Player is loading...
Pr. David Wannier & Jean-Marie Allder - Research advance in Energy prediction for electrical vehicles and green mobility hotels, the results of the eVIP project
Pr. David Wannier & Jean-Marie Allder, HES-SO Valais-Wallis
Monday, Nov. 15, 2021 · 11:46 a.m. · 12m 17s
The purpose of eVIP project is to manage flexible loads like electric vehicles (EV) charging stations. Pilot systems are installed in 8 GreenMobility hotels. eVIP is built on the architecture of the european project GoFlex. Main goal is to optimize management of an EV charging station regarding the local consumption and PV production.
Embed
Transcriptions
Note: this content has been automatically generated.
00:00:00
okay we go for the next presentation and the presenters i i thought it's too
00:00:04
again so somehow this seems to be a pattern one high even have moderate life
00:00:09
huh that's yeah yeah you know i i i had a
00:00:13
good party here someone i say oh so we now call
00:00:18
for the e. i'm not pop it off of complexity
00:00:23
by by changing pots and pans out something can move
00:00:26
so we go now to the mobility and these things also
00:00:30
need to be fuel and that's yours thank you very much
00:00:38
uh_huh him and
00:00:43
yeah i did i miss
00:00:51
uh_huh uh_huh uh_huh
00:00:56
uh_huh yeah uh_huh and moved to mexico
00:01:08
okay
00:01:10
thank you very much for the invitation so today i will presents and
00:01:15
the project cord the v. i. p. for energy visualisation integration and production
00:01:22
the bayes idea to place value has several hotels wanted to promote the
00:01:28
image of a green on the ecological region uh to the green mobility concepts
00:01:34
they receive the award based innovation in services in
00:01:37
addition to accommodation and that was uh the first discussions
00:01:43
we have built our development infrastructure at stake no borders yeah
00:01:48
on worked with bay shortages to create the first proof of concept
00:01:55
after the first phase we needed to improve the charging station uh capabilities
00:02:00
we had the the unit by yeah to have full control on
00:02:03
the power and the energy meter to collect the data can see
00:02:11
we had the chance to improve the hardware and software
00:02:14
on or l. test infrastructure at uh companies believe use yeah
00:02:19
the new version are continuously tested by proposals what teaching in business i tickles program
00:02:27
i'd yeah of the v. i. p. projects was to help direct hours on managers
00:02:32
to understand the magic role in their what that is especially if they i'd even charging stations
00:02:39
we use machine learning algorithm to predict the available power
00:02:44
regarding own consumption and eventually local for the whole day production
00:02:50
we base the v. i. p. architecture on the h. twenty
00:02:53
twenty go flex a infrastructure to collect data consumption on production
00:02:59
and we added the machine learning server to pretty
00:03:01
good about about power for the the um charging stations
00:03:08
the project digital decision as c. c. r. fury is
00:03:12
it compliments the i. d. v. i. p. we user interaction
00:03:17
we need to add information door machine learning algorithm as a c.
00:03:21
charging station do not i know to get information from the weekend
00:03:26
we need to ask but we stay it's time to
00:03:29
departure to better uh pretty the available power at the open
00:03:36
to interact with end users we implemented on drawing done i was up to
00:03:40
collect the information and also display the actual state use all the charging station
00:03:46
we can easily understand the red part to a charging you progress the green whether i'm
00:03:53
even charging station is available and the orange one this one is one of the most uh
00:04:01
uh important stages for us is the vehicle to breed availability it
00:04:05
means the car is full charge or charge like uh the parameters
00:04:10
and is available for concepts like you about certainly about the vehicle to with bigger
00:04:16
tool they can forward on that will be there next services will build on that
00:04:23
uh we have here a representation of the energy flows from the greed
00:04:27
well what what they power plants to the uh charging station
00:04:32
infrared you can see the data flow from hotel to time series data
00:04:36
base for the conception data and fraud to manage the recharging station to unify
00:04:43
i will now give the floor to germany with described implement in machine learning algorithm thank you david
00:04:53
sorry uh just a quick introduction and some uh i
00:04:57
work as a as an assistant uh digits so it's team
00:05:02
uh it's it in just going to uh about the prediction we in the the for the project
00:05:09
um so our our main goal was to predict a available
00:05:13
our uh four hotels in the next uh our year period
00:05:18
so with a lot of work on it before i
00:05:21
what introduced right um and and you know the people
00:05:26
uh especially i think he's basically in a situation
00:05:32
uh and he presented a a machine to a machine learning method
00:05:38
uh um uh that tries to predict uh
00:05:42
energy consumption for make really and also for restaurant
00:05:46
uh and used uh the battery uh time data no
00:05:50
