MSMirko Stojiljkovic

Mirko Stojiljkovic

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mirko Stojiljkovic has a total of 63 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-objective optimisation of deep energy retrofit strategies for a school building

    by Vladan Jovanović, Mirko Stojiljković, Marko Ignjatović, Dušan Ranđelović, Aleksandar S. Anđelković

  • COMPARISON AND ENHANCEMENT OF THE SURROGATE MODELS THAT PREDICT THE ENERGY CONSUMPTION OF BUILDINGS

    by Mirko Stojiljković, Vladan Jovanović, Dušan Ranđelović, Marko Ignjatović, Goran Vučković

    Building energy consumption is related to a large share of the primary energy consumption on the global level. Energy retrofit of buildings, which might involve improving envelopes, as well as installing efficient energy supply systems based on the renewable energy sources, has a potential to considerably reduce the consumption of energy and the environmental impact. An accurate assessment of the energy efficiency measures is essential for careful planning and decision making related to their implementation. Detailed building energy simulations have became widely-used tools for the assessment of these measures. The optimization of energy system design and operation parameters is often a very useful addition. However, this approach is often time-consuming and resource-intensive, and, as such, is being replaced or supplemented with much faster, yet precise enough, so called surrogate models. These models are data-driven and based on machine learning techniques. This paper considers the enhancements of the previously-defined surrogate models for the assessment of the energy retrofit measures, including envelope improvements, and the installation of photovoltaic systems and heat-pump-based heating and cooling. It applies supervised machine learning regression models, which are able to learn from a very limited number of data points, obtained with detailed simulations, and predict the primary energy consumption related to particular measures. The models are based on decision trees and their ensembles: random forest and gradient boosting. They are further improved by implementing with linear regression, which uses modified input features, as well as with the optimization of hyperparameters. The presented approach is tested on a building of a primary school. It yielded the improvement in the prediction performance of the surrogate models of 64–75%, compared to the baseline models. The resulting models, although obtained with relatively small datasets, are accurate enough, so they can partially replace detailed building simulations and energy system optimization. The most precise regression model is based on the combination of linear regression and gradient boosting.


  • Open Access

    The impact of surrounding structures on energy performance simulation of a primary school in Niš: Model refinement and simulation requirements

    by Vladan S. Jovanović, Marko G. Ignjatović, Dušan J. Ranđelović, Mirko M. Stojiljković

    This paper investigates the influence of surrounding structures on the energy performance of a primary school in Niš, focusing on their impact on energy consumption and shading. The study uses a reference energy consumption value of 177 kWh/m², established in prior research, as a benchmark to assess the changes introduced by nearby buildings. The primary aim is to understand how these structures affect the building's energy efficiency, particularly the thermal envelope, and to identify potential errors in the energy assessment process. Comprehensive simulations evaluate the effects of surrounding buildings on the school’s energy balance, considering factors such as shading, light reflection, and airflow. The study also examines how these structures contribute to a building's overall sustainability and energy stability, providing insights into optimizing energy efficiency in dense urban areas. Several scenarios are modeled to identify the most effective strategies for reducing energy consumption, tailored to the specific climate and urban characteristics of Niš. The findings from this research will offer valuable guidelines for improving architectural designs and urban planning, emphasizing reducing energy usage in similar settings. Additionally, this study highlights the importance of refining simulation models in complex urban contexts to ensure accurate energy performance predictions. The results may serve as a foundation for further exploration into building energy efficiency and have practical implications for sustainable city development.

  • Open Access

    Exploring the efficiency of a residential air-to-water heat pump in summer changeover regimes based on exergy analysis: A case study

    by Goran Vuckovic, Mirko Stojiljkovic, Marko Ignjatovic, Branka Radovanovic

    Heat pumps meet the needs of the residential sector through the following three purposes: domestic water heating, space heating and cooling. This paper presents experimental research into the energy performance of an air-to-water heat pump in real summer changeover regimes, given that these are periods that significantly affect the reduction of efficiency. The transition regimes between the two regimes of operation with the most pronounced changes were especially considered. These were the transition regimes characteristic of operation in the summer period, namely: the transition from the space cooling regime to the domestic water reheating regime, and vice versa. In the observed period, the focus has been on 60 readings, with a resolution of 1 minute. In that period two changes in the operating mode were made, from the stationary space cooling regime (when the heat pump prepared water for the underfloor cooling at 17?C) to the domestic water reheating mode (when the heat pump prepared hot water in the tank at 43?C during the day), as well as switching to the previous, cooling mode. The research results show that in the observed period the heat pump worked in stationary regimes of space cooling and domestic water reheating, respectively, with average performance values of 3.52 and 4.75, and average exergetic efficiency of 6.93% and 33.38%.

