\documentclass[12pt, handout]{beamer}
\input{style/style.tex}
\begin{document}

\frame{\titlepage \centering \footnotesize Online slideshow: \url{mjkw.pl/vu/bsc}}

\begin{frame}\frametitle{Motivation}
	\begin{tcolorbox}[title=Context]
		21\textsuperscript{st} century datacenters (DC) are mostly heterogeneous~\cite{DBLP:conf/date/MilojicicFDR21} and
		modern computational needs of AI drive managers to diversify datacenters even more~\cite{DBLP:journals/computer/AthavaleBBMMPS24}.
		In result datacenters become extremely complex and hard to operate with millions of CPU's, GPU's etc.
	\end{tcolorbox}
	\begin{center}
		\includegraphics[width=\linewidth]{images/datacenter_complexity.png}
	\end{center}
	\tiny
	\textbf{Figure 1.1:} Society depends on datacenters to keep running, and therefore we cannot afford to let these systems break down or experience significant performance-related issues.
	With millions of servers in the largest datacenters, real-time management becomes very difficult.
	Left to right: a Google datacenter, server racks, Ada Lovelace AD102 GPU architecture.
\end{frame}

\begin{frame}\frametitle{Problem Statement}
	\begin{tcolorbox}[title=DCDT's lack predictive analytics]
		We need Datacenter Digital Twins (DCDT) to be better able to detect and solve issues in critical ICT infrastructure~\cite{DBLP:journals/computer/AthavaleBBMMPS24}.
		However, DCDT's are still actively developed and lack crucial features such as predictive analytics~\cite{DBLP:usdoe/report/AP26894} to \emph{e.g.,} prevent unexpected failures.
		With predictive analysis (\emph{e.g.,} simulation) DCDT's could save millions of lost \$USD~\cite{DBLP:conf/acsos/TalluriOVTI21}.
	\end{tcolorbox}

	\begin{center}
		\includegraphics[width=0.9\linewidth]{images/predictive_analytics.pdf}
	\end{center}
	\tiny
	\textbf{Figure 1.2:} Where does our work fit within the field of datacenter digital twinning?
	There are 5 core elements to any Digital Twin: \myCircled{A} The Digital $\rightarrow$ Physical Twin link, \myCircled{B} the Physical Twin (\emph{e.g.,} the datacenter), \myCircled{C} the Physical $\rightarrow$ Digital Twin link, \myCircled{D} the Digital Twin, \myCircled{E} the features necessary to any Digital Twin.
	\textcolor{Green}{\faHighlighter~Highlighted areas are the contributions from this thesis, which include the autonomous actions resulting from predictive insights \myCircledGreen{A} and the predictive analysis itself within \myCircledGreen{E}.}
\end{frame}

\begin{frame}\frametitle{Research Questions}
	\begin{tcolorbox}[title=Main Research Question, colbacktitle=red!70!black,colback=red!20!white]
		How to enable predictive analytics for datacenters through digital twinning?
	\end{tcolorbox}

	\begin{tcolorbox}[title=Research Question 1]
		How to asses the current state-of-the-art of digital twinning for datacenters?
	\end{tcolorbox}

	\begin{tcolorbox}[title=Research Question 2]
		How to design a reference architecture for a predictive datacenter digital twin using discrete-event simulation?
	\end{tcolorbox}

	\begin{tcolorbox}[title=Research Question 3]
		% no "and validate?"
		How to validate and evaluate a datacenter digital twin architecture in relation to system requirements?
	\end{tcolorbox}
\end{frame}

\begin{frame}\frametitle{\textbf{RQ1}: Literature Review I}
	\begin{tcolorbox}[title=Main Finding I]
		The literature on DCDTs is scarce.
		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.
	\end{tcolorbox}
	\vspace{-0.1cm}
	\input{images/table.tex}
	% Research on DTs for datacenters have been separate, siloed efforts focused on either datacenter cooling, network performance, power consumption or visualization efforts.
	% CFD usually means Navier-Stokes equations.
	% CFD models take ages to compute.
\end{frame}

\begin{frame}\frametitle{\textbf{RQ1}: Literature Review II}
	% Mandatory: split the figure into 2: top and bottom, and that way you can fill in the entire slide nicely.

