Describing the gas boiler fuel consumption as a time series gives the opportunity to use tools appropriate for the processing of such data to analyze this phenomenon. One of them are ARIMA models. The article proposes this type of model to be used for predicting monthly gas consumption in a boiler room working for heating and hot water preparation. The boiler supplies heat to a group of residential buildings. Based on the collected data, three specific models were selected for which the forecast accuracy was assessed. Calculations and analyses were carried out in the R environment using “forecast” and “ggplot2” packages. A good quality of the obtained forecasts has been demonstrated, confirming the usefulness of the proposed analytical tools. The article summary also indicates for what purposes the forecasts obtained in this way can be used. They can be useful for diagnosing the correct operation of a heat source. Registering fuel consumption at a level significantly deviating from the forecast should be a signal to immediately diagnose the boiler room and the heat supply system and to explain the reason for this difference. In this way, it is possible to detect irregularities in the operation of the heat supply system before they are detected by traditional methods. The gas consumption forecast is also useful for optimizing the financial management of the property manager responsible for the operation of the boiler room. On this basis, operating fees or financial operations with the use of periodic surplus capital may be planned.
The heat supply systems energy efficiency improvement requires the use of increasingly complex methods. The basic ways to reduce heat consumption is by using better thermal insulation, although they have more and more limited possibilities and need relatively large financial outlays. Good effects can be achieved by the better heat source adaptation to the conditions of a specific facility supplied with heat. However, this requires research that identifies the effectiveness of such solutions as well as the tools used to describe selected elements of the system or its entirety. The article presents the results of tests carried out for a gas boiler room supplying heat to a group of residential buildings. The goal was to build a model that would forecast the day range in which the maximum gas consumption occurs for a given day. Having measurements of gas consumption in subsequent hours of the day, it was decided to build a forecasting model determining the part of the day in which such a maximum would occur. To create the model the random forest procedure was used along with the mlr (Kassambara) package. The model’s hyperparameters were tuned based on historical data. Based on data for another period of boiler room operation, the results of the model’s quality assessment were presented. Close to 44% efficiency was achieved. Tuning the model improved its predictive ability.