Luka Ivanović

Luka Ivanović

Auto-generated profile, based on publicly available information

Luka Ivanović

Univerzitet u Beogradu Elektrotehnički institut Nikola Tesla Koste Glavinića 8a 11000 Beograd Srbija

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
Verified
Journal Article
Open access
PDF file
LILuka Ivanović
Luka Ivanović
Saša MilićSaša Milić
Saša Milić
ŽSŽivko Sokolović
Živko Sokolović
ARAleksandar Živorad Rakić
Aleksandar Živorad Rakić
A vital step toward a sustainable future is the power grid's incorporation of renewable energy sources. Wind energy is significant because of its broad availability and minimal environmental impact. The paper presents a comparative analysis of recurrent neural network algorithms and gradient boosting machines applied to time series data for the regression issue of estimating the active power generated by a wind farm. Gradient boosting algorithms combine the advantages of a few machine learning models (decision trees, random forests, etc.) to produce a powerful prediction model. In addition to conventional recurrent neural networks, the article deals with long short-term memory and gated recurrent unit as cutting-edge models for time series analysis and predictions. A comprehensive analysis was carried out on a large wind power generation data set.

1 January 2025
Verified
Conference Paper
Closed access
DNDragana Naumović-Vuković
Dragana Naumović-Vuković
Boris AntićBoris Antić
Boris Antić
NMNevena Malešević
Nevena Malešević
LILuka Ivanović
Luka Ivanović
Critical thinking in science means the ability to distinguish facts from assumptions, analyzing data without bias, and asking questions that lead to deeper understanding. Through critical thinking, scientists make discoveries that change our perspective on the world. Critical thinking represents the foundation upon which the entire scientific method is built. Without the ability to think critically, scientific progress would be significantly limited, and our ability to solve problems, innovate, and build a sustainable future would be diminished. NANO-THINK project (Teaching critical thinking in science through nano-learning and virtual exchange principles) is dedicated to developing a specialized learning program that actively encourages the development of critical thinking in various scientific disciplines. By utilizing distance learning technology and concept of nano-learning, the project aims at providing an efficient and unique learning experience. This paper presents key results of the GAP analysis conducted on a sample of 585 students and 218 teaching staff from Serbia, Croatia, Montenegro and Bosnia and Herzegovina, as well as further steps in this project. The activities are implemented in partnership involving the following institutions: Faculty of Health Studies from Rijeka, which is also the project coordinator, the Nikola Tesla Institute from Belgrade, University of Donja Gorica, Medical Faculty from Graz, International Burch University, the Verlab Institute from Sarajevo, company B-Solutions from Tivat and the International Academy of Science and Arts in Bosnia and Herzegovina.

1 January 2024 in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
Verified
Journal Article
Open access
PDF file
IKIlija Klasnić
Ilija Klasnić
SVSlavko Veinović
Slavko Veinović
DJDušan Joksimović
Dušan Joksimović
LILuka Ivanović
Luka Ivanović
BRBojan Radojičić
Bojan Radojičić
MBMiloš Brdarević
Miloš Brdarević
This paper investigates a grid outage event at TPP "Nikola Tesla B" Unit B1 and analyzes the excitation system's response. Based on this analysis, modifications were made to the underexcitation limiter within the excitation system. The paper details the structure of the multi-segment straight-line limiter and its implementation methodology. The limiter's implementation was refined using recordings of the outage event and a detailed analysis of the excitation system's behavior. Additionally, the paper discusses the filtering of input measurements (stator voltage and generator active power) and the variable gain mechanism of the limiter. Finally, the paper presents the results of testing the modified limiter during grid operation, demonstrating stable behavior with damped oscillations.

1 January 2026 in Електропривреда = Electric Power Industry Journal
Verified
Journal Article
Open access
ДЈДушан Јоксимовић
Душан Јоксимовић
ЂСЂорђе Стојић
Ђорђе Стојић
НМНемања Милојчић
Немања Милојчић
ЗЋЗоран Ћирић
Зоран Ћирић
СВСлавко Веиновић
Славко Веиновић
ДТДушан Тришић
Душан Тришић
Проточна хидроелектрана и реверзибилна хидроелектрана (РХЕ) „Бајина Башта” у Перућцу представљају највеће хидроенергетске објекте изграђене на реци Дрини. РХЕ „Бајина Башта” има велики значај за електроенергетски систем Србије због могућности рада у генераторском и моторном режиму, чиме повећава флексибилност система са аспекта управљања производњом и потрошњом. Такође, због своје могућности да брзо стартује и брзо промени режим рада из генераторског у моторни и обрнуто, ова електрана може брзо да реагује на поремећаје у систему и замени било који други агрегат у систему „Електропривреде Србије”. Самим тим, и ревитализација РХЕ „Бајина Башта”, која треба да продужи животни век агрегата за неколико деценија, има велики значај за електроенергетски систем. Током 2024. ревитализован је први агрегат, док је ревитализација другог агрегата завршена 2026. У оквиру ревитализације су замењени и комплетни побудни системи. У оквиру енергетског дела система побуде уграђене су квалитетне компоненте: побудни трансформатори, прекидачи, тиристорски мостови, опрема за демагнетизацију итд. Основу управљачког дела система побуде чине сертификовани дигитални регулатори побуде у оквиру којих су реализовани секвентни аутомати за све режиме рада агрегата: генераторски режим, моторни режим, синхрони старт и електрично кочење. Регулатори омогућавају различите режиме регулације: аутоматска регулација напона статора, реактивне снаге или фактора снаге уз интегрисане лимитерске функције и стабилизатор електроенергетског система. Поузданост система додатно је осигурана редундантном имплементацијом тиристорских мостова и регулатора побуде у конфигурацији 1+1. Након завршене монтаже и повезивања комплетне опреме, спроведена су детаљна подешавања и испитивања система побуде, која су показала добре перформансе система. Ово гарантује поуздан и стабилан рад агрегата у свим предвиђеним режимима, уз аутоматско ограничење рада унутар дефинисаних граница погонског дијаграма.

