Jelena Gavrilovic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jelena Gavrilovic has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Luka Jovanovic
Singidunum University
2 shared publications - Aleksandar Petrovic
Singidunum University
1 shared publication - Amirhossein Tahmouresi
Kerman University of Medical Science
1 shared publication Branko Kovačević
School of Electrical Engineering, University Belgrade, Bulevar kralja Aleksandra 73, 11000 Belgrade, Serbia
1 shared publication- Eva Tuba
Jožef Stefan Institute, Ljubljana, Slovenia
1 shared publication - Ivana Kostić Kovačević
Faculty of Informatics and Computing, Singidunum University, 32 Danijelova St., Belgrade, Serbia
1 shared publication
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 1-13
Forecasting Energy Production at Solar Substations Utilizing Gated Recurrent Units Models Tuned by Adapted Metaheuristics
- 2 January 2026
- Published by Springer Nature
- p. 1-13
Forecasting Energy Production at Solar Substations Utilizing Gated Recurrent Units Models Tuned by Adapted Metaheuristics
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 189-194
Forecasting Domestic Solar Power Production via Recurrent Networks Tuned by a Modified Metaheuristic
The world's ever-increasing need for energy demands innovation and resourcefulness from engineers and power companies. Reducing transportation losses and providing reliable power are just some of the challenges facing power production from renewable resources. Nevertheless, addressing these challenges is essential for improving sustainability and slowing down climate change. The sporadic nature of power production from solar panels makes it difficult to integrate into existing power grid infrastructure. A robust forecasting system could help mitigate these issues. This study investigates the application of long short term memory (LSTM)-based neural networks to tackle production forecasting. Since forecasting models rely on proper hyperparameter selection, this study presents a modified optimizer for hyperparameter tuning to improve performance. Simulations on real world data have shown promising results, with LSTM based networks optimized by a modified metaheuristic based on the PSO showcasing favorable outcomes with a mean absolute percentage error (MAPE) as low as 4.112%.
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 189-194
Forecasting Domestic Solar Power Production via Recurrent Networks Tuned by a Modified Metaheuristic
The world's ever-increasing need for energy demands innovation and resourcefulness from engineers and power companies. Reducing transportation losses and providing reliable power are just some of the challenges facing power production from renewable resources. Nevertheless, addressing these challenges is essential for improving sustainability and slowing down climate change. The sporadic nature of power production from solar panels makes it difficult to integrate into existing power grid infrastructure. A robust forecasting system could help mitigate these issues. This study investigates the application of long short term memory (LSTM)-based neural networks to tackle production forecasting. Since forecasting models rely on proper hyperparameter selection, this study presents a modified optimizer for hyperparameter tuning to improve performance. Simulations on real world data have shown promising results, with LSTM based networks optimized by a modified metaheuristic based on the PSO showcasing favorable outcomes with a mean absolute percentage error (MAPE) as low as 4.112%.
- Open Access
- 1 December 2015
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 22 (6) , 1465-1474
Analysis of a class of adaptive robustified predictors in the presence of noise uncertainty
A new class of adaptive robust predictors has been considered in the paper. First an optimal predictor is developed, based on the minimization of a generalized mean square prediction error criterion. Starting from the obtained result, an...
- 1 December 2015
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 22 (6) , 1465-1474
Open AccessAnalysis of a class of adaptive robustified predictors in the presence of noise uncertainty
A new class of adaptive robust predictors has been considered in the paper. First an optimal predictor is developed, based on the minimization of a generalized mean square prediction error criterion. Starting from the obtained result, an...
- Open Access
- 1 January 2011
- Published by Taylor & Francis in Economic Research-Ekonomska Istraživanja
- Vol. 24 (2) , 99-111
Us American Versus German Activity-Based Costing. Effects on Business Decisions Management in Theautomotive Industry
This paper seeks to describe the role that activity-oriented cost accounting systems, i.e. US American and German activity-based costing, play in the establishment of supply-chainnetworks in the modern automotive industry. These costaccounting systems are the subject of analysis for two reasons: they relatively successfully describe the causality principle between cost drivers and cost objects and represent two different approaches of cost calculation within the activity-oriented concept. Also, the paper attempts to show that the efficiency of these systems is contingent on the value chain activity to which the systems were applied. Although based on identical conceptual frameworks, these systems do not have the same cost allocation purposes in automotive industry.
- 1 January 2011
- Published by Taylor & Francis in Economic Research-Ekonomska Istraživanja
- Vol. 24 (2) , 99-111
Open AccessUs American Versus German Activity-Based Costing. Effects on Business Decisions Management in Theautomotive Industry
This paper seeks to describe the role that activity-oriented cost accounting systems, i.e. US American and German activity-based costing, play in the establishment of supply-chainnetworks in the modern automotive industry. These costaccounting systems are the subject of analysis for two reasons: they relatively successfully describe the causality principle between cost drivers and cost objects and represent two different approaches of cost calculation within the activity-oriented concept. Also, the paper attempts to show that the efficiency of these systems is contingent on the value chain activity to which the systems were applied. Although based on identical conceptual frameworks, these systems do not have the same cost allocation purposes in automotive industry.