  • Open Access

    Assessment of low energy potential of a school building using operation optimization and surrogate models

    by Mirko M. Stojiljković, Vladan S. Jovanović, Dusan Randjelovic, Goran D. Vučković, Marko G. Ignjatović

    The retrofit of existing buildings has a notable potential to save energy and reduce the environmental impact. This paper presents an approach to assess the primary energy saving potential related to the retrofit of a school building. The retrofit includes wall and roof insulation, fenestration replacement, installation of heat pumps with thermal storage, and usage of photovoltaic panels. The approach relies on building simulations and operation optimization evaluate a limited number of retrofit combinations. The results are used to formulate two kinds of surrogate models based on gradient boosting: classifier that finds feasible options and regressor that estimates the primary energy consumption. The results show high precision of the predictive models. The F1 score of the classifiers exceeds 0.99 even for very small training samples. The most important feature for estimating feasibility is the heat pump capacity. The coefficient of determination of the regressors is close to 1 and the root mean square error is lower than 1 kWh/m2, even for moderate sizes of the training set. The most important feature for predicting energy consumption is related to the area and orientation of photovoltaic panels.


  • Open Access

    Cost-optimal operation of hybrid heat pump systems with progressive electricity tariffs

    by Mirko M. Stojiljković, Goran D. Vučković, Marko G. Ignjatović

    Heat pumps are very significant for wide application of RES and sustainable heating. Their market penetration and extensive application depend on economic performance. Optimization of the operation parameters of energy systems with heat pumps can result in lower costs and higher savings. Heat pumps operate under different electricity pricing structures, which affect the optimization process. This paper presents a methodology for cost-optimal operation optimization of hybrid energy systems with heat pumps that can be used with progressive electricity tariffs and their combination with time-of-use tariffs. It relies on mixed integer linear programming and includes the constraints that handle electricity tariff rules. The paper illustrates an example of the application of this methodology to a heating system with an air-source heat pump and an auxiliary heater. The results show the impact of the energy prices and electricity tariff structures on the operating regimes and the values of the objective function. This approach can enhance the quality of the optimization results and improve the comprehension of cost-optimal operation regimes.


  • Open Access

    Performance assessment of an air-to-air heat pump with advanced technologies based on exergy analysis

    by Goran Vuckovic, Mirko Stojiljkovic, Marko Ignjatovic, Mica Vukic

    The buildings sector has a significant impact on the environment, considering that in addition industry and transport among the largest consumers of energy. Preservation of the external appearance of building fa?ades and high standards in terms of thermal comfort have led to the development of systems in which many indoor units can be connected to a single outdoor unit. Such systems are widely known as variable refrigerant volume/variable refrigerant flow systems. However, the constant need to increase energy efficiency has given rise to new technology, named variable refrigerant temperature. Here, the first and Second law approach of an air-source heat pump with modern control strategies which worked in the moderate continental climate was performed. To fully understand the processes, the total exergy destruction for every main component split unavoidable and avoidable part. The results show the biggest negative impact on exergy efficiency of observed system has internal ireversibilities in the speed control compressor with 17.4%. Destroyed work in other main components generated cumulative negative impact of 26.7% and the exergy losses reduced exergy efficiency by 33.5%. If the available modern technologies are applied, the 27% of destroyed useful work in compressor can be avoided, but the bigger part (73%) is unavoidable.

  • XAI4HEAT: Towards Demand-Driven, AI Facilitated Management of District Heating Systems

    by Milan Zdravković, Stevica Cvetković, Marko Ignjatović, Ivan Ćirić, Dejan Mitrović, Mirko Stojiljković, Valentina Nejković, Dušan Stojiljković, Rajko Turudija


  • Open Access

    Predicting heat demand of residential buildings with lag and time variables

    by Mirko M. Stojiljković, Marko G. Ignjatović, Goran D. Vučković, Vladan S. Jovanović

    Building heat demand depends on various parameters: the properties of the materials, geometry, climate conditions, occupancy patterns, usage habits, etc. Short-term forecasts of the heat demand can be based on different subsets of these parameters, depending on the application and available data. Recently, black-box models that apply machine learning methods became widely used to predict the heat demand. This paper is a part of a broader research effort and investigates the time-series prediction properties of a simple model based on the Random Forest regression that uses only lag and time-related variables as inputs. The time resolution is one hour. The lag variables are the heat demand one hour before, 24 hours before, and 25 hours before the time of prediction. The time-related variables are the hour of day, day of week, and month. The model has the coefficient of determination of over 0.99, root-mean-square error 38.2 kWh, and mean absolute error 19.1 kWh. The most important predictor is the 24-hours lag. Large errors occur mainly early in the morning and late in the evening, when the heat demand changes have high values and the setpoint temperatures are being modified.

  • Open Access

    Operational optimization of heating systems with air-source heat pumps based on realistic electricity tariffs

    by Mirko M. Stojiljković, Goran D. Vučković, Marko G. Ignjatović

    Heat pumps are among the crucial technologies for increasing renewable energy utilization in the building sector. One of the main factors for adopting heat pumps is their economic attractiveness, which depends on several factors. Air-source heat pumps are especially challenging in this regard because their performance relates significantly to the outdoor conditions. Optimization of operational regimes can lead to lower running costs of heating systems with heat pumps. However, most research efforts in this area are based on relatively simple pricing rules. This paper presents an attempt to perform operation optimization of a heating systems based on a realistic electricity pricing policy, applicable to the households in Serbia. The approach uses the results of detailed building simulations and existing rules for charging electricity as the inputs. It applies mixed integer linear programming to obtain the operation regimes that minimize the operational cost of a heating system over one year. The paper shows the comparison of the obtained results and the results drawn from simplified electricity pricing rules. Finally, it discusses the importance, applicability, and limitations of the presented approach.