Merge work

This commit is contained in:
Loic Guegan 2019-07-19 10:52:09 +02:00
commit 218849f7fb
4 changed files with 78 additions and 17 deletions

View file

@ -169,4 +169,13 @@ A.~Shehabi, S.~Smith, D.~Sartor, R.~Brown, M.~Herrlin, J.~Koomey, E.~Masanet,
\url{http://www.osti.gov/servlets/purl/1372902/}
\BIBentrySTDinterwordspacing
\bibitem{Hassidim2013}
A.~{Hassidim}, D.~{Raz}, M.~{Segalov}, and A.~{Shaqed}, ``{Network utilization:
The flow view},'' in \emph{IEEE INFOCOM}, 2013, pp. 1429--1437.
\bibitem{Zhang2016}
Z.~{Zhang}, Y.~{Bejerano}, and S.~{Antonakopoulos}, ``{Energy-Efficient IP Core
Network Configuration Under General Traffic Demands},'' \emph{IEEE/ACM
Transactions on Networking}, vol.~24, no.~2, pp. 745--758, 2016.
\end{thebibliography}

View file

@ -470,7 +470,7 @@ In our case with small and sporadic network traffic, these results show that wit
** Cloud Energy Consumption
In this end-to-end energy consumption study, cloud accounts for a huge part of the overall energy
consumption. According a report \cite{shehabi_united_2016-1} on United States data center energy
consumption. According a report \cite{shehabi_united_2016-1} On United States data center energy
usage, the average Power Usage Effectiveness (PUE) of an hyper-scale data center is 1.2. Thus, in
our analysis, all energy measurement on cloud server will account
for this PUE. It means that the power consumption of the server is multiplied by
@ -493,7 +493,7 @@ In our case with small and sporadic network traffic, these results show that wit
\begin{figure}
\centering
\includegraphics[width=0.8\linewidth]{./plots/vmSize-cloud.png}
\caption{Server power consumption using 20 sensors sending data every 10s for various VM memory sizes}
\caption{Server power consumption multiplied by the PUE (= 1.2) using 20 sensors sending data every 10s for various VM memory sizes}
\label{fig:vmSize}
\end{figure}
#+END_EXPORT
@ -508,24 +508,26 @@ In our case with small and sporadic network traffic, these results show that wit
consumption is high (around 97 Watts), it is more
energy efficient to maximize the number of sensors per server. As shown on Figure
\ref{fig:sensorsNumber-WPS}, a significant amount of energy can be save when passing from 20 to
300 sensors per VM. Note that these measurements are the row
measurements taken from the wattmeters: they do not include the PUE
and are not shared among all the VMs that could be hosted on this
server.
300 sensors per VM. Note that these measurements are not the row
measurements taken from the wattmeters: they include the PUE
but they are not shared among all the VMs that could be hosted on this
server. So, for the studied server, its static power consumption
(also called idle consumption) is around 83.2 Watts and we consider
a PUE of 1.2, this value is taken from \cite{shehabi_united_2016-1}}.
#+BEGIN_EXPORT latex
\begin{figure}
\centering
\subfigure[Average server energy consumption]{
\subfigure[Average server energy consumption multiplied by the PUE (= 1.2)]{
\includegraphics[width=0.4\linewidth]{./plots/sensorsNumberLine-cloud.png}
\label{fig:sensorsNumber-server}
}
\hspace{0.5cm}
\subfigure[Average sensors energy cost on server]{
\subfigure[Average sensors energy cost on the server hosting only our VM]{
\includegraphics[width=0.4\linewidth]{./plots/WPS-cloud.png}
\label{fig:sensorsNumber-WPS}
}
\caption{Server energy consumption for sensors sending data every 10s}
\caption{Server energy consumption multiplied by the PUE (= 1.2) for sensors sending data every 10s}
\label{fig:sensorsNumber-cloud}
\end{figure}
#+END_EXPORT
@ -543,7 +545,7 @@ In our case with small and sporadic network traffic, these results show that wit
\begin{figure}
\centering
\includegraphics[scale=0.5]{plots/sendInterval-cloud.png}
\caption{Server energy consumption for 50 sensors sending requests at different transmission interval.}
\caption{Server energy consumption multiplied by the PUE (= 1.2) for 50 sensors sending requests at different transmission interval.}
\label{fig:sensorsFrequency}
\end{figure}
#+END_EXPORT
@ -552,10 +554,8 @@ In our case with small and sporadic network traffic, these results show that wit
