BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20221030T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.25673.field_data.0@www.glad.uniroma1.it
DTSTAMP:20260406T193345Z
CREATED:20230316T184843Z
DESCRIPTION:Care colleghe e colleghi\, Con la presente vi informo che In ot
 temperanza ai requisiti previsti dalla procedura selettiva per il reclutam
 ento di un ricercatore a tempo determinato tipologia A regime a tempo pien
 o PNRR PE7 SPOKE 9 SC 09/H1 - SSD ING-INF/05 Dipartimento di Ingegneria In
 formatica Automatica E Gestionale Antonio Ruberti\, codice bando 2023RTDAP
 NRR071\, pubblicata sulla Gazzetta Ufficiale della Repubblica Italiana n.5
  del 20/01/2023\, \, il Dr. Gabriele Proietti Mattia terrà un seminario pu
 bblico sulle attività di ricerca svolte e in corso di svolgimento il 20/03
 /2023 alle ore 15:00 presso l'aula magna del DIAG.  Il seminario sarà anch
 e trasmesso in modalità telematica su zoom al seguente linkhttps://uniroma
 1.zoom.us/j/91649876760?pwd=TXZ3amk2ZXVzZXM1UzhmdUZ4OWFHdz09Meeting ID: 91
 6 4987 6760Passcode: 420544 Titolo: Cooperative scheduling and load balanc
 ing approaches in Fog and Edge Computing: from randomized to online reinfo
 rcement learning strategiesAbstract: Fog and Edge Computing are two models
  that reached maturity in the last decade\, and they can now be considered
  de facto standards for deploying low and ultra-low latency applications\,
  privacy-oriented solutions\, industry 4.0\, and smart city infrastructure
 s. The common trait of Fog and Edge computing environments regards their i
 nherent distributed and heterogeneous nature where the multiple (Fog or Ed
 ge) nodes are able to interact with each other with the purpose of pre-pro
 cessing data gathered by the uncountable number of sensors to which they a
 re connected to\, even by running significant ML models and relying upon s
 pecific processors (TPU). In general\, these nodes are often placed in a g
 eographic domain\, like a smart city\, and the dynamic of the traffic duri
 ng the day may cause some nodes to be overwhelmed by requests while others
  instead may become completely idle. To achieve the optimal usage of the s
 ystem and also to guarantee the best possible QoS across all the users con
 nected to the Fog or Edge nodes\, the need to design load balancing and sc
 heduling algorithms arises. The talk will illustrate cooperation-based sol
 utions by showing the pros\, the cons\, and the results obtained by using 
 randomized approaches\, model-based ones\, and solutions based on online r
 einforcement learning algorithms.Short Bio: Gabriele Proietti Mattia is cu
 rrently a Postdoc at Sapienza University of Rome\, hosted by prof. Roberto
  Beraldi. Previously he completed his PhD in Engineering in Computer Scien
 ce at the same University\, then a Master's Degree and a Bachelor's Degree
  in the same field\, respectively\, in 2017 and 2019. He has published sev
 eral papers at leading conferences in the area of Cloud\, Fog\, and Edge C
 omputing (PerCom\, ICCCN\, MSWiM) and in Journals (IEEE Transactions on Cl
 oud Computing\, Computer Networks\, Pervasive and Mobile Computing).
DTSTART;TZID=Europe/Paris:20230320T150000
DTEND;TZID=Europe/Paris:20230320T150000
LAST-MODIFIED:20230710T173816Z
LOCATION:Aula Magna\, DIAG
SUMMARY:SEMINARIO PUBBLICO DI GABRIELE PROIETTI MATTIA (PROCEDURA VALUTATIV
 A PER N.1 POSTO DI RICERCATORE A TEMPO DETERMINATO TIPOLOGIA A - PNRR PE7 
 SPOKE 9 SC 09/H1 SSD ING-INF/05) - LUNEDI' 20/03/2023 ORE 15.00\, AULA MAG
 NA - Gabriele Proietti Mattia
URL;TYPE=URI:http://www.glad.uniroma1.it/node/25673
END:VEVENT
END:VCALENDAR
