers while meeting local conditions, such as alternative heat management and hardware configurations. A Physics-Informed Data-Driven Recurrent Neural Network (PIDD RNN) is trained on a small scale-model experiment of a six-server data center to control cooling fans and maintain the exhaust chamber temperature within safe limits. The model features a hierarchical regularizing structure that reduces the degrees of freedom by connecting parameters for related modules in the system. With a RMSE value of 1.69, the PIDD RNN outperforms both a conventional RNN (RMSE: 3.18), and a State Space Model (RMSE: 2.66). We investigate how this design facilitates transfer learning when the model is fine-tuned over a few epochs to small dataset from a second set-up with a server located in a wind tunnel. The transferred model outperforms a model trained from scratch over hundreds of epochs.

show abstract

Section: Related Workmentioning

confidence: 99%

Modular and Transferable Machine Learning for Heat Management and Reuse in Edge Data Centers

2023

View full text Add to dashboard Cite

show abstract

“…These are either using Model Predictive Control (MPC) and data-driven modeling or training an RL agent. In 2017, Lucchese et al [10] created a CFD based model for which they found the parameters using data-driven methods. In 2018 Lazic et al [11] estimated a linear model from data with only small amounts of knowledge imposed to create sparsity in the model.…”

Section: Controlmentioning

confidence: 99%

“…The model used for π θ and V ϕ is presented in Fig. 7 and is made up of policy and value networks, both using the input defined in (10). Figure 7: network structure used for the agent.…”

Section: Reinforcement Learning Agentmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Control of Data Center Cooling using Deep Reinforcement Learning

Heimerson

Sjölund

Brännvall

et al. 2022

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)

View full text Add to dashboard Cite

In this paper, we explore the use of Reinforcement Learning (RL) to improve the control of cooling equipment in Data Centers (DCs). DCs are inherently complex systems, and thus challenging to model from first principles. Machine learning offers a way to address this by instead training a model to capture the thermal dynamics of a DC. In RL, an agent learns to control a system through trial-and-error. However, for systems such as DCs, an interactive trial-and-error approach is not possible, and instead, a high-fidelity model is needed. In this paper, we develop a DC model using Computational Fluid Dynamics (CFD) based on the Lattice Boltzmann Method (LBM) Bhatnagar-Gross-Krook (BGK) algorithm. The model features transient boundary conditions for simulating the DC room, heat-generating servers, and Computer Room Air Handlers (CRAHs) as well as rejection components outside the server room such as heat exchangers, compressors, and dry coolers. This model is used to train a RL agent to control the cooling equipment. Evaluations show that the RL agent can outperform traditional controllers and also can adapt to changes in the environment, such as equipment breaking down.

show abstract

Energy‐efficient operation of indirect adiabatic data center cooling systems via Newton‐like phasor extremum seeking control

Lionello

Lucchese

Rampazzo

et al. 2021

Adaptive Control & Signal

Self Cite

View full text Add to dashboard Cite

Summary This paper considers the problem of optimizing the operation of Indirect Adiabatic Cooling (IAC) systems with application to data centers. Optimal operation is achieved when the required cooling demand is satisfied at the minimum energy cost. For this purpose, we design a supervisory control system, where the higher layer determines the optimal set‐points for the local controllers by employing an Extremum Seeking Control (ESC) scheme. In particular, we consider a Newton‐like phasor ESC, which augments the derivative estimator underlying the phasor approach to capture also the Hessian of the plant index and then it uses these estimates to steer the system along a Newton‐like direction. The effectiveness of the considered approach is tested in simulation by exploiting a Matlab‐based simulation environment including an IAC system and a computer room.

show abstract

Energy savings in data centers: A framework for modelling and control of servers’ cooling

Cited by 11 publications

References 9 publications

Modular and Transferable Machine Learning for Heat Management and Reuse in Edge Data Centers

Modular and Transferable Machine Learning for Heat Management and Reuse in Edge Data Centers

Adaptive Control of Data Center Cooling using Deep Reinforcement Learning

Energy‐efficient operation of indirect adiabatic data center cooling systems via Newton‐like phasor extremum seeking control

Contact Info

Product

Resources

About