The code represents the implementation for the paper
- Mohammadamin Moradi, Yang Weng, and Ying-Cheng Lai, 'Defending smart electrical power grids against cyberattacks with deep Q-learning'. PRX Energy
This code is free to use for research purpose. If you find this useful in your research, please cite the publication listed above.
*** DCSIMSEP should be installed first to simulate the power grid parts! ***
The environment used in this works is a customized version of DCSIMSEP - a DC load flow simulator of cascading (separation) in power systems developed primarily by Paul Hines, at the University of Vermont, with contributions from Eduardo Cotilla-Sanchez, Pooya Rezaei, and Maggie Eppstein.
- Margaret J. Eppstein and Paul D. H. Hines. A "Random Chemistry" Algorithm for Identifying Collections of Multiple Contingencies that Initiate Cascading Failure. IEEE Transactions on Power Systems, vol. 27, no. 3, 2012.
- Pooya Rezaei, Paul Hines and Margaret Eppstein, Estimating Cascading Failure Risk with Random Chemistry, IEEE Transactions on Power Systems, vol. 30, no. 5, 2015. http://arxiv.org/abs/1405.4213