Use case · Load Forecasting for Coincident Peak Demand

See the Peak Before It Costs You

DOTA AI builds a 7-day hourly load forecast from AMI, SCADA and weather, flags the likely peak hours, and plans the response.

Explainer video in production

The interactive walkthrough for See the Peak Before It Costs You is being produced. The full use case is below.

Illustrative data. No real utility names or plant names are used.

842 MW
Tomorrow's peak at 17:00
78%
Peak probability
2.1%
Day-ahead MAPE
Built for

Electric cooperatives and municipal utilities: power supply, operations, member services

The problem

One hour of monthly peak can set demand charges for the whole month, and calling demand response on the wrong day wastes programs and member goodwill.

With DOTA AI

DOTA AI builds a 7-day hourly load forecast from AMI, SCADA and weather, flags the likely peak hours, and plans the response.

How it works

From a question to a deployed app.

01

Ask

Forecast hourly system load for the next 7 days and flag likely monthly peak hours.

02

Connect

AMI/MDM, SCADA feeder load, weather forecasts, and calendar and holidays.

03

Forecast

A 7-day hourly forecast with P10 to P90 bands, and a pin on tomorrow at 17:00.

04

Plan

Stack the response and flatten the peak from 842 to 807 MW.

What you see
  • One hour sets the month's demand bill
  • Tomorrow 17:00: 842 MW, 78% chance of setting the monthly peak
  • Water heaters, batteries and a conservation call trim 35 MW off the peak
  • About $420K saved this month
  • One live forecast for every team
Source systems
AMI / MDMSCADA feeder loadWeather forecastsCalendar and holidays

The takeaway

See the peak coming.

Build see the peak before it costs you on your data.

See DOTA AI build a real utility app on your data in a 30-minute working session.