	\begin{tcolorbox}[title=A holistic DCDT system model]
		We propose a generic model of datacenter digital twinning that can be mapped to each system from \textbf{Table 1.1}. Within this model (see \textbf{Fig. 1.3}) we introduce a concept of the \emph{Digital Thread}: a bridge between the DCDT and the physical DC equipment.
	\end{tcolorbox}
	\begin{center}
		\vspace{-0.1cm}
		\includegraphics[width=0.8\textwidth]{images/system_model2.pdf}
	\end{center}
	% The reason why the cooling system is in the graph is because of the fact that 40\% of total energy consumed in DCs comes from cooling~\cite{DBLP:conf/noms/ZhangZLZWC22}.
	% It has come to the point where datacenters are being build in the Pan-Arctic region, such as Finland,Russia,Sweden etc. with Iceland leading in number of DCs https://www.datacentermap.com/iceland/
	% The SmarDC digital twin is purely to get more training data for AI models.
	% Not really a digital twin per se.

	\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.
	% 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
	% Use cases of DT's found by Brewer et al.: augmented reality, forensic analysis and diagnostics, predictive modelling, failure detection, operational optimization, ``what-if''' scenarios and virtual prototyping.
\end{frame}

\begin{frame}\frametitle{\textbf{RQ2}: Reference Architecture}
	% Make Kafka logos clearly defined --> add a legend with icons?
	\hspace{-0.3cm}
	\begin{minipage}[b]{0.45\linewidth}
		\begin{center}
			% Change to Datacenter (Physical Twin)
			\includegraphics[width=1.15\textwidth]{images/ref_architecture.pdf}
		\end{center}
		\vspace{-0.15cm}
		\tiny
		\textbf{Figure 1.4:} The predictive datacenter digital twin reference architecture.
		The architecture was designed with the \emph{AtLarge Design Process}~\cite{DBLP:conf/icdcs/IosupVTETBFMT19}.
		\vspace{0.2cm}
	\end{minipage}
	\hspace{0.6cm}
	\begin{minipage}[b]{0.45\linewidth}
		\begin{center}
			\includegraphics[width=1.17\linewidth]{images/implementation.png}
		\end{center}
		\vspace{-0.2cm}
		\tiny
		\textbf{Figure 1.5:} The prototype 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}.
		\vspace{0.1cm}
	\end{minipage}

	% We decided to use discrete-event simulation, as opposed to computational fluid dynamics because of the high overheads of development time needed for CFD.
	% CFD simply takes too long to run, making it unfeasible for real-time analytics and simulation.
	% Citing ExaDigit: [CFD] they are also more computationally expensive, generally making real-time operation unfeasible.
	% Consider adding this minipage directly to the ``draw.io'' diagram
\end{frame}
% You should skip \hfill completely or in favour of \hspace very minimally.
\begin{frame}\frametitle{\textbf{RQ3}: Experimental Setup I}
	\hspace{-0.3cm}
	\begin{minipage}[b]{0.45\linewidth}
		\begin{tcolorbox}[title=Problem, colbacktitle=red!70!black,colback=red!20!white]
			We cannot just go and test digital twins on large systems, because we do not have large systems at hand.
			Moreover, real-world experimentation is costly and unsustainable in the long run~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}.
		\end{tcolorbox}
		\vspace{0.5cm}
		\begin{tcolorbox}[title=Solution, colbacktitle=Green!70!black, colback=Green!20!white]
			\scriptsize
			They way we test our reference architecture prototype is by using multiple simulators.
			We use an additional OpenDC process to play the role of a real datacenter.
		\end{tcolorbox}
		\vspace{1cm}
	\end{minipage}
	\hspace{0.25cm}
	\begin{minipage}[b]{0.45\linewidth}
		\vspace{-0.2cm}
		\begin{center}
			\includegraphics[width=1.2\linewidth]{images/predictive_analyticsv3.pdf}
		\end{center}
		\tiny
		\vspace{-0.2cm}
		\textbf{Figure 1.6:} The experimental setup.
		Answering \textbf{RQ3} we provide a novel way to evaluate datacenter digital twins through discrete-event simulation.
	\end{minipage}
\end{frame}