production and uh and uh whether data to a pretty good
00:05:56
uh and he move present a justification of the international
00:06:02
uh um so for the justification to several uh i've reasons at third
00:06:08
and when it came out to be the best is
00:06:10
the greatest tree uh with a negative here ninety percent
00:06:16
uh and it's good to know that that that uh we separated the results into six different clusters
00:06:24
uh which uh present it six different
00:06:27
levels of production uh oh a consumption religion
00:06:32
uh so uh yeah here we also have the result
00:06:37
for the wiener a word sorry for the recursion a problem
00:06:42
uh and once again the region was really you know the
00:06:46
the the the uh uh action determination of you or maybe
00:06:52
ah and just you know we we can see a graph from from over thirty day period
00:06:58
uh we didn't read the measure of them were restroom is there and blew production
00:07:07
so we can see the results are promising and all our ah or something and uh and discovered
00:07:16
uh so uh it looks like the results of problem so
00:07:19
we you know uh we implemented then uh on the project
00:07:24
ah um to try to predict the consumption and also to provide a really very available
00:07:31
or that in order to use that as
00:07:34
much as possible uh self produced full of energy
00:07:39
oh so here we created a simple and user friendly there's four
00:07:43
uh where we can see the energy flow of the uh uh sorry let uh with the
00:07:50
a portable take power produced uh going into you
00:07:54
know and then uh being used by charging stations
00:07:58
and then the next ah here we can manage or
00:08:02
charging station any state for instance because a on off
00:08:06
and uh but what what is most interesting first it the production on the bottom right
00:08:13
uh so instead of having six clusters at the moment we only uh for uh
00:08:18
and we change them colours uh which uh which are a green colour represents a
00:08:25
no consumption production so i uh i haven't written in your state
00:08:31
and with this uh and i uh and we can also said management ah
00:08:37
an ethnic charging station to automatic uh on a right and
00:08:42
if we do this at the hands of the train station
00:08:45
with us according to the consumption production and like this
00:08:49
we ensure that uh as much stuff uh produced for the
00:08:53
whole day energies use and also all the other a
00:08:56
whole does installations i can use the separatist sort of energy
00:09:03
yeah so we've seen that uh the and we've seen a lot of uh
00:09:10
promising results uh and we know that uh we believe in and uh there
00:09:17
a real scale um it's just an interstate sure uh with the hotels
00:09:21
uh participating in the study but we also since and challenges for instance oh
00:09:27
complex it was to define architecture with so many
00:09:30
different people there's a so many different systems and technologies
00:09:35
uh we also have to deal with a maximum power uh you know uh uh go flex
00:09:43
a club i you know get weary uh used to gather a um
00:09:48
actually data uh and for instance one of
00:09:52
our uh that was hired and this consumption
00:09:57
ah we also that the recent f. or or uh uh it's um
00:10:02
or some delays uh with an incision the
00:10:06
means a software or installation delays as well
00:10:11
and of course uh we don't really think about it when uh when we're working if uh
00:10:19
four or on the law because uh we also your external
00:10:23
problems like uh i. t. programs and network problems with those
00:10:30
and uh i will let it uh for a fire words thank you very much um
00:10:40
in our goal at the university of uh by sounds is to disseminate on a different level
00:10:45
so we bought submitted to the local probably given to fifteen yes the
00:10:49
the ark foundations six hundred students uh these eat it or a presentation
00:10:55
here uh we also local organise the climate emergency there yeah um
00:11:00
with the students were musical there's a laptop up uh it
00:11:05
was a a here the presentation of the world the concept
00:11:08
uh we had the chance at the national level to join the
00:11:12
u. c.s competence centre imagery research if you really is huge transition project
00:11:17
and uh also present the result that the um national for the day conference in june
00:11:24
physically with returns this year and the main
00:11:28
version or libellous mention the before the international sustainability
00:11:33
and energy conference you can find the references there and
00:11:36
also in the in to be i don't know the images
00:11:44
i'm just about the easy route but our goal is to
00:11:47
easily integrate new technologies to help and accelerate uh the energy transition
00:11:53
we are working on three pilot three laws visualisation with j. s. so we could develop to
00:11:58
the grand uh the age twenty twenty what maps uh the base the two books and the um
00:12:05
the the broach a node that surprise systems integration you the second pillar
Conference Program
Workshop introduction by Jérôme Kämpf & Henning Müller + Keynote speech Pr. Dr. Guglielmina Mutani - Place-based energy models for sustainable cities
Pr. Dr. Guglielmina Mutani, Politecnico di Torino
Nov. 15, 2021 · 9 a.m.
