feat: changed experiment I to be something completely different

1 files changed, 41 insertions, 21 deletions

diff --git a/main.tex b/main.tex
index 051d295..5d3dfec 100644
--- a/main.tex
+++ b/main.tex
@@ -73,8 +73,10 @@
 
 	\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}. To answer \textbf{RQ2}, we design a ref. arch. for \emph{Operations Model}.
+		We introduce the \emph{Digital Thread}: a bridge between software and reality.
 	\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}.
@@ -103,48 +105,66 @@
 		\end{center}
 		\vspace{-0.2cm}
 		\tiny
-		\textbf{Figure 1.4:} The predictive datacenter digital twin architecture. 	\end{minipage}
+		\textbf{Figure 1.4:} The predictive datacenter digital twin reference architecture. 	\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}
+	% 			The software stack of \emph{Sunfish} includes state-of-the-art software.
+	%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}.
+
 	\begin{minipage}[b]{0.45\linewidth}
-		\begin{center}
-			\includegraphics[width=1.2\linewidth]{images/predictive_analyticsv2.pdf}
-		\end{center}
-		\vspace{-0.3cm}
-		\tiny
-		\textbf{Figure 1.5:} Evaluating DCDTs is difficult. To answer \textbf{RQ3} we provide a novel way to evaluate datacenter digital twins through discrete-event simulation.
+		\begin{tcolorbox}[title=Setup Recipe]
+			\scriptsize
+			\textbf{Step 1.} Ensure Redis and PostgreSQL servers are up and alive.\newline
+
+			\textbf{Step 2.} Run a Confluent Kafka setup: Kafka Connect, Schema Registry and a Kafka server.\newline
+
+			\textbf{Step 3.} Start the Python HTTP Server, and the Python Redis Monitor.\newline
+
+			\textbf{Step 4.} Run the (modified) OpenDC (physical twin) with example experiment.\newline
+
+			\textbf{Step 5.} \emph{Sunfish} will automatically start a second OpenDC instance, and start the data analysis.
+		\end{tcolorbox}
+		\vspace{0.5cm}
 	\end{minipage}
-	\hfill
+	\hspace{0.35cm}
 	\begin{minipage}[b]{0.45\linewidth}
+		\vspace{-0.2cm}
 		\begin{center}
-			\includegraphics[width=0.7\linewidth]{images/scrs.jpg}
+			\includegraphics[width=1.2\linewidth]{images/predictive_analyticsv2.pdf}
 		\end{center}
-		\vspace{-0.2cm}
 		\tiny
-		\textbf{Figure 1.6:} The software stack used to implement \emph{Sunfish}.
-		The time-series data flows initially to the \texttt{Grafana} dashboard, \texttt{PostgreSQL} database and \texttt{Redis} cache, as suggested in~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24}.
+		\vspace{-0.4cm}
+		\textbf{Figure 1.5:} We can't just go and test digital twins on large systems as large systems often aren't at hand.
+		Answering \textbf{RQ3} we provide a novel way to evaluate datacenter digital twins through discrete-event simulation instead.
 	\end{minipage}
 \end{frame}
 
 \begin{frame}\frametitle{\textbf{RQ3}: Experimental Results I}
-	\begin{tcolorbox}[title=Main Finding I]
-		On average, \emph{Sunfish} achieves 12.17\% less failures per task than baseline (OpenDC).
-		Insights from predictive digital twinning yield noticeable performance difference.
+	% 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.
+
+	\begin{tcolorbox}[title=Failure Detection: Main Finding I]
+		On average, \emph{Sunfish} can detect 14.5\% of unexpected failures in the physical twin.
+		We show, that digital twinning \emph{can} be used for failure detection.
+
 	\end{tcolorbox}
 	\begin{minipage}[b]{0.45\linewidth}
 		\begin{center}
-			\includegraphics[width=1.1\textwidth]{images/18_Jun_2026_201008.pdf}
+			\includegraphics[width=1.1\textwidth]{images/23_Jun_2026_102028.pdf}
 		\end{center}
 		\vspace{-0.3cm}
 		\tiny
-		\textbf{Figure 1.5:} Experiment 1 -- on the \emph{x}-axis are different community failure traces.
-		On the \emph{y}-axis is the mean number of times a task has failed, during the entire workload.
-		Vertical bars is standard deviation, measured over 5 repetitions.
+		\textbf{Figure 1.5:} Experiment 1 Setup: The Digital Twin estimates the failures based on the Normal Distribution \emph{N\textasciitilde($\mu$,$\sigma$)} with $\mu = 1.5$ and $\sigma = 0.5$.
+		``Real'' OpenDC failures come from a WhatsApp user reports.
 	\end{minipage}
 	% Explain what the axis are in the figure caption.
 	% Talk about the experimental setup in the figure.
@@ -153,7 +173,7 @@
 
 
 \begin{frame}\frametitle{\textbf{RQ3}: Experimental Results II}
-	\begin{tcolorbox}[title=Main Finding II]
+	\begin{tcolorbox}[title=Failure Prediction: Main Finding II]
 		Here explain what did you find.
 	\end{tcolorbox}