With the increase in frequency and duration of outages across the US, utilities struggle with effective communication of restoration plan to customers.

Exelon introduces their data-driven predictive algorithm to generate customer specific estimated time to restoration (ETR) that improves the speed of availability and accuracy of ETRs compared to existing methods. Exelon discusses the necessity to view ETR from the customer’s perspective, how historical and live outage data can be leveraged to predict accurate customer specific ETRs using advanced machine learning tools, the impact of accurate ETRs on customer satisfaction, and the change management processes required at utilities to replace existing ETR tools with analytic tools.

Session Takeaways:

• Necessity to view ETR from customer perspective rather than utility perspective.
• How historical and live outage data can be leveraged to predict accurate customer specific ETRs using advanced machine learning tools.
• Impact of Accurate ETRs on customer satisfaction.
• Change Management required at utilities to replace existing ETR tools with analytic tools.