Title:
Evolving Interconnection Procedures: The Chilean experience
Abstract:
Well-functioning planning, grid access, and interconnection procedures are key to ensuring that transmission systems support competition in generation and a sustainable and reliable electricity supply. The ongoing transformation of the power sector is increasing the number and variety of resources seeking grid interconnection, thus requiring proper and timely expansion and reinforcement of the transmission system. This presentation reviews recent changes in the Chilean regulatory framework to address current challenges, identifying changes that have had a positive impact and those that have not. Following the presentation, a discussion can be held to compare regulatory frameworks in Canada and Chile, identify common challenges, and explore how both countries have addressed them.
Bio:
Dr. Ricardo Álvarez received a degree in electrical engineering from the University of Chile in 2005, and the Ph.D. degree in electrical engineering from RWTH Aachen University, Germany, in 2016. He is currently associate Professor at the Universidad Técnica Federico Santa María, Researcher at the Solar Energy Research Center (SERC-Chile) and Director of the PhD Programm in Electrical Engineering at the Universidad Tecnica Federico Santa Maria. His main research interests include power system planning, operation, and optimization, large-scale integration of renewable energies, and the use of artificial intelligence in power system applications.
Title:
Accelerating column generation with machine learning for solving the transmission network expansion planning problem
Abstract:
This work presents a novel ML assisted algorithm for solving the multi-year TNEP problem. The proposal is to add a binary classifier into the CG algorithm in a way that can improve the convergence time and guarantee global optimality. The results show that the binary classifier has an accuracy above 90% for estimating the value of the binary variables. Additionally, the integration of the binary classifier into the Column Generation algorithm allowed us to reduce the computational time by over 50%.
Bio:
Pablo Oteiza is a Master thesis student at Federico Santa Maria Technical University. He has experience working in the Chilean energy industry, namely in the Chilean national ISO and in Transelec which is the largest transmission company in the country. His work focuses on Transmission network planning and the optimization of power system through machine learning. He is currently working with the University of Waterloo in a joint project for solving transmission planning problems with neural networks.
Register:
Zoom Link:
https://us02web.zoom.us/s/4640082022?omn=84861250239#success
Venue:
Engineering 2 (E2), Room 2350