diff options
Diffstat (limited to 'main.tex')
| -rw-r--r-- | main.tex | 39 |
1 files changed, 31 insertions, 8 deletions
@@ -53,7 +53,7 @@ \begin{frame}\frametitle{\textbf{RQ1}: Literature Review I} \begin{tcolorbox}[title=Main Finding I] - The literature on DCDTs is sparse. + There is little literature on DCDTs. Some systems barely classify as DTs (\emph{e.g.,} Kalibre~\cite{DBLP:conf/sensys/WangZD0TCWZ20}, ChatTwin~\cite{DBLP:conf/sensys/LiW0Z0T23}). Existing deployments specialize in \textcolor{Red}{Cooling and Heat Modelling}, together with \textcolor{Red}{3D visualizations}. Most lack predictive modelling of DC operations. @@ -81,6 +81,7 @@ \tiny \textbf{Figure 1.3:} To answer \textbf{RQ1} we designed a generic datacenter digital twin system model based on a comprehensive literature review and findings from \textbf{Table 1.1}. The \emph{Infrastructure Model} simulates the structure of the DC and the \emph{Operations Model} simulates the behaviour of the DC. + \emph{Note:} Federation is not included explicitly but is covered by the model. % Consider splitting the figure into 2 a.k.a. top and bottom. % By the AIAA definition, the DT mimicks the structure and behaviour. % Data Lake -> Data Storage @@ -98,6 +99,7 @@ \vspace{-0.15cm} \tiny \textbf{Figure 1.4:} The predictive datacenter digital twin reference architecture. + We call the system \emph{Sunfish}. The architecture was designed with the \emph{AtLarge Design Process}~\cite{DBLP:conf/icdcs/IosupVTETBFMT19} over several iterations in the past months. \vspace{0.2cm} \end{minipage} @@ -108,8 +110,8 @@ \end{center} \vspace{-0.2cm} \tiny - \textbf{Figure 1.5:} The prototype -- \emph{Sunfish}, and its components based on \textbf{Figure 1.4}. - The time-series data flows first to the \texttt{Grafana} dashboard, \texttt{PostgreSQL} database and \texttt{Redis} cache~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24}. + \textbf{Figure 1.5:} The prototype and its components based on the architecture. + The time-series data flows first to the \texttt{Grafana} dashboard, \texttt{PostgreSQL} database and \texttt{Redis} cache as advised in ~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24}. \vspace{0.1cm} \end{minipage} @@ -262,8 +264,8 @@ \begin{frame}\frametitle{Extra Slides: Technical Setup } \begin{tcolorbox}[title=What is the simulation workload?] The compute workload is BitBrainsSmall. - The failure traces include user reports from Gmail, WhatsApp, Facebook and Twitter. - For predictions we use \texttt{prefabs}~\cite{DBLP:journals/fgcs/VersluisCGLPCUI23}. + The failure traces include Gmail, WhatsApp, Facebook and Twitter. + For predictions we use different statistical distributions~\cite{DBLP:journals/fgcs/VersluisCGLPCUI23}. \end{tcolorbox} \begin{tcolorbox}[title=What is the experiment environment?] A commodity laptop: Framework Laptop 13, with 32GB of DDR5 RAM and an AMD Ryzen 7840U processor and an ArchLinux OS with Linux 7.0.13-arch1-1 kernel. @@ -282,6 +284,18 @@ \end{frame} +\begin{frame}\frametitle{Extra Slides: Experiment 1} + \begin{tcolorbox}[title=Clarification] + In experiment 1 we are able to differentiate between severe failures, that down more than some threshold $\tau$ hosts. + $\tau$ is determined using predictions based on potential distribution of failures, modeled with \textasciitilde\emph{N(1.5, 1.5)}. + \end{tcolorbox} + + \begin{center} + \includegraphics[width=0.58\linewidth]{images/alarms_vs_failures.pdf} + \end{center} + \tiny + \textbf{Figure E.1:} The comparison between failures experienced and alarms raised. +\end{frame} \begin{frame}\frametitle{Extra Slides: Why Digital Twinning?} \begin{tcolorbox}[title=Definition] @@ -312,11 +326,20 @@ \tiny \textbf{Figure E.3:} Real-time control that is tightly-coupled with the IT equipment is a prerequisite for timely predictions within seconds/minutes~\cite{DBLP:journals/computer/AthavaleBBMMPS24}. \end{frame} - - +\begin{frame}\frametitle{Extra Slides: Experiment 2} + \begin{tcolorbox}[title=Statistical Distributions] + Different failure distributions were used in order to predict the true failure distribution. + \textbf{Table E.1} summarizes the distributions. + \end{tcolorbox} + \begin{center} + \includegraphics[width=\linewidth]{images/failure_models_table.png} + \end{center} + \tiny + \textbf{Table E.1:} Different failure models used throughout this project. + All failure models come from Javadi \etal (for a more thorough overview see~\cite{DBLP:journals/jpdc/JavadiKIE13}) +\end{frame} % Computational Fluid Dynamics (CFD) have high computation overhead, unsuitable for real-time simulation of a dynamic datacenter. %Moreover oftentimes a poorly configured CFD model can lead to high error rates~\cite{DBLP:conf/sensys/WangZD0TCWZ20}. %Data-driven Machine Learning performs poorly by the cases not covered in the training data. - \end{document} |