Dragana Krstic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dragana Krstic has a total of 104 co-authors. Here are the top co-authors by number of shared publications:
Petar Nikolic
Tigar Tyres, Serbia
12 shared publicationsMihajlo Stefanovic
University of Nis
11 shared publications- Suad Suljovic
Metropolitan University,Faculty of Information Technologies,Belgrade,Serbia
9 shared publications - Nenad Petrovic
Technical University of Munich
7 shared publications - Stefan Panic
University of Priština in Kosovska Mitrovica, Faculty of Natural Sciences and Mathematics, Kosovska Mitrovica
5 shared publications - Goran Stamenovic
Tigar, Pirot, Serbia
4 shared publications
Latest Publications
- Top Cited PapersOpen Access
LLM-Driven Approach for Safe and Secure Network Management by Design in IoT-Based Systems
This paper introduces an LLM-driven design-time workflow for Internet of Things (IoT) and network management system development that combines the generative and summarization capabilities of Large Language Models with the formal rigor of Model-Driven Engineering (MDE). The key novelty lies in grounding LLM-assisted topology design and network management, including reasoning about configuration code to formally verifiable models, enabling security- and safety-aware decisions by design with improved trust and explainability compared with black-box runtime solutions. The approach relies on activity-diagram-based models that provide formal semantics for capturing control flows, decision points, and interactions among IoT devices, edge nodes, and network management components, supporting systematic functional safety validation. Design-time security analysis is realized through MDE combined with Object Constraint Language (OCL) rules, allowing explainable detection of misconfigurations, policy violations, and potential vulnerabilities before deployment. The workflow is evaluated using representative IoT and mobile network management scenarios, demonstrating enhanced effectiveness and up to 15 times reduction in detection and corrective action time for critical tasks.
Top Cited PapersOpen AccessLLM-Driven Approach for Safe and Secure Network Management by Design in IoT-Based Systems
This paper introduces an LLM-driven design-time workflow for Internet of Things (IoT) and network management system development that combines the generative and summarization capabilities of Large Language Models with the formal rigor of Model-Driven Engineering (MDE). The key novelty lies in grounding LLM-assisted topology design and network management, including reasoning about configuration code to formally verifiable models, enabling security- and safety-aware decisions by design with improved trust and explainability compared with black-box runtime solutions. The approach relies on activity-diagram-based models that provide formal semantics for capturing control flows, decision points, and interactions among IoT devices, edge nodes, and network management components, supporting systematic functional safety validation. Design-time security analysis is realized through MDE combined with Object Constraint Language (OCL) rules, allowing explainable detection of misconfigurations, policy violations, and potential vulnerabilities before deployment. The workflow is evaluated using representative IoT and mobile network management scenarios, demonstrating enhanced effectiveness and up to 15 times reduction in detection and corrective action time for critical tasks.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
LLM-Driven Approach to Automated Sustainability of IoT Systems
Due to huge number and heterogeneity of devices within Internet of Things (IoT)-based architectures, scalability and maintainability of such systems rise many challenges when it comes to long-term sustainability, especially regarding scalability and maintainability aspects. In this paper, we explore state-of-art Large Language Model (LLM)-based techniques as well as Agentic AI approaches in order to automate these aspects and reduce the cognitive load and need for human intervention. As intermediary step for system representation, we leverage Model-Driven Engineering (MDE) approach in order to ensure verifiability. As outcome, two case studies relying on GPT-40 model are presented.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
LLM-Driven Approach to Automated Sustainability of IoT Systems
Due to huge number and heterogeneity of devices within Internet of Things (IoT)-based architectures, scalability and maintainability of such systems rise many challenges when it comes to long-term sustainability, especially regarding scalability and maintainability aspects. In this paper, we explore state-of-art Large Language Model (LLM)-based techniques as well as Agentic AI approaches in order to automate these aspects and reduce the cognitive load and need for human intervention. As intermediary step for system representation, we leverage Model-Driven Engineering (MDE) approach in order to ensure verifiability. As outcome, two case studies relying on GPT-40 model are presented.
