From a615b61e97511ba656d6ef154141083fa2ce9a61 Mon Sep 17 00:00:00 2001 From: mjkwiatkowski Date: Wed, 15 Jul 2026 13:35:47 +0200 Subject: feat: fixed the comments from Dante about section 2.2 --- appendix/glossary.tex | 7 +++ citations/CondorPractice1984.pdf | Bin 0 -> 559583 bytes citations/CondorScheduler1968.pdf | Bin 0 -> 597202 bytes content/background.tex | 64 +++++++++++++++++++++------- images/datacenter.jpg | Bin 0 -> 529581 bytes images/system_model.png | Bin 0 -> 809267 bytes images/thesis_structure.png | Bin 507885 -> 489827 bytes main.bib | 41 ++++++++++++++++++ notes/.~lock.Full_Document_Annot_Dante.pdf# | 2 +- notes/Full_Document_Annot_Dante.pdf | Bin 8813011 -> 9356311 bytes sources/dt_features_comparison.tex | 5 +-- sources/thesis_structure.drawio | 2 +- 12 files changed, 100 insertions(+), 21 deletions(-) create mode 100644 citations/CondorPractice1984.pdf create mode 100644 citations/CondorScheduler1968.pdf create mode 100644 images/datacenter.jpg create mode 100644 images/system_model.png diff --git a/appendix/glossary.tex b/appendix/glossary.tex index a46f42a..ac4548c 100644 --- a/appendix/glossary.tex +++ b/appendix/glossary.tex @@ -30,3 +30,10 @@ \newacronym{gui}{GUI}{Graphical User Interface} \newacronym{tui}{TUI}{Terminal User Interface} \newacronym{nasa}{NASA}{National Aeronautics and Space Agency} +\newacronym{cpu}{CPU}{Central Processing Unit} +\newacronym{ram}{RAM}{Random Access Memory} +\newacronym{gpu}{GPU}{Graphics Processing Unit} +\newacronym{npu}{NPU}{Neural Processing Unit} +\newacronym{tpu}{TPU}{Tensor Processing Unit} +\newacronym{cern}{CERN}{Conseil Europ\'een pour la Recherche Nucl\'eaire} +\newacronym{it}{IT}{Information Technology} diff --git a/citations/CondorPractice1984.pdf b/citations/CondorPractice1984.pdf new file mode 100644 index 0000000..401fe21 Binary files /dev/null and b/citations/CondorPractice1984.pdf differ diff --git a/citations/CondorScheduler1968.pdf b/citations/CondorScheduler1968.pdf new file mode 100644 index 0000000..c247e10 Binary files /dev/null and b/citations/CondorScheduler1968.pdf differ diff --git a/content/background.tex b/content/background.tex index 5ab53dc..8349bcf 100644 --- a/content/background.tex +++ b/content/background.tex @@ -4,33 +4,66 @@ The contribution in this chapter is three-fold: \begin{enumerate}[label=\emph{C\textsubscript{\arabic*}}, itemsep=0.2pt] - \item We provide a brief overview on datacenter simulation (\Cref{sss:simulation}), compute failures (\Cref{sss:failures}), and digital twinning (\Cref{sss:what_is_digital_twinning}). - \item We survey the state-of-the-art concerning datacenter digital twinning (\Cref{ss:digital_twins_for_datacenters}). + \item We provide a brief overview on datacenters (\Cref{ss:datacenters}) datacenter simulation (\Cref{sss:simulation}), compute failures (\Cref{sss:failures}), and digital twinning (\Cref{ss:digital-twinning}). + \item We survey the state-of-the-art concerning datacenter digital twinning (\Cref{sss:advanced_dts}). \item We construct a system model for existing datacenter digital twins (\Cref{ss:system_model_for_dcdts}) \end{enumerate} \end{mynote} \section{Datacenters}\label{ss:datacenters} -In this section we provide a short background on datacenter simulation and compute failures. -We find it useful to provide a brief introduction to both topics so as to ensure reader's fullest understanding of subsequent chapters. -Since datacenters are important building blocks of the digital society, reliable warehouse management is a key priority for datacenter operators. -Incorrect management decisions can lead to missed \gls{sla}s~\cite{DBLP:journals/corr/IosupKLVG22} and even large financial penalties~\cite{DBLP:report/AnnualOutageAnalysis2025}. -However, efficient and timely management is a difficult challenge, because datacenters are extremely complex facilities. -To help datacenter operators, the scientific community proposes to simulate datacenters to make more informed decisions. +In this section we provide a short background on datacenters, datacenter simulation and compute failures. +We find it useful to provide a brief introduction to these topics so as to ensure reader's fullest understanding of subsequent chapters. +%What are the parts of a data center? + +A datacenter is ``a physical room, building, or facility for the purpose of the storage, management, and dissemination of data and information, including training artificial intelligence, housing IT infrastructure, computer systems, and associated components.''