Forecast the heat load for each network
Forecast for 3 networks over 96 quarter-hours, peak of 41.2 MW at 07:15
Energy
a spreadsheet and experience.Open agent
Enlarge demo
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
Heat load depends on outdoor temperature, wind, day of the week and the inertia of the network. Operations management estimates it in advance for each network and then decides which plant runs when. If the estimate is too high, the peak load boiler runs for no reason; if it is too low, the boiler has to start up at short notice.
3
heating networks
Each network has its own inertia and its own customer mix.
5
generation plants
Two combined heat and power plants, a heating plant and two peak load boilers share the schedule.
96
quarter-hours
For each one, someone decides which plant covers the load.
180 hours
of peak load per heating season
The boiler runs when the estimate comes too late or is too rough.
The headline figure targets these 180 boiler hours: 30% fewer peak load hours per heating season.
The 30% reduction in peak load hours is this agent's headline figure. Networks, plants, quarter-hours and boiler hours reflect a typical heating season at a municipal utility and do not come from any measurement.
The agent forecasts the heat load for each network and proposes a schedule for the plants; nothing runs until operations management approves it.
Forecast for 3 networks over 96 quarter-hours, peak of 41.2 MW at 07:15
CHP 2 on base load from 04:30, boiler 2 on standby from 06:45
fahrplan_23-01-2026.csv, 5 plants, 2 changes from the previous day
The schedule remains a proposal in the control centre. Technical operations management approves it and carries out the switching.
If CHP 2 fails, it only notices once the report is in the control system. Until then, it works with the reported availability.
It takes the date maintenance enters for boiler 1 after the burner fault unchanged, and plans without the plant until then. *Maintenance reports in the control system whether the spare part delivery will meet that date.*
Connected systems
Network control centre's control system
load profile database
weather data service
Operations
Deployment model
Data processing
Responsible teams
How quickly is the Heat Load Forecast Agent ready to use?
Where is the data processed?
Where does the figure “30% fewer peak load hours” come from?
All agents
35%
less coordination effort
Production Management, Production Planning
40%
fewer delivery delays
Purchasing, dispatch, production
60%
less preparation time
Executive board, management
15%
higher efficiency
Plant operations, engineering
20%
better purchasing decisions
Purchasing, supply chain
50%
less reporting effort
Sustainability, management