| Title | Deep Reinforcement Learning for Mitigating Cyber-Physical DER Voltage Unbalance Attacks |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Roberts, Ciaran, Ngo, Sy-Toan, Milesi, Alexandre, Scaglione, Anna, Peisert, Sean, Arnold, Daniel |
| Conference Name | 2021 American Control Conference (ACC) |
| Keywords | attack surface, Inverters, Libraries, Metrics, Performance gain, Power systems, pubcrawl, reinforcement learning, resilience, Resiliency, Scalability, Sensitivity, Training |
| Abstract | The deployment of DER with smart-inverter functionality is increasing the controllable assets on power distribution networks and, consequently, the cyber-physical attack surface. Within this work, we consider the use of reinforcement learning as an online controller that adjusts DER Volt/Var and Volt/Watt control logic to mitigate network voltage unbalance. We specifically focus on the case where a network-aware cyber-physical attack has compromised a subset of single-phase DER, causing a large voltage unbalance. We show how deep reinforcement learning successfully learns a policy minimizing the unbalance, both during normal operation and during a cyber-physical attack. In mitigating the attack, the learned stochastic policy operates alongside legacy equipment on the network, i.e. tap-changing transformers, adjusting optimally predefined DER control-logic. |
| DOI | 10.23919/ACC50511.2021.9482815 |
| Citation Key | roberts_deep_2021 |
Deep Reinforcement Learning for Mitigating Cyber-Physical DER Voltage Unbalance Attacks