Abstract

The heat load in district heating systems is affected by the weather and by human behavior, and special consumption patterns are observed around holidays. This study employs a top-down approach to heat load forecasting using meteorological data and new untraditional data types such as school holidays. Three different machine learning models are benchmarked for forecasting the aggregated heat load of the large district heating system of Aarhus, Denmark. The models are trained on six years of measured hourly heat load data and a blind year of test data is withheld until the final testing of the forecasting capabilities of the models. In this final test, weather forecasts from the Danish Meteorological Institute are used to measure the performance of the heat load forecasts under realistic operational conditions. We demonstrate models with forecasting performance that can match state-of-the-art commercial software and explore the benefit of including local holiday data to improve forecasting accuracy. The best forecasting performance is achieved with a support vector regression on weather, calendar, and holiday data, yielding a mean absolute percentage error of 6.4% on the 15–38 h horizon. On average, the forecasts could be improved slightly by including local holiday data. On holidays, this performance improvement was more significant.

Highlights

  • Energy systems are changing throughout the world, and heat load forecasting is gaining importance in modern district heating systems [1]

  • The heat load in district heating systems is affected by the weather and by human behavior, and special consumption patterns are observed around holidays

  • Real weather forecasts were used as weather inputs for 4 May, as opposed to the historical weather data used for training

Read more

Summary

Introduction

Energy systems are changing throughout the world, and heat load forecasting is gaining importance in modern district heating systems [1]. The growing penetration of renewable energy sources makes energy production fluctuate beyond human control and increases the volatility in electricity markets. It is not trivial to forecast district heating demand on time scales that are relevant for trading on the day-ahead electricity market. The total heat load in a district heating system is influenced by several factors—most importantly, the weather, the building mass of the city, and the behavior of the heat consumers. The constitution of the building mass influences how the heat load responds to changes in the weather [2]. Human behavior is an often overlooked factor, and, especially in summer, the heat demand is dominated by hot water consumption rather than space heating.

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call