~\cite{Wikipedia:article/Datacenter}. +In essence, datacenters contain a large amount servers, and everything that is needed to maintain them. +Most often servers are specially-designed motherboards with a (multicore) \gls{cpu}, \gls{ram} and storage. +More diverse servers include a \gls{cpu}, \gls{tpu}, or \gls{npu}. +To efficiently organize the datacenter, servers are placed within server \emph{racks}. +To maintain a large number of server racks, datacenters contain a cooling system to control the heat transfer and temperature of both the hardware and the entire facility. +Additionally, datacenters consume vast amounts of electricity~\cite{Wikipedia:article/Datacenter}. +Because of this, the datacenter power supply play a critical role in keeping the services running on the servers always available. +An example datacenter in \gls{cern}, is depicted on \Cref{fig:datacenter}. + +\begin{figure}[t] + \centering + \includegraphics[width=0.9\linewidth]{images/datacenter.jpg} + \caption[Datacenter in CERN.]{Example of a datacenter in \gls{cern}, Switzerland (2010)~\cite{Wikipedia:article/Datacenter}. In the figure we can see servers within servers racks, and the network cables.} + \label{fig:datacenter} +\end{figure} + +%Who are the stakeholders? +Datacenters form the backbone of the digital society. +The main stakeholders, besides the companies in the \gls{it} sector, are intelligent healthcare, remote work, online gaming, digital government and education, banking and finance, transport and logistics~\cite{DBLP:journals/corr/IosupKLVG22}. +All of the above industries need reliable datacenters to work well in the 21\textsuperscript{st} century. + +%Where does the actual complexity come from? +The high demand for online services drives datacenter complexity. +Moreover, due to the Jevon's paradox of Computer Systems~\cite{Wikipedia:article/JevonsParadox}, improved availability increases the demand. +As a result, datacenters contain hundreds, or even thousands of hardware components. +Every device may have a different vendor, new configuration, unusual interface \etc +Because of this, datacenter operators are often faced with difficult operational and architectural challenges~\cite{Wiley:book/Condor2005,DBLP:conf/ccgrid/MastenbroekAJLB21}, which span software and performance engineering. +Making sure that all the parts of the datacenter work together is a tough task. +What drives datacenter complexity even further is that sophisticated systems are not merely a sum of their parts~\cite{Wikipedia:article/Systems_Thinking}. +The combination of the above factors makes datacenter management a difficult, non-trivial challenge. \subsection{Datacenter Simulation}\label{sss:simulation} \input{sources/simulator_comparison.tex} + +Efficient and timely datacenter management is a difficult challenge, because datacenters are extremely complex facilities. +They require deep understanding to operate properly. +However, running real-world experiments is costly in both time and resources. +Additionally, experimentation \emph{in situ} is unsustainable and difficult to reproduce. +Alternatives to real-world experiments include simulation and mathematical analysis. +Because mathematical analysis is not scalable to modern datacenters~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}, in this project we only consider simulation as a foundation for the \gls{dcdt}. +%To help datacenter operators, the scientific community proposes to simulate datacenters to make more informed decisions. + Simulation empowers better design, testing and management of datacenters~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. A well-designed datacenter simulator can estimate a months-long workload in a few minutes or hours. To simulate is to ``imitate of real-world process or system over time, enabling the study of, and experimentation with the internal interactions of complex systems''~\cite{DBLP:books/daglib/0034857} In this project we only consider \emph{discrete-event simulation}. - Discrete-event simulation represents system operations as a sequence of events over time, with an assumption that no changes occur between the events. Due to the scale and complexity of datacenters, most simulators