SolarSTARTS: Solar-Assisted State-Aware and ResilienT Infrastructure Systems



The incorporation of distributed energy resources (DER), automation, remote control, and data acquisition technologies has the potential to enhance the capability of the power grid to withstand high-impact events (e.g., faults caused by natural disasters) that can adversely affect the continuous supply of electricity to customers, incurring substantial economic losses. The growing use of communication networks and digital devices, however, has made power distribution systems vulnerable to cyberattacks.

Our research develops and demonstrates the integrated, scalable and cost-effective automated resilience management system (ARMS) solution for enhancing the resilience of U.S. critical infrastructure by improving the situational awareness and flexibility of solar PV systems. The proposed solution integrates a variety of modules and technologies to collect, analyze, and visualize data from multiple monitoring and control devices, classify different types of anomalies such as faults and cyberattacks, intelligently restore electricity exploiting PVs and energy storage, and facilitate the response capabilities of system operators.


  • FALCON: Fault and Attack Location and Classification
    FALCON is a technology that is able classify and localize cyber and physical anomalies, including false data injection attacks on protection devices, replay attacks on communication networks, and physical faults on distribution lines. FALCON takes as input monitoring and control signals from protection relays and fault indicators, which are fed into a deep neural network that classifies and identifies the location of the fault and attacks in the distribution system.

  • IRC: Intelligent Resilient Controller
    This technology utilizes deep reinforcement learning to develop an intelligent resilience controller (IRC) that devises fast real-time operation decisions to strategically dispatch distributed generation and energy storage units for restoring power to customers after sudden outages. The proposed IRC learns the failure development pattern of uncertain high-impact events and is able to explore a large action space in the partially observable state space of distribution grids under widespread outages.