- Open Access
- 13 March 2025
- Published by Qeios Ltd
Review of: "Higher-Order Meta Distribution Analysis of Wireless Systems with Application to the Reliability of UWB THz Networks"
I haven't really had the opportunity to encounter this topic until now. After reading the work, I can notice that the authors have given a precise mathematical analysis for a defined scenario of wireless systems and an application to the UWB THz netw...
- 13 March 2025
- Published by Qeios Ltd
Open AccessReview of: "Higher-Order Meta Distribution Analysis of Wireless Systems with Application to the Reliability of UWB THz Networks"
I haven't really had the opportunity to encounter this topic until now. After reading the work, I can notice that the authors have given a precise mathematical analysis for a defined scenario of wireless systems and an application to the UWB THz netw...
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (7) , 8049-8063
Secrecy Analysis and Optimization of UAV-Assisted IoT Networks With RF-EH and Imperfect Hardware
This paper introduces unmanned aerial vehicles (UAVs) assisted communication system for energy-constrained Internet of Things (IoT) devices. Herein, a power beacon transmits radio frequency (RF) signals to enable energy harvesting at the IoT devices (IoDs). The source IoD utilizes harvested energy to transmit information to the destination IoD through multiple UAV relays. Among multiple UAV relays, a selected UAV applies a decode-and-forward operation to relay the information to the destination. An eavesdropper near the destination IoD poses a threat to information secrecy. Consequently, the selected UAV injects artificial noise to degrade the accessibility of the eavesdropper’s link. For this setup, we employ a composite fading channel model by combining log-normal distribution for shadowing effects and Nakagami-m distribution for small-scale fading to evaluate system performance. Specifically, the compact expressions for secrecy outage probability and effective secrecy throughput (EST) are derived using the Gauss-Hermite quadrature method. Moreover, we conduct a trade-off analysis between reliability and security by factoring in outage and intercept probabilities. Lastly, we formulate an EST maximization problem by optimizing the system parameters and UAV’s locations under the outage and secrecy constraints. We propose a particle swarm optimization and continuous genetic algorithm-based hybrid algorithm for solving the non-linear optimization problem. The numerical findings demonstrate that the proposed algorithm outperforms the baseline algorithms regarding the achieved EST.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (7) , 8049-8063
Secrecy Analysis and Optimization of UAV-Assisted IoT Networks With RF-EH and Imperfect Hardware
This paper introduces unmanned aerial vehicles (UAVs) assisted communication system for energy-constrained Internet of Things (IoT) devices. Herein, a power beacon transmits radio frequency (RF) signals to enable energy harvesting at the IoT devices (IoDs). The source IoD utilizes harvested energy to transmit information to the destination IoD through multiple UAV relays. Among multiple UAV relays, a selected UAV applies a decode-and-forward operation to relay the information to the destination. An eavesdropper near the destination IoD poses a threat to information secrecy. Consequently, the selected UAV injects artificial noise to degrade the accessibility of the eavesdropper’s link. For this setup, we employ a composite fading channel model by combining log-normal distribution for shadowing effects and Nakagami-m distribution for small-scale fading to evaluate system performance. Specifically, the compact expressions for secrecy outage probability and effective secrecy throughput (EST) are derived using the Gauss-Hermite quadrature method. Moreover, we conduct a trade-off analysis between reliability and security by factoring in outage and intercept probabilities. Lastly, we formulate an EST maximization problem by optimizing the system parameters and UAV’s locations under the outage and secrecy constraints. We propose a particle swarm optimization and continuous genetic algorithm-based hybrid algorithm for solving the non-linear optimization problem. The numerical findings demonstrate that the proposed algorithm outperforms the baseline algorithms regarding the achieved EST.
