diff options
| -rw-r--r-- | citations/LiBUILDSYS2023.pdf (renamed from citations2/iteration1/acm/3600100.3623719.pdf) | bin | 3047370 -> 3047370 bytes | |||
| -rw-r--r-- | content/background.tex | 4 | ||||
| -rw-r--r-- | main.bib | 19 | ||||
| -rw-r--r-- | notes/meetin2.txt | 6 | ||||
| -rw-r--r-- | sources/dt_features_comparison.tex | 38 |
5 files changed, 48 insertions, 19 deletions
diff --git a/citations2/iteration1/acm/3600100.3623719.pdf b/citations/LiBUILDSYS2023.pdf Binary files differindex a442e3d..a442e3d 100644 --- a/citations2/iteration1/acm/3600100.3623719.pdf +++ b/citations/LiBUILDSYS2023.pdf diff --git a/content/background.tex b/content/background.tex index fc1fce7..4218380 100644 --- a/content/background.tex +++ b/content/background.tex @@ -47,6 +47,10 @@ The digital twin is designed to provide extra datasets for training \gls{ai} mod DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} is an adaptive digital twin with visualization and anomaly detection features. +% What is more, Microsoft already offers digital twinning as a service https://azure.microsoft.com/en-us/products/digital-twins/ +% Documentation: https://learn.microsoft.com/en-us/azure/digital-twins/ +% Moreover, NVIDIA is doing too as well https://www.nvidia.com/en-sg/omniverse/ + Predictive modelling uses statistics to predict outcomes. When deployed commercially, for example in datacenters, predictive modelling is often referred to as predictive analytics~\cite{Wikipedia:PredictiveModelling}. Almost any statistical model can be used for prediction purposes, but nowadays predictive analysis is synonymous with machine learning. @@ -554,3 +554,22 @@ biburl = {https://dblp.org/rec/conf/sc/TaheriBPRHDEWPM24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org}, } + +@inproceedings{DBLP:conf/sensys/LiW0Z0T23, + author = {Minghao Li and Ruihang Wang and Xin Zhou and Zhaomeng Zhu and + Yonggang Wen and Rui Tan}, + title = {ChatTwin: Toward Automated Digital Twin Generation for Data + Center via Large Language Models}, + booktitle = {Proceedings of the 10th {ACM} International Conference on + Systems for Energy-Efficient Buildings, Cities, and + Transportation, BuildSys 2023, Istanbul, Turkey, November + 15-16, 2023}, + pages = {208--211}, + publisher = {{ACM}}, + year = {2023}, + url = {https://doi.org/10.1145/3600100.3623719}, + doi = {10.1145/3600100.3623719}, + timestamp = {Tue, 13 May 2025 13:47:03 +0200}, + biburl = {https://dblp.org/rec/conf/sensys/LiW0Z0T23.bib}, + bibsource = {dblp computer science bibliography, https://dblp.org}, +} diff --git a/notes/meetin2.txt b/notes/meetin2.txt new file mode 100644 index 0000000..6ed2515 --- /dev/null +++ b/notes/meetin2.txt @@ -0,0 +1,6 @@ +Servo paper: this is the kind of system model you have to do. +A reference architecture. +The design is more specific than the reference architecture. +The contribution of RQ1 should be a system model. +The abstraction level goes: system model/reference architecture -> system design -> prototype implementation +There is also taxonomy: Procedural Content Generation for Games -> taxonomy of different types of content. diff --git a/sources/dt_features_comparison.tex b/sources/dt_features_comparison.tex index be53e13..2bc3305 100644 --- a/sources/dt_features_comparison.tex +++ b/sources/dt_features_comparison.tex @@ -1,26 +1,26 @@ \begin{table}[t] \centering \renewcommand{\arraystretch}{1.4} - \begin{tabular}{m{0.4\linewidth}cccc} + \begin{tabular}{m{0.4\linewidth}ccccc} \toprule - Feature & ExaDigiT~\cite{DBLP:conf/sc/BrewerMKWBHSGGW24} & SmartDC~\cite{DBLP:conf/noms/ZhangZLZWC22} & DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} \\ - \midrule - Virtual Prototyping & & \ding{51} & \\ - Scenario Exploration & & & \\ - 3D Facility Modelling & \ding{51} & \ding{51} & \\ - Predictive maintenance & & & \\ - Predictive energy modelling & & \ding{51} & \\ - Reliability and availability modeling & & & \\ - Cooling system modelling & & \ding{51} & \\ - Network modelling & & & \\ - Predictive modelling & & & \\ - Power/Energy consumption optimization (PUE) & & \ding{51} & \\ - Heat and Airflow distribution modelling & & \ding{51} & \\ - Visual analytics dashboard & & & \\ - Forensic analysis and diagnostics & & & \\ - Failure detection & & & \\ - Operational optimization & & & \\ - Resource allocation & & & \\ + Feature & ExaDigiT~\cite{DBLP:conf/sc/BrewerMKWBHSGGW24} & SmartDC~\cite{DBLP:conf/noms/ZhangZLZWC22} & DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} & ChatTwin~\cite{DBLP:conf/sensys/LiW0Z0T23}\\ + \midrule + Virtual Prototyping & & \ding{51} & &\\ + Scenario Exploration & & & &\\ + 3D Facility Modelling & \ding{51} & \ding{51} & &\\ + Predictive maintenance & & & &\\ + Predictive energy modelling & & \ding{51} & &\\ + Reliability and availability modeling & & & &\\ + Cooling system modelling & & \ding{51} & &\\ + Network modelling & & & &\\ + Predictive modelling & & & &\\ + Power/Energy consumption optimization (PUE) & & \ding{51} & &\\ + Heat and Airflow distribution modelling & & \ding{51} & &\\ + Visual analytics dashboard & & & &\\ + Forensic analysis and diagnostics & & & &\\ + Failure detection & & & &\\ + Operational optimization & & & &\\ + Resource allocation & & & &\\ \midrule \end{tabular} \caption{Comparison of selected features of existing datacenter digital twins.} |