BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260619T010105Z
UID:C7DBE9E1-E4D9-44B4-B4BD-024C0A5B4561
DTSTART;TZID=America/Chicago:20260618T190000
DTEND;TZID=America/Chicago:20260618T200000
DESCRIPTION:Forecasting is essential for ensuring grid stability given the 
 unpredictable nature of renewables like solar power and wind energy. Deep 
 learning methods that have been deployed to date can generate inaccurate f
 orecasts in certain situations and fail to satisfy physical assumptions an
 d constraints. In this paper\, we propose a framework to enhance the accur
 acy and reliability of renewable energy forecast models. The RAG framework
  is augmented with safety guardrails to ensure that the forecasts are robu
 st\, accurate\, and interpretable. Specifically\, the framework retrieves 
 historical weather-generation patterns relevant to the current state to in
 crease the context-awareness of the time series models. We further deploy 
 the guardrails to constrain predictions and avoid impossible values. Throu
 gh experiments done on benchmark data from the National Renewable Energy L
 aboratory and Global Energy Forecasting Competition\, we prove that our ap
 proach reduces prediction errors and constraint violations compared to the
  baselines.\n\nSpeaker(s): Rakesh More\, \n\nAgenda: \nRenewable Energy Fo
 recasting\, Retrieval-Augmented Generation\, Explainable AI\, Smart Grid\,
  Guardrails\, Time-Series Prediction\, AI Safety\n\nVirtual: https://event
 s.vtools.ieee.org/m/561841
LOCATION:Virtual: https://events.vtools.ieee.org/m/561841
ORGANIZER:muktevisree@gmail.com
SEQUENCE:28
SUMMARY:Safe and Explainable Renewable Energy Forecasting using Retrieval-A
 ugmented Generation and Guardrails
URL;VALUE=URI:https://events.vtools.ieee.org/m/561841
X-ALT-DESC:Description: <br /><p>Forecasting is essential for ensuring grid
  stability given the unpredictable nature of renewables like solar power a
 nd wind energy. Deep learning methods that have been deployed to date can 
 generate inaccurate forecasts in certain situations and fail to satisfy ph
 ysical assumptions and constraints. In this paper\, we propose a framework
  to enhance the accuracy and reliability of renewable energy forecast mode
 ls. The RAG framework is augmented with safety guardrails to ensure that t
 he forecasts are robust\, accurate\, and interpretable. Specifically\, the
  framework retrieves historical weather-generation patterns relevant to th
 e current state to increase the context-awareness of the time series model
 s. We further deploy the guardrails to constrain predictions and avoid imp
 ossible values. Through experiments done on benchmark data from the Nation
 al Renewable Energy Laboratory and Global Energy Forecasting Competition\,
  we prove that our approach reduces prediction errors and constraint viola
 tions compared to the baselines.</p><br /><br />Agenda: <br /><p>Renewable
  Energy Forecasting\, Retrieval-Augmented Generation\, Explainable AI\, Sm
 art Grid\, Guardrails\, Time-Series Prediction\, AI Safety</p>
END:VEVENT
END:VCALENDAR