- Open Access
MDE and LLM Synergy for Network Experimentation: Case Analysis of Wireless System Performance in Beaulieu-Xie Fading and κ-µ Co-Channel Interference Environment with Diversity Combining
Channel modeling is a first step towards the successful projecting of any wireless communication system. Hence, in this paper, we analyze the performance at the output of a multi-branch selection combining (SC) diversity receiver in a wireless environment that has been distracted by fading and co-channel interference (CCI), whereby the fading is modelled by newer Beaulieu-Xie (BX) distribution, and the CCI is modelled by the κ-µ distribution. The BX distribution provides the ability to include in consideration any number of line-of-sight (LOS) useful signal components and non-LOS (NLOS) useful signal components. This distribution contains characteristics of some other fading models thanks to its flexible fading parameters, which also applies to the κ-µ distribution. We derived here the expressions for the probability density function (PDF) and cumulative distribution function (CDF) for the output signal-to-co-channel interference ratio (SIR). After that, other performances are obtained, namely: outage probability (Pout), channel capacity (CC), moment-generating function (MGF), average bit error probability (ABEP), level crossing rate (LCR), and average fade duration (AFD). Numerical results are presented in several graphs versus the SIR for different values of fading and CCI parameters, as well as the number of input branches in the SC receiver. Then, the impact of parameters on all performance is checked. From our numerical results, it is possible to directly obtain the performance for all derived and displayed quantities for cases of previously known distributions of fading and CCI by inserting the appropriate parameter values. In the second part of the paper, a workflow for automated network experimentation relying on the synergy of Large Language Models (LLMs) and model-driven engineering (MDE) is presented, while the previously derived expressions are used for evaluation. Due to the aforementioned, the biggest value of the obtained results is the applicability to the cases of a large number of other distributions for fading and CCI by replacing the corresponding parameters in the formulas for the respective performances.
Open AccessMDE and LLM Synergy for Network Experimentation: Case Analysis of Wireless System Performance in Beaulieu-Xie Fading and κ-µ Co-Channel Interference Environment with Diversity Combining
Channel modeling is a first step towards the successful projecting of any wireless communication system. Hence, in this paper, we analyze the performance at the output of a multi-branch selection combining (SC) diversity receiver in a wireless environment that has been distracted by fading and co-channel interference (CCI), whereby the fading is modelled by newer Beaulieu-Xie (BX) distribution, and the CCI is modelled by the κ-µ distribution. The BX distribution provides the ability to include in consideration any number of line-of-sight (LOS) useful signal components and non-LOS (NLOS) useful signal components. This distribution contains characteristics of some other fading models thanks to its flexible fading parameters, which also applies to the κ-µ distribution. We derived here the expressions for the probability density function (PDF) and cumulative distribution function (CDF) for the output signal-to-co-channel interference ratio (SIR). After that, other performances are obtained, namely: outage probability (Pout), channel capacity (CC), moment-generating function (MGF), average bit error probability (ABEP), level crossing rate (LCR), and average fade duration (AFD). Numerical results are presented in several graphs versus the SIR for different values of fading and CCI parameters, as well as the number of input branches in the SC receiver. Then, the impact of parameters on all performance is checked. From our numerical results, it is possible to directly obtain the performance for all derived and displayed quantities for cases of previously known distributions of fading and CCI by inserting the appropriate parameter values. In the second part of the paper, a workflow for automated network experimentation relying on the synergy of Large Language Models (LLMs) and model-driven engineering (MDE) is presented, while the previously derived expressions are used for evaluation. Due to the aforementioned, the biggest value of the obtained results is the applicability to the cases of a large number of other distributions for fading and CCI by replacing the corresponding parameters in the formulas for the respective performances.
