Effectively scheduling utility crews to inspect and repair grid assets is critical to ensuring grid health and minimizing customer outages. Whether repair crews are proactively addressing detected anomalies or being dispatched to resolve reported outages, landing on an optimal route and schedule for the day is not a simple task. Out-of-the-box routing algorithms do not account for the nuanced objectives and constraints unique to utility crews, driving the need for custom algorithm development that can handle the particulars of the problem at hand.
In this session, Mosaic explores the value of taking a holistic approach to tackling problems with data science. We explore the integration of machine learning and mathematical optimization to solve challenging scheduling problems. We also look at the value of integrating third-party data into custom algorithms to provide better recommendations to operational decision-makers.