\begin{frame}\frametitle{\textbf{RQ3}: Experimental Results I}
	% You have some model, and this can be based on multiple traces.
	%Get insight from CINECA --> you get a probability of certain hosts failing.
	% Anomaly detection --> CINECA, how good their detection is?
	%If you incorporate that? If you can make the case that because of our new digital twin we can incorporate such models, anomaly/failure detection, from CINECA.
	%If we had that in, we can reach these kinds of gains.
	% @Mateusz there is really not a possibility to incorporate CINECA's models, so to address Dante's feedback, I created this experiment.
	% If a single host crashes for the entire workload, that's not really that bad.
	% If a lot of hosts suddenly crash but for a really short time, that's terrible.
	% Failures that are more intensive are worse than failures with long duration.
	\begin{tcolorbox}[title=Main Finding II]
		We posit digital twinning can be used for failure detection to the benefit of DC operators.
		We replicate an experiment from DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} designed by Milojicic \etal to show our system can reliably detect \emph{unexpected} host failures.
	\end{tcolorbox}
	\hspace{-0.2cm}
	\begin{minipage}[b]{0.45\linewidth}
		\begin{center}
			\includegraphics[width=1.1\textwidth]{images/25_Jun_2026_152341.pdf}
		\end{center}
		\vspace{-0.3cm}
		\tiny
		\textbf{Figure 1.7:} Experiment 1a. In this experiment we use red and yellow alarms to notify datacenter operators of unexpected failures.
		We use a threshold based on predictions done by the simulator.
	\end{minipage}
	\hspace{0.6cm}
	\begin{minipage}[b]{0.45\linewidth}
		\begin{center}
			\includegraphics[width=1.1\textwidth]{images/25_Jun_2026_161052.pdf}
		\end{center}
		\vspace{-0.3cm}
		\tiny
		\textbf{Figure 1.8:} Experiment 1b. The mean failure detection rate is around 15\%. Even though this seems low, if we look at \textbf{Fig. 1.9} (see extra slides), this simply means around 15\% of failures are unexpected.
	\end{minipage}
	% Explain what the axis are in the figure caption.
	% Talk about the experimental setup in the figure.
	% Give more reliable results than just numbers -- do statistical testing, i.e., standard deviation, confidence intervals.
\end{frame}

%\begin{frame}\frametitle{\textbf{RQ3}: Experimental Results II}
%	\begin{tcolorbox}[title=Evaluation]
%		Predictive analytics is core to digital twinning. We evaluate our system against the requirements (extra slides) by predicting an optimal scheduling policy.
%		During runtime, we make dynamic adjustments to the physical twin, if the scheduling results differ.
%	\end{tcolorbox}
%	\hspace{0.2cm}
%	\begin{minipage}[b]{0.32\linewidth}
%		\begin{center}
%			\includegraphics[width=1.1\textwidth]{images/23_Jun_2026_102028.pdf}
%		\end{center}
%		\vspace{-0.3cm}
%		\tiny
%		\textbf{Figure 1.9:} Experiment 1
%	\end{minipage}
%\end{frame}

\begin{frame}\frametitle{Key Takeaways}
	\begin{tcolorbox}[title=What is the societal context?]
		Datacenter manageability is a top-priority for the digital society.
		Over 3 million jobs in the Netherlands directly depend on cloud services, which are hosted in datacenters~\cite{DBLP:journals/corr/IosupKLVG22}.
	\end{tcolorbox}

	\begin{tcolorbox}[title=What problem did we solve?]
		DCDT's, still under development, lack crucial features such as predictive analytics to manage datacenters well.
		The entire DCDT design space remains largely unexplored.
	\end{tcolorbox}

