BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Bucharest
BEGIN:DAYLIGHT
DTSTART:20200329T040000
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20191027T030000
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191122T120209Z
UID:FBE27D82-957D-4929-BBFD-93E63C7722B3
DTSTART;TZID=Europe/Bucharest:20191122T110000
DTEND;TZID=Europe/Bucharest:20191122T120000
DESCRIPTION:The talk will provide a brief overview of current methods for e
 nergy time series forecasting using data mining and computational intellig
 ence techniques with particular focus on building energy traces. This will
  include: the Matrix Profile\, an efficient technique for time series expl
 oratory analysis and data mining\, typical regression models with domain-s
 pecific feature engineering and new end-to-end deep learning approaches by
  means of recurrent neural networks.\n\nAn hierarchical energy system arch
 itecture with embedded control will be discussed which pushes prediction m
 odels to edge devices to address the challenge of managing demand-side res
 ponse locally. We employ a two-step approach: At an upper level of hierarc
 hy\, we adopt a conventional machine learning pipeline to build load predi
 ction models using automated feature extraction and selection. On a lower 
 level of hierarchy\, computed labels are used to train impact models reali
 zed by LSTM networks running on edge devices to infer the probability that
  the power consumption of the player contributes to the upper level predic
 tion failure event. The system is evaluated on individual and aggregated p
 ublic energy traces of academic buildings.\n\nThis event is technically su
 pported by the IEEE Romania RAS Chapter within the seminar of Automation a
 nd Information Systems of the Department of Automatic Control and Computer
 s\, University "Politehnica" of Bucharest.\n\nSpeaker(s): Grigore Stamates
 cu\, \n\nRoom: PRECIS PR406\, Bldg: Facultatea de Automatica si Calculatoa
 re\, Splaiul Independentei 313\, Bucharest\, Municipiul Bucuresti\, Romani
 a\, 060042
LOCATION:Room: PRECIS PR406\, Bldg: Facultatea de Automatica si Calculatoar
 e\, Splaiul Independentei 313\, Bucharest\, Municipiul Bucuresti\, Romania
 \, 060042
ORGANIZER:grig@me.com
SEQUENCE:3
SUMMARY:Time series models for prediction and anomaly detection of building
  energy consumption
URL;VALUE=URI:https://events.vtools.ieee.org/m/211109
X-ALT-DESC:Description: <br /><div class="">The talk will provide a brief o
 verview of current methods for energy time series forecasting using data m
 ining and computational intelligence techniques with particular focus on b
 uilding energy traces. This will include: the Matrix Profile\, an efficien
 t technique for time series exploratory analysis and data mining\, typical
  regression models with domain-specific feature engineering and new end-to
 -end deep learning approaches by means of recurrent neural networks.</div>
 \n<div class="">\n<div class="">An hierarchical energy system architecture
 &nbsp\;with embedded control will be discussed which pushes prediction mod
 els to edge devices&nbsp\;to address the challenge of&nbsp\;managing deman
 d-side response&nbsp\;locally. We employ a two-step approach: At an upper 
 level of hierarchy\, we adopt a conventional machine learning pipeline to 
 build load prediction models using&nbsp\;automated feature extraction and 
 selection. On a lower level of hierarchy\, computed labels are used to tra
 in&nbsp\;impact models&nbsp\;realized by LSTM networks running on edge dev
 ices to infer the probability that the&nbsp\;power consumption of the play
 er contributes to the upper level prediction failure event. The system is 
 evaluated on individual and aggregated public energy traces of academic&nb
 sp\;buildings.&nbsp\;</div>\n<div class="">&nbsp\;</div>\n<div class=""><e
 m>This event is technically supported by the IEEE Romania RAS Chapter with
 in the seminar of Automation and Information Systems of the Department of 
 Automatic Control and Computers\, University "Politehnica" of Bucharest.</
 em></div>\n</div>
END:VEVENT
END:VCALENDAR