To Örebro University

In the domain of building energy systems, many district heating control strategies rely on simplistic approaches that fail to account for the unique thermal characteristics of individual buildings. Traditional district heating control methods apply generic linear relationships between outdoor and supply temperatures, disregarding the significant variations in building-specific factors such as architectural design, geographical location, and occupancy patterns. These conventional approaches often result in substantial energy waste and suboptimal indoor comfort conditions. The challenge of optimizing energy consumption in residential buildings requires sophisticated methods that can adapt to diverse building characteristics while maintaining occupant comfort. Current prediction models treat buildings as homogeneous entities, leading to significant performance gaps between predicted and actual thermal behaviour. This limitation becomes particularly pronounced when attempting to develop control strategies that can generalize across different building types and geographical contexts. This dissertation addresses these challenges by developing a comprehensive framework for context-aware district heating optimization using advanced machine learning techniques. Context, in this work, refers to building-specific characteristics such as architectural design (building type, size, floors), and geographical location (climate zone, city) that uniquely influence each building’s thermal behavior and heating requirements. The approach systematically incorporates building-specific contextual information including rise type, geographical location, and architectural features into both predictive modelling and control optimization. We propose an adaptive context-aware transformer architecture that dynamically learns contextual representations through innovative embedding mechanisms, enabling the model to capture complex relationships between building characteristics and thermal behaviour patterns. Building upon these predictive foundations, we extend the framework to control optimization through two complementary approaches. First, we develop a context-enhanced district heating control system using dual-output prediction and multi-objective optimization that balances energy efficiency with comfort maintenance. Second, we introduce a novel reinforcement learning framework that integrates the adaptive context-aware transformer with Deep Q-Networks to discover optimal control policies without being constrained by historical control patterns. The outcome of this dissertation advances building energy systems through machine learning approaches that can adapt to individual building characteristics while optimizing across multiple objectives. Our proposed methods demonstrate how context-aware modelling can transform district heating systems from reactive, generic control to proactive, building-specific optimization. We evaluate and validate our methods experimentally in real-world scenarios across diverse building types and geographical locations, underscoring the effectiveness and practical applicability of our approaches for reducing energy consumption while maintaining occupant comfort.

As district heating networks evolve to meet climate-neutral objectives, optimizing their control under heterogeneous building characteristics and dynamic environmental conditions remains a significant challenge. Traditional control strategies often lack the adaptability necessary to account for building-specific dynamics and to ensure real-time adherence to operational safety constraints. In this work, we present an integrated machine learning-based framework that combines an adaptive context-aware transformer model with deep reinforcement learning to address these limitations. The proposed approach introduces an adaptive context-aware transformer as a predictive environment within a Deep Q-Network (DQN) framework, enabling data-driven, building-specific control of district heating systems. Utilizing real-world data from 148 residential buildings across Sweden and Finland, the model incorporates contextual embeddings and temporal features to predict indoor temperature trajectories with high accuracy, achieving root mean square error values between 0.18-0.24 degrees C for Swedish buildings and 0.26-0.32 degrees C for Finnish buildings. The DQN agent leverages these predictions to optimize heating control while ensuring compliance with operational safety limits and preserving occupant comfort. Experimental results demonstrate significant energy savings, with mid-rise buildings achieving up to 14.85% reduction in energy consumption, and peak seasonal savings exceeding 20% during spring months. This integrated approach illustrates the potential for substantial energy optimization and reliable indoor climate management in future district heating networks.

Transformer-based models have gained increasing popularity for time-series prediction; however, in specific applications such as residential heating systems, static contextual data of buildings is crucial to effectively capture and learn complex environmental dynamics. This paper presents a novel transformer-based model that adapts the contextual meta-data of residential buildings, generalizing across diverse environments. The model integrates temporal data with adaptive embedding of building-specific contextual meta-data such as geographic locations and building characteristics to dynamically learn and adapt to the variations. These adaptive context embeddings allow the model to comprehensively understand how different buildings respond to environmental changes over time. Initial results show improved accuracy and reliability in indoor temperature predictions of residential buildings, demonstrating the model’s potential to optimize district heating systems across a diverse array of residential buildings. This proposed model provides a basis for developing proactive heat management systems in buildings.

This paper presents a novel approach for predicting average indoor temperature in residential buildings, utilizing contextual factors of the rise of the building and geographical location. The proposed approach employs advanced deep learning architectures, such as Long Short-Term Memory (LSTM) and Transformers, to create generalized predictive models applicable to a range of residential buildings. The models are trained using historical data from 18 residential buildings over a period of 6 to 10 years, where the buildings are located in different climate zones. Testing is done on nine different data sets representing three different locations and three different types of buildings. The study demonstrates that incorporating the context of building rise significantly improves the models' predictive performance. Specifically, the transformer-based models show improvements in R2 of 4%-27% in a 6 h prediction horizon. The proposed approach explicitly using context information significantly improves the accuracy of predicting, making learnt models a good starting point for optimizing district heating distribution.

Energy optimization plays a vital role in decreasing the carbon footprint of residential buildings. In this paper, we present a prediction model of indoor temperature in residential buildings in three different case studies in different towns in Sweden. To predict the indoor temperature accurately, a dataset based on several years of data collection (up to 7 years) has been used. This paper applies both the traditional LSTM model as well as the more recent transformer model. The latter has been used because of its ability to perform a mechanism of self-attention that shows particular promise in multivariate sensor data. In addition to these algorithms, the data set is also modified based on contextual information and compared against an approach where no contextual information is used. Contextual information in this case takes into account the physical location of specific apartment units within the full residence and builds individual models based on the location of the unit. The results demonstrate that transformers are better suited for task of prediction, and that transformers combined with contextual information, provide a suitable approach for energy consumption prediction.