SPYROS CHATZIVASILEIADIS

Downloads

Download the assignment material here: Assignment Material

Code on Github for Physics-Informed Neural Networks for Power Systems: Github Code.
Code on Github for Physics-Informed Neural Networks for System Identification: Github Code.
Assignment and Code on Physics-Informed Neural Networks: Assignment, Code

The available code is based on the following two papers:

[1]	G. S. Misyris, A. Venzke, S. Chatzivasileiadis, Physics-Informed Neural Networks for Power Systems, presented at the Best Paper Session of IEEE PES General Meeting 2020, Montreal, Canada. [ paper ]
[2]	J. Stiasny, G. S. Misyris, S. Chatzivasileiadis, Physics-Informed Neural Networks for Non-linear System Identification applied to Power System Dynamics, Accepted to IEEE Powertech, 2021. [ paper ]

The available code is based on the following paper:

[1]	A. Venzke, G. Qu, S. Low, S. Chatzivasileiadis, Learning Optimal Power Flow: Worst-case Guarantees for Neural Networks. IEEE SmartGridComm 2020. Best Student Paper Award! [ .pdf \| slides \| poster \| video ]

The available code is based on the following paper:

[1]	A. Venzke, D. T. Viola, J. Mermet-Guyennet, G. S. Misyris, S. Chatzivasileiadis, Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow to Mixed-Integer Linear Programs, submitted, 2020. [ paper ]

IEEE 14-bus system; N-1 and Small-Signal Stability, Q-limits not enforced, 49'615 points: Database
IEEE 14-bus system; N-1 and Small-Signal Stability, Q-limits enforced, 675'367 points: Database
NESTA 162-bus system; N-1 and Small-Signal Stability, >500'000 points: Database

The two 14-bus system databases are considered complete. More information about these can be found here: Instructions about IEEE 14-bus databases

The available databases have been based on the following papers:

[1]	F. Thams, A. Venzke, R. Eriksson, S. Chatzivasileiadis, Efficient Database Generation for Data-Driven Security Assessment of Power Systems, IEEE Transactions on Power Systems, vol 35, no. 1, pp. 30-41, Jan. 2020. [ paper ]
[2]	A. Venzke, D.K. Molzahn, S. Chatzivasileiadis, Efficient Creation of Datasets for Data-Driven Power System Applications, Accepted at the 21st Power System Computation Conference (PSCC), 2020. [ paper ]

Code available on: https://github.com/LucienBobo/SOCP_OPF_Nick2017
You can find more information about how the code has been used here: Lucien Ali Bobo, Andreas Venzke, S.Chatzivasileiadis, Second-Order Cone Relaxations of the Optimal Power Flow for Active Distribution Grids: Comparison of Methods, International Journal of Electrical Power and Energy Systems, vol. 127, 106625, 2021 [ Paper ]
The code is based on the method proposed in: M. Nick, R. Cherkaoui, J. L. Boudec and M. Paolone, "An Exact Convex Formulation of the Optimal Power Flow in Radial Distribution Networks Including Transverse Components," in IEEE Transactions on Automatic Control, vol. 63, no. 3, pp. 682-697, March 2018. [ Paper on IEEExplore ]

Code available on: https://github.com/ID-EDGe/DR-CC-tool
This code has been developed in the framework of the ID-EDGE project, "Indo-Danish collaboration for data-driven control and optimization for a highly Efficient Distribution Grid", funded by Innovation Fund Denmark.
You can find details about the code and a code manual here: Dominic Scotoni, Development and Implementation of a Distributionally Robust Chance Constrained Optimization Tool for Distribution Grids, Master Thesis, Technical University of Denmark and ETH Zurich, 2020. [ Report ]

Data and Code available on: https://github.com/antosat/Nordic-Market-Model/tree/v1.0.0
The Nordic Market model has been created based on real market data from 2019. The code includes a useful DC-OPF formulation that also considers the AC and HVDC losses.
You can find a video presentation and more information about how the code has been used here: Andrea Tosatto, Spyros Chatzivasileiadis, HVDC loss factors in the Nordic Market, Accepted for publication to PSCC 2020. [ .pdf | Video Presentation | slides ]