No abstract

No abstract

The paper proposes an approach to predict the temperature in the rooms of a public building. The model of the building is described by the average temperatures in its rooms, the characteristics of external walls and heating elements. Weather conditions are determined by the temperature, speed and direction of the wind. The state of the thermal unit is described by the temperature of heat agent at the inlet and outlet of a heat supply system, as well as the flow rate. To build a predictive model, it is necessary to identify a nonlinear dependence of the temperature inside the room on these parameters. This problem is solved using a recurrent artificial neural network. The network based on gated recurrent unit was selected as the base for the network architecture in this approach. The features of this structure allow to take into account the sequence of data without using excessive parameters. To train the model and predict temperature values, measurement sequences of different lengths were used to determine the most effective model. The number of blocks corresponds to the length of the time series. The state of the network on the last block is a predicted temperature.

No abstract

The efficiency of using thermal energy that is received from the central heating system to supply a building (a complex of interconnected rooms) is determined by the completeness of information available on the factors that affect the thermal regime. This article presents an approach that allows evaluating the significance for thermal management of such complex parameters as thermal inertia of a room and features of its use. The proposed methodology is based on the analysis of the dynamics of temperature changes in rooms, considering the standard characteristics that determine heat exchange, meteorological conditions, and the presence of people. The degree of the thermal inertia influence on a room is determined on the lag time, which is the time interval between a significant change in weather conditions or the supply of thermal energy and a change in the air temperature in the room. The initial data included the values of the temperature of the air and heating elements, that were obtained from the sensors located in a university building. The observation was conducted between 1 March and 19 April 2020 (measurement frequency — 10 minutes). The collected data consist of measurements gathered during room usage in different modes. Additionally, the presence of periods of complete shutdown of the heating system also affected the respective data. The module of the intelligent monitoring system for the thermal regime of the building was developed to perform data analysis. The module was implemented as a pipeline that sequentially performs the following operations: filtering and cleaning data; aggregation for specified periods; determination of the delay time. The results of the data analysis show the possibility of selecting groups of rooms that react to significant changes in external conditions and heating mode with a remarkable lag time. This confirms the importance of considering the thermal inertia for efficient heating control (intermittent operation). The results allow concluding that it is possible to build a classification model based on the thermal inertia parameter. These models will help in determining the most significant factors affecting the thermal regime of the room. In its turn, it allows producing recommendations for making decisions on heat supply management.