BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Brussels
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241011T111238Z
UID:EC65F0BB-5A39-426B-B18D-0EBE2E2FB37E
DTSTART;TZID=Europe/Brussels:20241010T130000
DTEND;TZID=Europe/Brussels:20241010T143000
DESCRIPTION:[]\n\nThis talk will describe some recent research works at the
  IETR lab on the decentralized smart charging of large fleets of electric 
 vehicles. This work is based on an artificial intelligence method combinin
 g adaptive multi-agent systems (AMAS) and bandits (a reinforcement learnin
 g method) [Zafar\, 2023]. As the training of AI-based energy management me
 thods requires numerous iterations to determine the state of the electrica
 l network (e.g presence/absence of congestion)\, whose computations may be
  time-consuming\, recent work have focused on the development of fast surr
 ogate models based on artificial intelligence. This talk will present a pr
 eliminary work on this topic covering tools such as deep neural network\, 
 decision trees and XGBoost\, and several training dataset generation techn
 iques including data augmentation techniques such as called Synthetic Mino
 rity Oversampling Technique (SMOTE) [Cuenca\, 2024]. It is also important 
 to note that currently enforced grid constraints may be considered as quit
 e conservative (seasonal or even static ratings applied to power transmiss
 ion/distribution components) in a context where the penetration rate of va
 riable renewables (such as wind and PV) increases. This justifies the grow
 ing integration of dynamic rating to maximise the utilization of the power
  system closer to its limits. However\, operating electrical networks with
  dynamic grid constraints presents challenges that works conducted at IETR
  contributed to address\, in particular on the relevant modeling of electr
 othermal behaviours for their integration in stochastic dynamic programmin
 g for storage management under uncertainty [Faye\, 2023].\n\n[Zafar\, 2023
 ] S. Zafar\, “[Optimized management of an active distribution network us
 ing AMAS combined with the RL bandit method](https://theses.hal.science/te
 l-04530782v1/file/sharyal_thesis_mars_24.pdf)”\, PhD thesis\, ENS Rennes
 \, France\, 2023.\n\n[Cuenca\, 2024] J. Cuenca\, E. Aldea\, E. Le Guern-Da
 ll’o\, R. Féraud\, G. Camileri\, A. Blavette\, “Training Data Generat
 ion Strategies for Data-driven Security Assessment of Low Voltage Smart Gr
 ids »\, to be presented at the IEEE ISGT Europe conference\, Dubrovnik\, 
 Croatia\, October 2024.\n\n[Faye\, 2023] A. Faye-Bédrin\, A. Blavette\, P
 . Haessig\, S. Bourguet\, I. Daminov\, “[Stochastic Dynamic Programming 
 for Energy Management of an Overplanted Offshore Wind Farm with Dynamic Th
 ermal Rating and Storage](https://hal.science/hal-04212709v1/file/powertec
 h_IEEE_validated.pdf)”\, in Proc. IEEE PowerTech\, Belgrade\, Serbia\, 2
 023.\n\nSpeaker(s): Anne Blavette\n\nRoom: Room Wind\, Bldg: EnergyVille 1
 \, Thor Park 8310\, Genk\, Limburg\, Belgium\, 3600\, Virtual: https://eve
 nts.vtools.ieee.org/m/435636
LOCATION:Room: Room Wind\, Bldg: EnergyVille 1\, Thor Park 8310\, Genk\, Li
 mburg\, Belgium\, 3600\, Virtual: https://events.vtools.ieee.org/m/435636
ORGANIZER:pes.sb.leuven@gmail.com
SEQUENCE:22
SUMMARY:Lecture by Anne Blavette - Decentralized smart charging of large fl
 eets of electric vehicles
URL;VALUE=URI:https://events.vtools.ieee.org/m/435636
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot;&gt;&lt;span lang=&quot;EN-US&quot; style
 =&quot;mso-ansi-language: EN-US\;&quot;&gt;&lt;img style=&quot;display: block\; margin-left: au
 to\; margin-right: auto\;&quot; src=&quot;https://events.vtools.ieee.org/vtools_ui/m
 edia/display/7e57e919-5c4e-4569-b52d-550d50ba0f79&quot; alt=&quot;&quot; width=&quot;719&quot; heig
 ht=&quot;508&quot;&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;text-align: justify\; ms
 o-layout-grid-align: none\; text-autospace: none\;&quot;&gt;&lt;span lang=&quot;EN-US&quot; sty
 le=&quot;mso-ansi-language: EN-US\;&quot;&gt;This talk will describe some recent resear
 ch works at the IETR lab on the decentralized smart charging of large flee
 ts of electric vehicles. This work is based on an artificial intelligence 
 method combining adaptive multi-agent systems (AMAS) and bandits (a reinfo
 rcement learning method) [Zafar\, 2023]. As the training of AI-based energ
 y management methods requires numerous iterations to determine the state o
 f the electrical network (e.g presence/absence of congestion)\, whose comp
 utations may be time-consuming\, recent work have focused on the developme
 nt of fast surrogate models based on artificial intelligence. This talk wi
 ll present a preliminary work on this topic covering tools such as deep ne
