Data Center Networking and Monitoring

Objectives #

According to the latest reports of the US Environmental Protection Agency (EPA), 70 billion kWh equals 1.8% of the whole electricity power of the U.S.was consumed in DCs by 2014. Up to 50% of this power is consumed for cooling of IT and communication equipment in a wasteful way. Inefficient regions in a DC are detectable based on high temporal and spatial fidelity maps of temperature, relative humidity, airflow, and other environmental parameters. These maps can also be used in predictive maintenance, floor planning, and smart ventilation of cooling units. The objective of this project was to facilitate environmental monitoring and predictive maintenance in data centers by studying the feasibility and performance of three different approaches or a combination of them:

  • Physical modeling using Computational Fluid Dynamic (CFD) simulations and surrogate modeling
  • Statistical modeling by machine learning.
  • Real-time measurement by an automated data collection framework from wireless sensors.

Participant #

  1. Sahar Asgari (PhD)
  2. Mehdi Jafarizadeh (PhD)
  3. Chenhe Li (MSc)
  4. Jun (Tyler) Li (MSc)
  5. Xingzhi Liu (MSc)
  6. Ghada Badawy

Research Thrusts #

1- Data Center Wireless Sensor Networks

The main outcome of this research is a reliable, low-power, adaptable, and easy-to-commission Bluetooth Low Energy (BLE) based network architecture for Data Center Wireless Sensor Networks (DCWSNs). Toward this goal:

  • A hierarchical network, named Low Energy Monitoring Network (LEMoNet) is designed and evaluated experimentally in a small-scale DC, by simulation in a medium scale DC, and through an analytical model in a large scale DC.
  • LeMoNet is further improved by a Software-Defined Networking (SDN) based framework, named SoftBLE.
  • Sensor deployment was accelerated by two automated sensor mapping approaches, named thermal piloting and multimodal sensor localization
2- Hybrid Modeling for DCs

In this research, a fast, adaptive, and accurate hybrid surrogate model is developed by combining a DDM and physics-based relations to predict real-time temperatures in a DC. Toward this goal:

  • An artificial neural network (ANN) in conjunction with a 3D zonal model is employed to predict the spatio-temporal temperature distributions.
  • The model is compared with a black-box model based on a nonlinear autoregressive exogenous model (NARX) for interpolative and extrapolative predictions.
  • The influence of varying server workload distribution and cooling unit operational conditions on temperature distribution is investigated.
3- Fault Diagnosis in DCs

In this research, fault detection and diagnosis (FDD) algorithms and associated control strategies are applied to detect, diagnose, and isolate faults to ensure that the cooling system runs appropriately. Toward this goal:

  • A rapid and accurate single and multiple FDD strategy are developed for a DC using data-driven fault classifiers informed by a gray-box temperature prediction model.
  • OCSVM and Nonlinear AutoRegressive Exogenous (NARX) techniques are considered for fault detection.
  • Two different data-driven classifiers, 2D-CNN and CNN_LSTM, are implemented to predict multiple simultaneous failures while using a few simultaneous failure conditions in training data.

Publications #

Sorry, no publications matched your criteria.

Downloads #

    Acknowledgement #

    This research was in part supported by the collaborative research and development grant NSERC CRDPJ 500720 and NSERC Discovery grant.

    Powered by BetterDocs