333 views
Q&A (Keynote speech: Pr. Dr. Guglielmina Mutani)
Pr. Dr. Guglielmina Mutani, Politecnico di Torino
Nov. 15, 2021 · 9:49 a.m.
Roberto Boghetti - Simulating District Heating Networks’ hydraulics with residual physics neural networks
Roberto Boghetti, Idiap Research Institute
Nov. 15, 2021 · 10 a.m.
Q&A (Roberto Boghetti)
Roberto Boghetti, Idiap Research Institute
Nov. 15, 2021 · 10:13 a.m.
Amine Weibel - Machine learning forecast for photovoltaic power stations (PV) with spatial interpolation on the COSMO-7 model. A real ‘use-case’ on the Czech Republic
Amine Weibel, HES-SO
Nov. 15, 2021 · 10:16 a.m.
Q&A (Amine Weibel, HES-SO Valais-Wallis)
Amine Weibel, HES-SO
Nov. 15, 2021 · 10:27 a.m.
101 views
Dr. Giuseppe Peronato - HeatLearn: a convolutional neural network to assess the building energy consumption at regional scale from open land-use maps
Dr. Giuseppe Peronato, Idiap Research Institute
Nov. 15, 2021 · 10:30 a.m.
Q&A (Dr. Giuseppe Peronato)
Dr. Giuseppe Peronato, Idiap Research Institute
Nov. 15, 2021 · 10:43 a.m.
Pr. Dominique Genoud & Jérôme Treboux - Integrating machine learning and AI in practical energy applications : a review of these last 10 years activities at the Institute of Information Systems
Pr. Dominique Genoud & Jérôme Treboux, HES-SO Valais-Wallis
Nov. 15, 2021 · 10:46 a.m.
Q&A (Pr. Dominique Genoud & Jérôme Treboux)
Pr. Dominique Genoud & Jérôme Treboux, HES-SO Valais-Wallis
Nov. 15, 2021 · 10:59 a.m.
Dr. Marco Tognoli - Fuel-saving potential simulation and estimation when optimally predicting the supply set-point conditions of a District Heating Network with detailed system data-driven modelling
Dr. Marco Tognoli, Politecnico di Milano
Nov. 15, 2021 · 11:31 a.m.
Q&A (Dr. Marco Tognoli)
Dr. Marco Tognoli, Politecnico di Milano
Nov. 15, 2021 · 11:44 a.m.
Pr. David Wannier & Jean-Marie Allder - Research advance in Energy prediction for electrical vehicles and green mobility hotels, the results of the eVIP project
Pr. David Wannier & Jean-Marie Allder, HES-SO Valais-Wallis
Nov. 15, 2021 · 11:46 a.m.
Q&A (Pr. David Wannier & Jean-Marie Allder)
Pr. David Wannier & Jean-Marie Allder, HES-SO Valais-Wallis
Nov. 15, 2021 · 11:58 a.m.
Dr. Kavan Javanroodi - Extending the concept of energy hub to facilitate sector and spatial coupling
Dr. Kavan Javanroodi, Solar Energy and Building Physics Laboratory (LESO-PB) at EPFL
Nov. 15, 2021 · 11:59 a.m.
143 views
Q&A (Dr. Kavan Javanroodi)
Dr. Kavan Javanroodi, Solar Energy and Building Physics Laboratory (LESO-PB) at EPFL
Nov. 15, 2021 · 12:16 p.m.
Pr. Pierre Roduit - Prediction of the electricity flexibility of households using Machine Learning
Pr. Pierre Roduit, HES-SO Valais-Wallis
Nov. 15, 2021 · 12:18 p.m.
Q&A (Pr. Pierre Roduit)
Pr. Pierre Roduit, HES-SO Valais-Wallis
Nov. 15, 2021 · 12:32 p.m.
Loïc Puthod - An open-data acquisition toolchain for AI applications
Loïc Puthod, Centre de recherche Crem
Nov. 15, 2021 · 1:59 p.m.
Q&A (Loïc Puthod)
Loïc Puthod, Centre de recherche Crem
Nov. 15, 2021 · 2:10 p.m.
Cédric Mugabo Serugendo - EnerMaps: The open data tool empowering your energy transition
Cédric Mugabo Serugendo, Centre de recherche Crem
Nov. 15, 2021 · 2:16 p.m.
&Q (Cédric Mugabo Serugendo)
Cédric Mugabo Serugendo, Centre de recherche Crem
Nov. 15, 2021 · 2:27 p.m.
Recommended talks
Projets SEMIAH et GOFLEX
Prof. Pierre Roduit, HES-SO
April 25, 2018 · 2:20 p.m.
296 views