use discrete-event simulation~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. - -Alternatives to simulation include real-world experimentation and mathematical analysis. -However, experimentation \emph{in situ} is unsustainable, expensive and difficult to reproduce and mathematical analysis is not scalable to modern datacenters~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. -Therefore, in this project we only consider simulation as a foundation for the \gls{dcdt}. There exist many datacenter simulation tools, for example DGSim~\cite{DBLP:conf/europar/IosupSE08}, CloudSim~\cite{DBLP:journals/spe/CalheirosRBRB11}, SimGrid~\cite{DBLP:journals/corr/CasanovaGLQS13}, iCanCloud~\cite{DBLP:journals/grid/NunezVCCCL12}, GroudSim~\cite{DBLP:conf/europar/OstermannPPF10} and OpenDC~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. See \Cref{tab:datacenter_simulator_comparison} for a comparison of selected datacenter simulators, combined by Mastenbroek \etal~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. In order to narrow the scope of the project, we only consider {OpenDC} as a simulator for the digital twin design. @@ -54,11 +87,10 @@ A failure model consists of two statistical distributions: \item to model service unavailability \item to model service availability. \end{enumerate*} -A failure trace is defined by an interval, duration, and intensity of several failures, which are later looped throughout the simulated workload (source \url{opendc.org}). +A failure trace is defined by an interval, duration, and intensity of several failures, which are later looped throughout the simulated workload~\cite{GitHub:software/OpenDC}. In summary OpenDC enables experimentation with failures that enables insights that are not provided by other state-of-the-art software. However, the fidelity of failure modeling inside a datacenter simulation is still insufficient to predict in failures in real-time, as they happen in a physical datacenter. Since a datacenter simulator is quite different from a digital twin, we cannot use the same computation methods from simulation to predict real-time failures. -Digital twinning is an improvement upon pure simulation. \begin{figure}[t] \centering \includegraphics[width=0.95\linewidth]{images/five_dimensional_dt.pdf} @@ -225,7 +257,7 @@ Kalibre takes the best of both \gls{ml} and \gls{cfd} approaches and achieves su \begin{figure}[t] \centering - \includegraphics[width=0.95\linewidth]{images/system_model.pdf} + \includegraphics[width=0.95\linewidth]{images/system_model.png} \caption[A system model for datacenter digital twins.]{A generic system model for datacenter digital twin deployments. The design of DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} indirectly incorporates in its architecture a ``virtual-to-virtual`` digital thread between different digital twins. Zhao \etal likewise present key elements to the digital thread in their architecture~\cite{DBLP:conf/AppliedEnergy/Zhao20}. We add the \emph{Digital Thread} to our model explicitly.} diff --git a/images/datacenter.jpg b/images/datacenter.jpg new file mode 100644 index 0000000..28c7acd Binary files /dev/null and b/images/datacenter.jpg differ diff --git a/images/system_model.png b/images/system_model.png new file mode 100644 index 0000000..5bb4d8e Binary files /dev/null and b/images/system_model.png differ diff --git a/images/thesis_structure.png b/images/thesis_structure.png index e64a64d..fce3ccc 100644 Binary files a/images/thesis_structure.png and b/images/thesis_structure.png differ diff --git a/main.bib b/main.bib index 185d3d2..d141a51 100644 --- a/main.bib +++ b/main.bib @@ -1150,3 +1150,44 @@ note = {This RIS citation comes from \url{ https://www.nature.com/articles/s41598-026-45272-z#citeas}.