Analytica Data Science SolutionsContact
Services
Work
Products
Company
ESC

↑↓ to move↵ to open

← All work

Case study

Predicting where a storm will break the grid — five days out

The utility could see a storm coming. What it could not see was which districts would fail, how badly, or where to put its crews before the first pole came down.

Client
A major US investor-owned electric utility
Sector
Energy · Utilities
Role
Subcontracted delivery
Period
2 years
reduction in outage times
15%reduction in outage times
forecast horizon
5 daysforecast horizon
model stages
2model stages

The problem

Storm response at a large utility is a staging problem. Crews, transformers, poles and wire have to be in roughly the right place before the weather arrives, because moving them afterwards is what turns a six-hour outage into a two-day one.

The utility had weather forecasts and it had asset records. What it did not have was anything connecting the two: no way to turn "a storm is coming" into "these districts will take damage, of roughly this magnitude, needing roughly these resources."

What we built

A two-stage predictive model, deliberately split so each stage answers one question and can be validated on its own.

Stage one — will it break?
Predicts the likelihood of damage occurring in a given district.
Stage two — how badly?
Predicts damage to specific grid assets within districts flagged by stage one.
Resource model
Converts predicted damage into the crews, materials and hours required — the output the operations team actually acts on.

Two stages, because the second one is expensive

Two-stage storm damage model over a service territoryA forecast cone crosses the utility's service territory, widening with lead time. Stage one scores every district for the likelihood of damage; the districts crossing the threshold are outlined. Stage two runs only inside those districts, scoring individual poles and transformers along the distribution feeders — and the predicted failures cluster under tree canopy, because in most storms something falls on the grid rather than the grid failing on its own. A resource model turns that into crews, materials and hours, up to five days before the storm arrives.SERVICE TERRITORYONE FLAGGED DISTRICTFORECAST TRACK · CONE WIDENS WITH LEAD TIMEEvery district scored. Most will be fine.FEEDER · POLES · CANOPY12 predicted failures, every one of them under canopy.STAGE 01 · WHICH DISTRICTSSTAGE 02 · WHICH ASSETSCREWS + MATERIALS STAGEDFORECAST ISSUEDSTORMUp to five days of lead time — long enough to move crews, not just to watch.
likelihood of damageflagged by stage 01predicted asset failureSplitting the model in two is the design decision worth noticing. Stage one is cheap and runs over the whole territory; stage two is expensive and runs only where stage one fired. That is what made asset-level prediction affordable to run daily — and it is why the answer arrives while there is still time to act on it.

The data

Weather feeds from multiple open sources, automatically ingested and prepared. Static asset data — the number, age and location of poles, transformers and other equipment exposed to a given storm track. And the geospatial layer that turns out to matter most: tree cover and soil moisture, because in most storms the grid does not fail on its own. Something falls on it.

How it was delivered

A cloud-hosted dashboard with interactive maps showing predicted damage by district, the resources required, and the hours to restore. Automated severe-weather alerts by email so the model reaches people who are not sitting in front of a dashboard at 4am.

Result

Outage times fell by 15%, with damage predicted up to five days ahead — enough lead time to stage resources rather than chase failures.

The number worth dwelling on is not the accuracy of the damage model. It is the five days. A model that is right on the morning of the storm is interesting; a model that is roughly right five days out is operationally useful, because that is how long it takes to move crews.

What are you trying to get right?

Tell us the decision you keep having to make with less certainty than you would like. We will tell you honestly whether the data you already have can support it — and if it cannot, we will say so on the first call rather than the third.

Start a conversation