Search Results (3)

The current energy crisis raised concern about the lack of electricity during the wintertime, especially that consumption should be cut at peak consumption hours. For the building owners, this is visible as rising electricity prices. Availability of near real-time data on energy performance is opening new opportunities to optimize energy flexibility capabilities of buildings. This paper presents a reinforcement learning (RL)-based method to control the heating for minimizing the heating electricity cost and shifting the electricity usage away from peak demand hours. Simulations are carried out with electrically heated single-family houses. The results indicate that with RL, in the case of varying electricity prices, it is possible to save money and keep the indoor thermal comfort at an appropriate level. Full article

The availability of near-real-time data on energy performance is opening new opportunities to optimize buildings’ energy efficiency and flexibility capabilities and to support the decision-making and planning process of building retrofitting infrastructure investment. Existing tools can support retrofitting design and energy performance contracting. However, there are well-recognized shortcomings of these tools related to their usability, complexity, and ability to perform calculations based on the real-time energy performance of buildings. To address this gap, the advanced retrofitting decision support tool is developed and presented in this study. The strengths of our solution rely on easy usability, accuracy, and transparency of results. The automatic collection of real-time building energy consumption data gathered from the building management systems, combined with data analytics techniques, ensures ease of use and quickness of calculation. These results support step-by-step thinking for retrofitting design and hopefully enable a larger utilization rate for deep building retrofits. Full article

Accurate short-term forecasts of building energy consumption are necessary for profitable demand response. Short-term forecasting methods can be roughly classified into physics-based modelling and data-based modelling. Both of these approaches have their advantages and disadvantages and it would be therefore ideal to combine them. This paper proposes a novel approach that allows us to combine the best parts of physics-based modelling and machine learning while avoiding many of their drawbacks. A key idea in the approach is to provide a variety of building parameters as input for an Artificial Neural Network (ANN) and train the model with data from a large group of simulated buildings. The hypothesis is that this forces the ANN model to learn the underlying simulation model-based physics, and thus enables the ANN model to be used in place of the simulator. The advantages of this type of model is the combination of robustness and accuracy from a high-detail physics-based model with the inference speed, ease of deployment, and support for gradient based optimization provided by the ANN model. To evaluate the approach, an ANN model was developed and trained with simulated data from 900–11,700 buildings, including equal distribution of office buildings, apartment buildings, and detached houses. The performance of the ANN model was evaluated with a test set consisting of 60 buildings (20 buildings for each category). The normalized root mean square errors (NRMSE) were on average 0.050, 0.026, 0.052 for apartment buildings, office buildings, and detached houses, respectively. The results show that the model was able to approximate the simulator with good accuracy also outside of the training data distribution and generalize to new buildings in new geographical locations without any building specific heat demand data. Full article