}, } + +@misc{Wikipedia:article/Datacenter, + author = "{Wikipedia contributors}", + title = "Data center --- {Wikipedia}{,} The Free Encyclopedia", + year = "2026", + howpublished = "\url{ + https://en.wikipedia.org/w/index.php?title=Data_center&oldid=1364097634 + }", + note = "This BibTeX citation comes from \url{ + https://en.wikipedia.org/w/index.php?title=Special:CiteThisPage&page=Data_center&id=1364097634&wpFormIdentifier=titleform#BibTeX_entry + }", +} + +@article{Wiley:book/Condor2005, + author = {Thain, Douglas and Tannenbaum, Todd and Livny, Miron}, + title = {Distributed computing in practice: the Condor experience}, + journal = {Concurrency and Computation: Practice and Experience}, + volume = {17}, + number = {2-4}, + pages = {323-356}, + keywords = {Condor, Grid, history, community, planning, scheduling, + split execution}, + doi = {https://doi.org/10.1002/cpe.938}, + url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.938}, + eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.938}, + year = {2005}, + note = {This BibTeX citation comes from \url{ + https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.938}}, +} + +@misc{Wikipedia:article/JevonsParadox, + author = "{Wikipedia contributors}", + title = "Jevons paradox --- {Wikipedia}{,} The Free Encyclopedia", + year = "2026", + howpublished = "\url{ + https://en.wikipedia.org/w/index.php?title=Jevons_paradox&oldid=1363548499 + }", + note = "This BibTeX citation comes from \url{ + https://en.wikipedia.org/w/index.php?title=Special:CiteThisPage&page=Jevons_paradox&id=1363548499&wpFormIdentifier=titleform#BibTeX_entry + }", +} diff --git a/notes/.~lock.Full_Document_Annot_Dante.pdf# b/notes/.~lock.Full_Document_Annot_Dante.pdf# index 4f00f34..2eab09f 100644 --- a/notes/.~lock.Full_Document_Annot_Dante.pdf# +++ b/notes/.~lock.Full_Document_Annot_Dante.pdf# @@ -1 +1 @@ -,matt,frame,14.07.2026 13:21,/home/matt/.local/share/onlyoffice; \ No newline at end of file +,matt,frame,15.07.2026 11:20,/home/matt/.local/share/onlyoffice; \ No newline at end of file diff --git a/notes/Full_Document_Annot_Dante.pdf b/notes/Full_Document_Annot_Dante.pdf index 20e68d4..ebaeb90 100644 Binary files a/notes/Full_Document_Annot_Dante.pdf and b/notes/Full_Document_Annot_Dante.pdf differ diff --git a/sources/dt_features_comparison.tex b/sources/dt_features_comparison.tex index ee849c8..b9f3110 100644 --- a/sources/dt_features_comparison.tex +++ b/sources/dt_features_comparison.tex @@ -10,7 +10,7 @@ \midrule DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} & Gaussian Process Regression, AI/ML & Anomaly Detection & Cloud Datacenter Operators & A\textsuperscript{$\star$}, FD, VP\textsuperscript{$\star$}, SE\textsuperscript{$\dagger$} \\ \midrule - ChatTwin~\cite{DBLP:conf/sensys/LiW0Z0T23} & \textbf{\Large \sffamily?} & Digital Twin\newline Definition Language & Cloud Datacenter Engineers & { 3D\textsuperscript{$\star$}} \\ + ChatTwin~\cite{DBLP:conf/sensys/LiW0Z0T23} & \textbf{Unknown} & Digital Twin\newline Definition Language & Cloud Datacenter Engineers & { 3D\textsuperscript{$\star$}} \\ \midrule Reducio~\cite{DBLP:conf/sensys/CaoW0022} & POD, Gaussian\newline Process Modelling (ML) & {Heat Modelling} & Edge and Hyper-scale Datacenter Operators & {CH\textsuperscript{$\ddagger$}, 3D\textsuperscript{$\star$}}, SE \\ \midrule @@ -21,8 +21,7 @@ \bottomrule \end{tabular} } - \caption[Comparison of selected datacenter digital twins.]{Comparison of selected datacenter digital twins. \textbf{Modelling capability:} {3D = Visualizations}; {CH = Cooling/Heat}, PE = Power/Energy Consumption, A = Anomaly Detection, N = Network Modelling, SE = Scenario Exploration, VP = Virtual Prototyping, FD = Federation, RA = Resource Allocation; \textbf{Data Analytics}: $\ddagger$ = Predictive Analysis; $\star$ = Descriptive Analysis, $\dagger$ = Prescriptive Analysis.} - \label{tab:dt_features_comparison} + \caption[Comparison of selected datacenter digital twins.]{Comparison of selected datacenter digital twins. \textbf{Modelling capability:} {3D = Visualizations}; {CH = Cooling/Heat}, PE = Power/Energy Consumption, A = Anomaly Detection, N = Network Modelling, SE = Scenario Exploration, VP = Virtual Prototyping, FD = Federation, RA = Resource Allocation; \textbf{Data Analytics}: $\ddagger$ = Predictive Analysis; $\star$ = Descriptive Analysis, $\dagger$ = Prescriptive Analysis. \textbf{Unknown}: Information is Not Available/Not Published.} \label{tab:dt_features_comparison} \end{table} % Autonomous decisions (autonomous twinning) from~\cite{DBLP:conf/sc/BrewerMKWBHSGGW24} is inherent to digital twinning -- it is better left unsaid in the table. % I.e., the foundation of any DT is autonomous decisions, so without them they don't qualify as a DT. diff --git a/sources/thesis_structure.drawio b/sources/thesis_structure.drawio index 670dc70..18814ac 100644 --- a/sources/thesis_structure.drawio +++ b/sources/thesis_structure.drawio @@ -87,7 +87,7 @@ - + -- cgit v1.2.3