1 January 2025
Verified
Conference Paper
Closed access
DJDušan Joksimović
Dušan Joksimović
DSdjordje stojic
djordje stojic
ZĆZoran Ćirić
Zoran Ćirić
SVSlavko Veinović
Slavko Veinović
LILuka Ivanović
Luka Ivanović
MPMiroslav Pavićević
Miroslav Pavićević
The Bajina Bašta hydropower plant and the Bajina Bašta pumped-storage hydropower plant in Perućac are the largest hydroelectric facilities built on the Drina River. The Bajina Bašta pumped-storage hydropower plant is of great importance to the Serbian power system due to its ability to operate in both generator and motor modes, which increases system flexibility in terms of production and consumption management. Periods of low electricity consumption are used to fill the upper reservoir by operating the plant in motor mode. When the system requires additional energy, the units switch to the opposite mode, and by releasing water from the higher-altitude reservoir, the turbines are driven to generate electricity. Also, due to its ability to quickly start and quickly change the operating mode from generator to motor and vice versa, this plant can quickly respond to system disturbances and replace any other unit in the Elektroprivreda Srbije system. Therefore, the revitalization of the Bajina Bašta pumped-storage hydropower plant, which should extend the lifespan of the units by several decades, is of great importance to the power system. In 2024, the first unit was revitalized, while the revitalization of the second unit is planned for 2025. The Nikola Tesla Institute participated in the revitalization by replacing the excitation systems. Within the energy part of the excitation system, components with top performance were installed: excitation transformers, switches, thyristor bridges, demagnetization equipment, etc. The basis of the control part of the excitation system consists of certified INTROL excitation regulators, within which sequential automats for all operating modes of the units were implemented: generator mode, motor mode, synchronous start, electric braking, and test for testing purposes. INTROL regulators enable various control modes: automatic stator voltage regulation, automatic reactive power regulation, and automatic power factor regulation, along with which limiter functions and a power system stabilizer were implemented. Thyristor bridges and excitation regulators are implemented redundantly in a 1+1 configuration. After installation and connection, the excitation system was adjusted and tested, which showed good system performance, enabling reliable and stable operation of the units in all operating modes with automatic limitation of operation within the limits defined by the operating diagram.

1 January 2025
Verified
Conference Paper
Closed access
EBElektrotehnički Institut Nikola Tesla Beograd
Elektrotehnički Institut Nikola Tesla Beograd
LILuka Ivanović
Luka Ivanović
IKIlija Klasnić
Ilija Klasnić
Saša MilićSaša Milić
Saša Milić
Wind turbines are inherently intermittent energy sources that predominantly depend on meteorological conditions. Accurate prediction of wind turbine active power generation is crucial for optimizing the operation of modern power systems rich in renewable energy sources, improving system stability, enhancing the efficiency of production and consumption balancing, optimizing the electricity market, and numerous other aspects. The development and application of advanced artificial intelligence and machine learning (ML) methods can further increase prediction accuracy, enabling the system to better adapt to the variable nature of wind energy. This paper investigates the efficiency of two machine learning approaches for predicting wind turbine active power, focusing on ML models based on recurrent neural networks (LSTM and GRU) and Transformer models adapted for processing and predicting time series data. Transformer models have recently gained prominence in time series analysis due to their ability to effectively recognize long-term dependencies in data through the self-attention mechanism, enabling parallel sequence processing and more accurate identification of relevant patterns in the data. The choice of transformer model architecture and parameter tuning is conditioned by two iterative processes. The validation of the developed ML model is performed using a practical open-source dataset that contains a large number of input features related to meteorological and operational system parameters. The selection of the most relevant features is based on their correlation with the target variable (in this case, active power), reducing the dimensionality of the problem and improving model efficiency. The experimental evaluation includes an analysis of model performance using standard metrics (RMSE and MAEI), while simultaneously examining the transformer architecture and its parameter set. The obtained results provide insight into the advantages and limitations of both approaches in various scenarios of short-term and long-term prediction, with the aim of improving broader prediction strategies and optimizing wind farm operations.