Abstract-This paper presents data centers from a cyberphysical system (CPS) perspective. Current methods for controlling information technology (IT) and cooling technology (CT) in data centers are classified according to the degree to which they take into account both cyber and physical considerations. To evaluate the potential impact of coordinated CPS strategies at the data-center level, we introduce a control-oriented model that represents the data center as two coupled networks: a computational network representing the cyber dynamics and a thermal network representing the physical dynamics. These networks are coupled through the influence of the IT on both networks: servers affect both the quality of service (QoS) delivered by the computational network and the generation of heat in the thermal network. Using this model, three control strategies are evaluated with respect to their energy efficiency and computational performance: a baseline strategy that ignores CPS considerations, an uncoordinated strategy that manages the IT and CT independently, and a coordinated strategy that manages the IT and CT together to achieve optimal performance with respect to both QoS and energy efficiency. Simulation results show that the benefits to be realized from coordinating the control of IT and CT depend on the distribution and heterogeneity of the computational and cooling resources throughout the data center. A new cyber-physical index (CPI) is introduced as a measure of this combined distribution of cyber and physical effects in a given data center. We illustrate how the CPI indicates the potential impact of using coordinated CPS control strategies.
This paper presents a new control strategy for data centers that aims to optimize the trade-off between maximizing the payoff from the provided quality of computational services and minimizing energy costs for computation and cooling. The data center is modeled as two interacting dynamic networks: a computational (cyber) network representing the distribution and flow of computational tasks, and a thermal (physical) network characterizing the distribution and flow of thermal energy. To make the problem tractable, the control architecture is decomposed hierarchically according to time-scales in the thermal and computational network dynamics, and spatially, reflecting weak coupling between zones in the data center. Simulation results demonstrate the effectiveness of the proposed coordinated control strategy relative to traditional approaches in which the cyber and physical resources are controlled independently.
Abstract-This paper concerns the management of energy in data centers using a cyber-physical model that supports the coordinated control of both computational and thermal (cooling) resources. On the basis of the structure of the proposed model and practical issues related to the data center layout and distribution of information, we propose a hierarchical optimization scheme in which the higher level chooses goals for regulation at the lower level. Linear programming is applied to solve sequences of one-step look-ahead problems at both the top level and in the lower-level controllers to solve. The approach is illustrated with simulation results.
Abstract-This paper concerns the power minimization problem in server farms. The power minimization problem over dynamic power allocation schemes is formally defined and formulated as an optimization problem. It is shown that finding the optimal solution for this optimization problem is not feasible. Inspired by control theory, a well-established method to optimize a cost function over the constraints imposed by the evolution of a dynamical system, called Real-Time Optimization (RTO), is invoked to find a sub-optimal solution for the power minimization problem. The obtained algorithm is simulated and compared with the state-of-the-art optimal static power allocation solution. A considerable improvement in energy consumption is attained for the same quality of service (QoS) level, when dynamic power allocation is used.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.