Heat Load Prediction and Energy Systems Optimization
HeatFor (formerly known as PRESS-Prognosis) is a software system for forecasting of heat demand in district heating systems. HeatFor is a self-learning and self-calibrating system. It is based on machine learning, weather forecasts, historical demand and online measurements in order to automatically produce very accurate heat demand forecasts.
Why do you need HeatFor?
An accurate heat demand forecast enables efficient planning and operation of both production and distribution of district heating. Accurate demand forecasts are essential in order to optimize and plan production and utilize heat storage units. District heating network operators can also operate their network more efficiently and reliably by having an accurate heat demand forecast. The results are that security of supply is increased and costs are reduced at the same time. HeatFor automatically forecasts heat demand and requires minimal effort from the users.
As an additional environmental benefit, CO² emissions can also often be reduced by having a more accurate forecast and thereby a more efficient planning and operation of production assets and heat distribution network.
HeatFor can also be combined with a temperature optimization solution like HeatTO with additional advantages as costs reductions and increase of supply security for the heat-consumers.
- Automatically and accurately forecasts heat demand in district heating networks
- Increases security of supply for heat customers
- Easy and inexpensive to install, maintain and operate
- Reliable, stable and high availability with a proven operational track record of 20 years
- Low maintenance with minimal interference and interaction required for the client
- Highly flexible. Can be configured to various network configurations with and without dependencies between the networks
- Can easily be integrated with the HeatTO solution and provide additional reductions in heat and fuel costs
- HeatFor is an industry leading solution which requires minimal effort from the client and yet yields superior forecast accuracy when compared to competing technologies.
How Does HeatFor Work?
HeatFor is a self-learning system based on machine learning. On the basis of measurements from the district heating system, local weather stations and meteorological forecasts, the system is not only able to predict the heating demand but can also automatically and continuously improve its predictions as it is fed more data. Based on input data HeatFor automatically identifies and takes the systematic behavior of heat consumers into account. This means that HeatFor continuously adapts to the actual situation by continuously monitoring the consumption and automatically adapts to changes, such as:
- Changes in consumer behavior
- Changes in the number of consumers
- Changes in the meteorological models
- Changes in the thermal characteristics of the buildings
- Changes in the district heating network
The self-learning mechanism has the benefit, that it is not necessary to establish and maintain a complex physical description of the heating network, which is often time consuming. HeatFor will identify the impact of such changes by itself and quickly adapt.
Heat demand/load forecasting is complicated by the fact that the dynamics of buildings seriously affect the heat demand on an hourly basis. HeatFor system automatically applies an optimal smoothing effect which solves this issue, such that the physical properties of the underlying energy system are modeled correctly.
Ideally (but optionally) HeatFor is deployed in combination with MetFor (ENFOR service for locally optimized weather forecast) to obtain a more accurate local weather forecast, which will result in superior heat demand forecast accuracy.
HeatFor is provided as an integrated service from the ENFOR platform also which contains a data collection and validation module. The data collection and validation module collects the necessary data, ensures that the necessary data is available and contains a toolbox for automatic detection and correction of missing and/or erroneous measurements. The module then feed the validated data into the core HeatFor module which then provides the forecasts.
The ENFOR platform also provides HeatFor with data integration modules through either FTP, SFTP or web-services such that HeatFor can be seamlessly integrated with the operational system (SCADA) controlling the district heating system. System integration is provided by one of the HeatFor system integration partners.
HeatFor can be installed locally on customer systems or hosted by ENFOR as a service. It is also possible to get a customized support and maintenance agreement from ENFOR or one of the partner companies.
The following key features are provided by HeatFor:
- Self-learning and self-calibrating algorithms for accurate forecasting of heat demand in district heating systems
- Integrates seamlessly with: SCADA systems for retrieval of heat production data
- Local weather measurements
- Locally optimized weather forecasts (ideally provided by MetFor)
- HeatTO for temperature optimization of district heating networks
- Web-interface available for configuration and monitoring of system
- Data integration interfaces based on FTP, SFTP or web-services supporting numerous formats and file types (CSV, XML, SOAP, JSON etc.)
- Runs on all commons server platforms (Windows, Linux)
Wind power prediction for wind farms
Solar power prediction for PV plants
Electricity load prediction of electrical power systems