The study is experimentally inclined, with a high target precision for performance measurement. A comprehensive programme of measurements was carried out in a two-storey building, having a massive structure and dating from 1970. Measurements were made continuously during the heating season from a total of about 70 points. Readings were taken every 30 seconds, and the mean values stored in a computer every 15 minutes. Analysis of the results have been concentrated on: * Thermal inertia, and particularly that of cooling mechanisms. * Time delays in heat flows through the building envelope in response to variations in ambient temperature. * The amount of solar input beneficially retained when operating with night setback and with normal operation. The results indicate that the building has both a long time constant, of about 200 h, and a short one, of about 1.5 h. The magnitude of the shorter time constant depends on the thermal capacity of the interior of the building (furniture, curtains etc.), and can be regarded as having some validity for other apartment building stock. Analyses of temperature gradients in the internal surfaces of the exterior walls indicate that the building's ventilation system, which was originally constructed as an exhaust air ventilation system, but with the inflow of fresh air blocked off, generates a dynamic insulation effect. Calculations indicate that this effect can provide a saving of 6 % of the total heating requirement, excluding that for domestic hot water. Investigation of the static heat requirement with and without night set-back indicate a considerable potential annual saving of heating energy, amounting to a maximum of 13 %, provided that the building is heated in accordance with a prescribed strategy. A 'comfort indoor temperature' has also been determined, being the temperature above which the occupants of the building consume excessive heating energy. Theoretical models have been derived to illustrate the short time constant and to analyse the dynamic insulation effect noted. / <p>Diss. Umeå : Umeå universitet, 1987</p> / digitalisering@umu

Energy efficiency of district heating systems is of great interest to energy stakeholders. However, it is not uncommon that district heating systems fail to achieve the expected performance due to inappropriate operations. Night setback is one control strategy, which has been proved to be not a suitable setting for well-insulated modern buildings in terms of both economic and energy efficiency. Therefore, identification of a night setback control is vital to district heating companies to smoothly manage their heat energy distribution to their customers. This study is motivated to automate this identification process. The method used in this thesis is a Convolutional Neural Network(CNN) approach using the concept of transfer learning. 133 substations in Oslo are used in this case study to design a machine learning model that can identify a substation as night setback or non-night setback series. The results show that the proposed method can classify the substations with approximately 97% accuracy and 91% F1-score. This shows that the proposed method has a high potential to be deployed and used in practice to identify a night setback control in district heating substations.