Utilities are faced with increasing pressure to cut costs while maintaining reliability and reducing risk. Most still approach age-old problems with tried-and-true solutions. They trim vegetation on a set schedule, they address gas-leak issues only when they become a problem, and they don’t plan proactively for predicted storms and their potential impacts.
Traditional risk management approaches now have risk managers scrambling, mainly because of climate change and the severe weather it’s unleashing. Utilities can’t afford to keep doing what they’ve always done.
The good news is through data science and machine learning, there’s a better way to get ahead of outages and manage risk. We call it the three Ps of outage management: prevention, prediction, and proactive communication.
Check out our recorded webinar, where data science expert Tom Martin covered how E Source can help your utility reduce operating costs and improve grid reliability through better vegetation management.
Prevent vegetation-induced outages
Managing vegetation and tree growth around power lines is an important utility responsibility. It plays a critical role in mitigating fire hazards and ensuring grid reliability, but it’s costly when done inefficiently.
Traditionally, utilities have handled vegetation management with a recurring schedule. This has worked well enough, but that was before advances in predictive data science. It’s inefficient to treat all areas of the grid as equal in terms of vegetation management. Now, we have the technologies to reevaluate traditional approaches to vegetation management through granular data analysis, which will help utilities achieve operational efficiencies and save money.
Our vegetation management module displays a view from above, representing individual trees mapped onto the grid. By combining methodologies from environmental science, forestry, statistics, and computer science with historical utility data such as outage records, asset types, maintenance and inspection records, and lidar scans, our AI and machine learning models calculate a vegetation risk score. With this score, you can better prioritize vegetation management to the most at-risk areas. Budget planners can also use our risk scores and propensity models to forecast the effects of initiatives like spraying a certain herbicide or postponing the removal of hazard trees.
Predict storm impacts to better allocate resources
In the most extreme storm events, a utility’s storm-response team is tasked with appropriately allocating resources before the storm. They need to predict how many crews to send out, where to send them, and whether other utilities might need mutual aid.
But predicting the number of expected outages and the resources needed to restore power is extraordinarily difficult. Weather forecasts are complex, and the interaction with vegetation and utility infrastructure plays a huge factor in outage predictions. But E Source can help.
Our storm outage model is a real-time, data-driven outage prediction system that determines when and where outages will occur. Our modeling approach is comprehensive, collaborative, and configured specifically to the utility.
E Source Data Science builds a model on data that incorporates the relative risk from vegetation, infrastructure, terrain, geography, and inspection history and integrates it with high-resolution numerical weather prediction models. This delivers a more accurate prediction of hourly, location-specific outages up to 24 hours before storm impact.
Proactively communicate to improve the customer experience
Even with the advances in data science, outages will still occur. You need to have solid plans in place to provide customers with the best experience. During outages, customers want proactive, clear, and frequent updates so they can work around the outage. Put together a plan for:
- How quickly you’ll notify customers
- How often you’ll provide updates
- What information you’ll include
Proactive communication is the most effective way to reduce strain on the contact center during an outage while also easing customer concerns. The best way to accomplish this is by streamlining your internal systems, processes, and communications—for example, using an outage management system (OMS). Doing so will help you give customers faster, more-accurate, and more-frequent updates during unplanned outages.
The City of Palo Alto Utilities (CPAU) uses an OMS to share updates with customers and the media. When large outages happen, the operator team—in conjunction with the OMS—sends outage information via text message and email to a distribution list that includes the utility’s communications manager and key account reps. Customer service reps also receive updates and follow progress via CPAU’s outage map to keep customers informed of restoration efforts. And the communications manager updates social media accounts and the website during and after all outage incidents.
Earlier this year, we looked through the E Source Website Benchmark and reviewed eight utilities’ websites at random to learn which channels they use to notify customers about an outage and what information they provide.
Channels and content of eight utilities’ public-facing outage alert websites
| Utility | Text message | Phone call | Expected time of restoration | Status update | Cause | Notice of restoration | Lets users exclude time periods for receiving alerts | |
|---|---|---|---|---|---|---|---|---|
| © E Source (Website Benchmark and utility websites) | ||||||||
| Alabama Power | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| Alliant Energy | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | |
| ComEd | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ||
| FPL | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | |
| Hydro One | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | |
| MidAmerican Energy | ✔ | ✔ | ✔ | ✔ | ✔ | |||
| PSEG Long Island | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ||
| WPS | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ||
If you subscribe to the E Source Corporate Communications Service or Digital Self-Service, you can read more about this data in our report The essentials for communicating about unplanned and planned outages.
