Sensor-driven maintenance and operations scheduling in energy systems revolves around coordinating fleet-level electricity production with sensing and asset monitoring to help support maintenance decisions and constrol asset loading.
What makes this setting intersting is the presence of unique interactions and dependencies among generation assets, which are typically driven by different physical phenoomena and complex constraints such as power flow, degradation and operational limits.
In this talk, we will present a unified framework that embeds predictive degration models pertaining to the energy assets within decision optimization models to jointly solve operations and maintenance in variety of energy system settings. We will demonstrate decision making and AI mechanisms to address challenges associated with uncertainty modeling, scalability and privacy. Using classic benchmarks from the IEEE community coupled with real-world sensor data, we will illustrate some of the considerable cost and reliability improvements relative to existing state-of-the art approaches.
Speaker(s): Murat Yildirim,
Agenda:
7:00 pm – Introduction and Opening remarks
7:10 pm – Presentation starts
8:15 pm – Presentation ends
8:20 pm – Questions & Answers
8:50 pm – Closing remarks
9:00 pm – Meeting ends
Virtual: https://events.vtools.ieee.org/m/477621