BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095745Z
LOCATION:Davos
DTSTART;TZID=Europe/Stockholm:20230626T112000
DTEND;TZID=Europe/Stockholm:20230626T115000
UID:submissions.pasc-conference.org_PASC23_sess104_pos109@linklings.com
SUMMARY:P23 - Evaluation of GPU Accelerated Machine Learning Algorithms fo
 r Energy Price Prediction
DESCRIPTION:Poster\n\nNaga Venkata Sai Jitin Jami (Università della Svizze
 ra italiana, Friedrich-Alexander-Universität Erlangen-Nürnberg); Juraj Kar
 dos and Olaf Schenk (Università della Svizzera italiana); and Harald Köstl
 er (Friedrich-Alexander-Universität Erlangen-Nürnberg)\n\nThe Locational M
 arginal Pricing (LMP) mechanism is a way to calculate the cost of providin
 g electricity to a specific point in the grid. Accurate forecasting of LMP
  is important for market participants such as power producers or financial
  institutions to optimize operations and bidding strategies. The LMP is ca
 lculated using the optimal power flow (OPF) problem, which is a constraine
 d nonlinear optimization problem to determine the least-cost power generat
 ion in the grid. However, this can be a time-consuming and computationally
  demanding task. Recent efforts have focused on using machine learning tec
 hniques, such as Decision Tree Regressor, Random Forest Regressor, Gradien
 t Boosting Regressor, and Deep Neural Networks, to predict LMP more effici
 ently. Modern machine learning libraries like Scikit-Learn and PyTorch are
  optimised to use multi-core CPU and GPU architectures that are common in 
 modern High-Performance Computing (HPC) clusters. These models have been t
 ested on multiple electricity grids and found to be 4-5 orders of magnitud
 e faster than traditional methods. However, they do have slightly higher e
 rror rates on edge-case scenarios. Overall, there is a strong case for usi
 ng machine learning models for LMP prediction on large scale electricity g
 rids with the aid of HPC resources.\n\nSession Chair: Elaine M. Raybourn (
 Sandia National Laboratories)
END:VEVENT
END:VCALENDAR