	\begin{tcolorbox}[title=How did we solve this problem?]
		Our contributions are: a thorough literature survey with a system model, a DCDT reference architecture, and prototype-based experiments via a novel evaluation method.
	\end{tcolorbox}

	\begin{tcolorbox}[title=What did we find?]
		\emph{Sunfish} can reliably detect unexpected failures based on discrete-event predictions, and can serve as a foundation for additional research and future work.
	\end{tcolorbox}
	% Mandatory to mention here the future work that you see happening.
	% Not enough space for another tcolorbox.
\end{frame}

\setcounter{framenumber}{3}
\setbeamertemplate{footline}[page number]{}


% Unfortunately this must remain here.
\setbeamercolor{frametitle}{fg=Brown,bg=Brown!20}
\setbeamertemplate{frametitle}{
	\vspace*{-0.1cm}
	\begin{beamercolorbox}[wd=\paperwidth, ht=0.75cm, dp=0.3cm,leftskip=10pt, rightskip=10pt]{frametitle}
		\usebeamerfont{frametitle}\insertframetitle\hfill
	\end{beamercolorbox}
}
\begin{frame}[allowframebreaks]\frametitle{Extra Slides: References}
	\tiny
	\bibliographystyle{is-plain}
	\bibliography{main.bib}
\end{frame}

\begin{frame}\frametitle{Technical Setup }
	\begin{tcolorbox}[title=What is the simulation workload?]
		The compute workload is BitBrainsSmall.
		The failure traces include user reports from Gmail, WhatsApp and Twitter.

	\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.

	\end{tcolorbox}


	\begin{tcolorbox}[title=How did we adjust OpenDC (Physical Twin)?]
		We use a SURF~\cite{DBLP:journals/fgcs/VersluisCGLPCUI23} datacenter topology with 277 hosts.
		We wrote a custom Kotlin \texttt{ComputeMonitor} to export live-metrics into Kafka, and a custom Kotlin \texttt{HTTPClient} to talk to the digital twin.
		We add a new scheduling mechanism, the \texttt{SmartScheduler}.

	\end{tcolorbox}
	\begin{tcolorbox}[title=Which metrics do we measure?]
		Timestamps, host names, uptime, downtime, CPU utilization \emph{etc.}
	\end{tcolorbox}

\end{frame}


\begin{frame}\frametitle{Extra Slides: Why Digital Twinning?}
	\begin{tcolorbox}[title=Definition]
		A DCDT mirrors the structure, context and behaviour of a datacenter~\cite{DBLP:journals/computer/AthavaleBBMMPS24}. The prerequisite to any digital twin is good monitoring and sensing capabilities in the physical entity.
		Datacenters meet this requirement easily because they already connect hundreds of monitoring sensors. 	\end{tcolorbox}

	\begin{center}
		\includegraphics[height=10em]{images/dt_timeline.pdf}
	\end{center}
	\tiny

	\textbf{Figure E.2:} Due to insufficient technological foundations,
	little work is available on DTs between 2003 and 2018, and it is only with the rapid growth
	of cloud computing, Internet-of-Things and Big Data analytics that DTs have reemerged~\cite{DBLP:conf/cirp/TAO2018169}.
	That is why nobody used digital twins to mirror datacenters earlier.
\end{frame}

\begin{frame}\frametitle{Extra Slides: Why not pure simulation?}
	\begin{tcolorbox}[title=Predicting job failures]
		Preventing failure-caused outages in advance
		can reduce huge operational costs, as over 20\% of all reported outages amount to more than 1 million
		US\$~\cite{DBLP:report/AnnualOutageAnalysis2025}.
		Only a constant bi-directional interaction (digital twin $\iff$ physical entity) can achieve this.
	\end{tcolorbox}
	\begin{center}
		\includegraphics[height=10em]{images/digital_twin_ms.pdf}
	\end{center}
	\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}




% 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}