 ural network\, decision trees and XGBoost\, and several training dataset g
 eneration techniques including data augmentation techniques such as called
  Synthetic Minority Oversampling Technique (SMOTE) [Cuenca\, 2024]. It is 
 also important to note that currently enforced grid constraints may be con
 sidered as quite conservative (seasonal or even static ratings applied to 
 power transmission/distribution components) in a context where the penetra
 tion rate of variable renewables (such as wind and PV) increases. This jus
 tifies the growing integration of dynamic rating to maximise the utilizati
 on of the power system closer to its limits. However\, operating electrica
 l networks with dynamic grid constraints presents challenges that works co
 nducted at IETR contributed to address\, in particular on the relevant mod
 eling of electrothermal behaviours for their integration in stochastic dyn
 amic programming for storage management under uncertainty [Faye\, 2023].&lt;/
 span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;text-align: justify\; mso-layout-gr
 id-align: none\; text-autospace: none\;&quot;&gt;&lt;span lang=&quot;EN-US&quot; style=&quot;mso-ans
 i-language: EN-US\;&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;text-
 align: justify\; mso-layout-grid-align: none\; text-autospace: none\;&quot;&gt;&lt;sp
 an lang=&quot;EN-US&quot; style=&quot;mso-ansi-language: EN-US\;&quot;&gt;[Zafar\, 2023] S. Zafar
 \, &amp;ldquo\;&lt;/span&gt;&lt;span lang=&quot;FR&quot;&gt;&lt;a href=&quot;https://theses.hal.science/tel-
 04530782v1/file/sharyal_thesis_mars_24.pdf&quot;&gt;&lt;span lang=&quot;EN-US&quot; style=&quot;mso-
 ansi-language: EN-US\;&quot;&gt;Optimized management of an active distribution net
 work using AMAS combined with the RL bandit method&lt;/span&gt;&lt;/a&gt;&lt;/span&gt;&lt;span 
 lang=&quot;EN-US&quot; style=&quot;mso-ansi-language: EN-US\;&quot;&gt;&amp;rdquo\;\, PhD thesis\, EN
 S Rennes\, France\, 2023.&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;t
 ext-align: justify\; mso-layout-grid-align: none\; text-autospace: none\;&quot;
 &gt;&lt;span lang=&quot;EN-US&quot; style=&quot;mso-ansi-language: EN-US\;&quot;&gt;[Cuenca\, 2024] J. 
 Cuenca\, E. Aldea\, E. Le Guern-Dall&amp;rsquo\;o\, R. F&amp;eacute\;raud\, G. Cam
 ileri\, A. Blavette\, &amp;ldquo\;Training Data Generation Strategies for Data
 -driven Security Assessment of Low Voltage Smart Grids&amp;nbsp\;&amp;raquo\;\, to
  be presented at the IEEE ISGT Europe conference\, Dubrovnik\, Croatia\, O
 ctober 2024.&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;text-align: justify\;
  mso-layout-grid-align: none\; text-autospace: none\;&quot;&gt;&lt;span lang=&quot;EN-US&quot; 
 style=&quot;mso-ansi-language: EN-US\;&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;span lang=&quot;EN-US&quot; style=
 &quot;font-size: 12.0pt\; font-family: &#39;Aptos&#39;\,sans-serif\; mso-ascii-theme-fo
 nt: minor-latin\; mso-fareast-font-family: Aptos\; mso-fareast-theme-font:
  minor-latin\; mso-hansi-theme-font: minor-latin\; mso-bidi-font-family: &#39;
 Times New Roman&#39;\; mso-bidi-theme-font: minor-bidi\; color: windowtext\; m
 so-ansi-language: EN-US\;&quot;&gt;[Faye\, 2023] A. Faye-B&amp;eacute\;drin\, A. Blave
 tte\, P. Haessig\, S. Bourguet\, I. Daminov\, &amp;ldquo\;&lt;/span&gt;&lt;span lang=&quot;F
 R&quot;&gt;&lt;a href=&quot;https://hal.science/hal-04212709v1/file/powertech_IEEE_validat
 ed.pdf&quot;&gt;&lt;span lang=&quot;EN-US&quot; style=&quot;font-size: 12.0pt\; font-family: &#39;Aptos&#39;
 \,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-fareast-font-family
 : Aptos\; mso-fareast-theme-font: minor-latin\; mso-hansi-theme-font: mino
 r-latin\; mso-bidi-font-family: &#39;Times New Roman&#39;\; mso-bidi-theme-font: m
 inor-bidi\; mso-ansi-language: EN-US\;&quot;&gt;Stochastic Dynamic Programming for
  Energy Management of an Overplanted Offshore Wind Farm with Dynamic Therm
 al Rating and Storage&lt;/span&gt;&lt;/a&gt;&lt;/span&gt;&lt;span lang=&quot;EN-US&quot; style=&quot;font-size
 : 12.0pt\; font-family: &#39;Aptos&#39;\,sans-serif\; mso-ascii-theme-font: minor-
 latin\; mso-fareast-font-family: Aptos\; mso-fareast-theme-font: minor-lat
 in\; mso-hansi-theme-font: minor-latin\; mso-bidi-font-family: &#39;Times New 
 Roman&#39;\; mso-bidi-theme-font: minor-bidi\; color: windowtext\; mso-ansi-la
 nguage: EN-US\;&quot;&gt;&amp;rdquo\;\, in Proc. IEEE PowerTech\, Belgrade\, Serbia\, 
 2023.&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;text-align: justify\; mso-la
 yout-grid-align: none\; text-autospace: none\;&quot;&gt;&lt;span lang=&quot;EN-US&quot; style=&quot;
 mso-ansi-language: EN-US\;&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR