diff options
Diffstat (limited to 'content/background.tex')
| -rw-r--r-- | content/background.tex | 60 |
1 files changed, 22 insertions, 38 deletions
diff --git a/content/background.tex b/content/background.tex index e65dc17..55cfe16 100644 --- a/content/background.tex +++ b/content/background.tex @@ -13,22 +13,6 @@ A prime example of using probability to find a good machine learning model is Ba % Stanford Encyclopedia of Philosophy, Douven 2017 The process of inference from data to provide the best explanation is called abduction. - - -A \gls{dt} is a digital model of an intended or actual real-world system that serves as a digital counterpart of it for purposes such as simulation, integration, testing, monitoring and maintenance %cite the Wikipedia page here!. -The system requires real-time synchronization with the actual system. -A closed loop of continuous feedback exists between the digital twin and physical object. - -The digital twin replicates the physical system to predict failures and opportunities for changing, to prescribe real-time actions for optimizing and/or mitigating unexpected events, observing and evaluating the profile of the system. - -A digital twin is often called a virtual twin. - -The communication between a physical entity and the digital twin is referred to as a digital thread. - -One key application is predictive maintenance, where the digital twin analyzes operational data (e.g., temperature, vibration) to predict when a component is likely to fail. - -This allows maintenance to be scheduled proactively, reducing unplanned downtime and preventing catastrophic failures. - %Include something about data-preprocessing in the pipeline. %See the article by Fei Tao @@ -41,14 +25,7 @@ ODA can predict failures, help maintain the equipment, save bills, cut costs. But currently one of the key challenges is to somehow connect the physical and virtual spaces. The answer to how to do this is a digital twin. -Since DT's are relatively a new concept, I think they require a short introduction to their history. -It's enough to mention that the first presentation was done by Grieves in 2003, from 2003 to 2018 we have seen a slow incline in numbers of papers (around 50) and now DT's are re-emerging. - -You must include the DT white paper from 2014. -The concept of a \gls{dt} dates back to 2003, when Dr. Michael Grieves of Dassault Syst\'emes introduced the 3 core components of a \gls{dt}: the virtual entity, physical entity and the two-way connection (see Figure \ref{fig:five_dimensional_dt}). -Due to insufficient technological foundations, little work is available on \gls{dt}s between 2003 and 2018~\cite{DBLP:conf/cirp/TAO2018169}, and it is only with the rapid growth of cloud computing, \gls{iot} and big data analytics that \gls{dt}s have re-emerged. -Today, research is focused on bridging the gap between the long-established foundations of \gls{dt}s and new, novel applications in academia and industry, such as the \gls{dcdt}. %[citation needed] As of 2026, there is a lack of consensus of what is a digital twin. @@ -56,23 +33,30 @@ By proxy, there is neither consensus on what is the definition of a datacenter d A generic definition is needed. -Most of \gls{dt} usages are related to prognostics and health management. - - -One of the many applications of \gls{dt} is timely system maintenance. -In aerospace engineering, the \gls{dt} can reliably manage the health of the physical entity by detecting \eg fatigue cracks on aircraft wings or damage to the wind turbine blades~\cite{DBLP:conf/cirp/TAO2018169}. -A forecast of future maintenance and virtual health management are the prime purpose of many \gls{dt}s~\cite{DBLP:conf/AIAA/Teugel2012}. - -Optimal datacenter management is characterized by high service availability and low downtime. -However, achieving this in a 21\textsuperscript{st} century datacenter requires revolutionary changes in the way datacenters are operated and maintained. -A concept that creates just such a revolutionary change is the \gls{dcdt}. -% This sentence is stolen from an article. -% Make sure to paraphrase it. - -% This is stolen from the AIAA article. -% Make sure to paraphrase this. +%Why predictive analytics? Why predictive behaviour? +%What is below here is true, but nonetheless the argumentation should be slightly changed. And a citation is needed. +However, there has been little effor made to integrate analytics that enable consistent and relaible prediction of datacenter behaviour into a holistic digital twin of a datacenter. +Nor has the fidelity of failure modeling inside a datacenter simulation increased. +The failure model is still a linear model. +% Since a datacenter simulator is quite different from a digital twin, we cannot use the same computation methods (not as they are right now, at least) -- we must adapt them. +The prediciton models are the same ones for the digital twin as the ones used for the datacenter simulator. +Since a digital twin is not a standalone simulator, a change to how we both predict and model failures is necessary. +The longer the DT is working, the more accurate its predictions. +All the results are aggregated. +% Why has not anyone done this before? +It is also the case that currently this is possible only and only because of the recent development in High Performance Computing. +Between 2003 and 2011 the compute needed to run a Digital Twin was simply not there. +As such, while the concept existed, the hardware did not catch up yet. +However, in the last decade, multicore computing paradigms and the advent of GPU computing has finally enabled computation needed to run a Digital Twin. +This is what has changed, so that today running a digital twin is relevant, much more relevant than it was 10 years ago. +This is also why nobody has done a Digital Twin of a datacenter before. +The current widespread availability of HPC makes this possible. +Because of judgement born out of experience, evolution of existing datacenters is fairly successful; however the development of a new, modern datacenters is fraught with unexpected problems that results in weight growth, schedule delays and cost overruns. +Optimal datacenter management is characterized by high service availability and low downtime. +Achieving this in a 21\textsuperscript{st} century datacenter requires revolutionary changes in the way datacenters are operated and maintained. +A concept that creates just such a revolutionary change is the \gls{dcdt}. |