#+LaTeX: \label{sec:discuss}
To have an overview of the energy consumed by the overall system, it is important to consider the
end-to-end energy consumption. The Figure \ref{fig:end-to-end} represents the end-to-end system
energy consumption while varying the number of sensors. The values
are extracted from the experiments presented in the previous
section. We detail here the model used to attribute the energy
end-to-end energy consumption.
We detail here the model used to attribute the energy
consumption of our application for each part of the
architecture. For a given IoT device, we have:
1. For the IoT part, the entire consumption of the IoT device
@ -572,17 +572,59 @@ In our case with small and sporadic network traffic, these results show that wit
Concerning the sharing of the network costs, for each router, we
consider its aggregate bandwidth (on all the ports), its average
link utilization and the share taken by our IoT application. For a
given network device, we compute our share as follows:
given network device, we compute our share of the static energy
part as follows:
#+BEGIN_EXPORT latex
\[P_{static}^{netdevice} = \frac{P_{static}^{device} \times Bandwidth^{application}}{AggregateBandwidth^{device}
\times LinkUtilization^{device}}\]
#+END_EXPORT
#+End_EXPORT
where $P_{static}^{device}$ is the static power consumption of the
network device (switch fabrics for instance or gateway),
$Bandwidth^{application }$ is the bandwidth used by our IoT application,
$AggregateBandwidth^{device }$ is the overall aggregated bandwidth of the
network device on all its ports, and $LinkUtilization^{device}$ is the
effective link utilization percentage. The formula includes the
link utilization in order to charge for the effective energy cost
per trafic and not for the theoretical upper bound which is the
link bandwidth. Indeed, using such an upper bound leads to greatly
underestimate our energy part, since link utilization typically
varies between 5 to 40% \cite{Hassidim2013,Zhang2016}.
Similarly, for each network port, we take the share attributable to
our application: the ratio of our bandwidth utilization over the
port bandwidth multiplied by the link utilization and the overall
static power consumption of the port.
For the sharing of the Cloud costs, we take into account the number
of VMs that a server can host, the CPU utilization of a VM and the
PUE.
PUE. For a given Cloud server hosting our IoT application, we
compute our share of the static energy part as follows:
#+BEGIN_EXPORT latex
\[P_{static}^{Cloudserver} = \frac{P_{static}^{server} \times PUE^{DataCenter}}{HostedVMs^{server}}\]
#+End_EXPORT
Where $P_{static}^{server}$ is the static power consumption of the
server, $PUE^{DataCenter}$ is the data center PUE, and
$HostedVMs^{server}$ is the number of VMs a server can host. This last
parameter should be adjusted in the case of VMs with multiple
virtual CPUs. We do not
consider here over-commitment of Cloud servers. Yet, the dynamic
energy part is computed with the real dynamic measurements, so it
accounts for VM over-provisionning and resource under-utilization.
In our case, the Cloud server has 14 cores, which corresponds to
the potential hosting of 14 small VMs with one virtual CPU each,
and each vCPU is pinned to a server core. We consider that for
fault-tolerance purpose, the IoT application has a replication
factor of 2, meaning that two cloud servers store its database.
The Figure \ref{fig:end-to-end} represents the end-to-end system
energy consumption using the model described above while varying
the number of sensors. The values are extracted from the
experiments presented in the previous section.
Note that, for small-scale systems, the server energy consumption
is dominant compared to the energy consumed by the

Binary file not shown.

View file

@ -2524,3 +2524,13 @@ volume={18},
number={4},
pages={2822-2846},
}
@ARTICLE{Zhang2016,
author={Z. {Zhang} and Y. {Bejerano} and S. {Antonakopoulos}},
journal={IEEE/ACM Transactions on Networking},
title={{Energy-Efficient IP Core Network Configuration Under General Traffic Demands}},
year={2016},
volume={24},
number={2},
pages={745-758},
}