- Open Access
- 29 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (19) , 4088
AI-Enabled Framework for Mobile Network Experimentation Leveraging ChatGPT: Case Study of Channel Capacity Calculation for η-µ Fading and Co-Channel Interference
Artificial intelligence has been identified as one of the main driving forces of innovation in state-of-the-art mobile and wireless networks. It has enabled many novel usage scenarios, relying on predictive models for increasing network management efficiency. However, its adoption requires additional efforts, such as mastering the terminology, tools, and newly required steps of data importing and preparation, all of which increase the time required for experimentation. Therefore, we aimed to automate the manual steps as much as possible while reducing the overall cognitive load. In this paper, we explore the potential use of a novel Chat Generative Pre-trained Transformer (ChatGPT) conversational agent together with a model-driven approach relying on the Neo4j graph database in order to aid experimentation and analytics in the case of wireless network planning. As a case study, we present a derivation of the expression for the channel capacity (CC) metric in the case of η-µ multipath fading and η-µ co-channel interference. Moreover, the derived expression is leveraged for quality of service (QoS) estimation within the software simulation environment. ChatGPT, in synergy with a model-driven approach, is used to automate several steps: data importing, generation of graph construction, and machine learning-related Neo4j queries. According to the achieved outcomes, the proposed QoS estimation method, based on the derived CC expression (with precision up to the fifth significant digit), demonstrates satisfactory accuracy (up to 98%) and faster training than the deep neural network-based solution. On the other hand, compared to the manual approach based on our previous work, ChatGPT-based code generation reduces the time required for experimentation by more than 4 times.
- 29 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (19) , 4088
Open AccessAI-Enabled Framework for Mobile Network Experimentation Leveraging ChatGPT: Case Study of Channel Capacity Calculation for η-µ Fading and Co-Channel Interference
Artificial intelligence has been identified as one of the main driving forces of innovation in state-of-the-art mobile and wireless networks. It has enabled many novel usage scenarios, relying on predictive models for increasing network management efficiency. However, its adoption requires additional efforts, such as mastering the terminology, tools, and newly required steps of data importing and preparation, all of which increase the time required for experimentation. Therefore, we aimed to automate the manual steps as much as possible while reducing the overall cognitive load. In this paper, we explore the potential use of a novel Chat Generative Pre-trained Transformer (ChatGPT) conversational agent together with a model-driven approach relying on the Neo4j graph database in order to aid experimentation and analytics in the case of wireless network planning. As a case study, we present a derivation of the expression for the channel capacity (CC) metric in the case of η-µ multipath fading and η-µ co-channel interference. Moreover, the derived expression is leveraged for quality of service (QoS) estimation within the software simulation environment. ChatGPT, in synergy with a model-driven approach, is used to automate several steps: data importing, generation of graph construction, and machine learning-related Neo4j queries. According to the achieved outcomes, the proposed QoS estimation method, based on the derived CC expression (with precision up to the fifth significant digit), demonstrates satisfactory accuracy (up to 98%) and faster training than the deep neural network-based solution. On the other hand, compared to the manual approach based on our previous work, ChatGPT-based code generation reduces the time required for experimentation by more than 4 times.
- Open Access
- 27 June 2023
- Published by Kaunas University of Technology (KTU) in Elektronika ir Elektrotechnika
- Vol. 29 (3) , 68-73
Combining Receiver Damaged by Beaulieu-Xie Fading and Rician Co-Channel Interference with a Purpose of Machine Learning QoS Level Prediction
In this paper, a wireless system is considered impacted by Beaulieu-Xie (BX) fading and Rician co-channel interference (CCI). A selection diversity combining technique is used to combat multi-path fading and CCI effects. The expression for the level crossing rate (LCR) is formulated for the receiver with more input branches, and the corresponding curves that have dependence on the signal-to-interference ratio (SIR) are drawn. On the basis of the presented graphs, we quantify the amount of LCR affected by the presence of fading and interference. Additionally, we propose a classification-based predictive model which leverages the previously calculated LCR value as one of inputs among other variables (number of users, base station, the day of the week) with the aim of Quality of Service (QoS) level prediction.
- 27 June 2023
- Published by Kaunas University of Technology (KTU) in Elektronika ir Elektrotechnika
- Vol. 29 (3) , 68-73
Open AccessCombining Receiver Damaged by Beaulieu-Xie Fading and Rician Co-Channel Interference with a Purpose of Machine Learning QoS Level Prediction
In this paper, a wireless system is considered impacted by Beaulieu-Xie (BX) fading and Rician co-channel interference (CCI). A selection diversity combining technique is used to combat multi-path fading and CCI effects. The expression for the level crossing rate (LCR) is formulated for the receiver with more input branches, and the corresponding curves that have dependence on the signal-to-interference ratio (SIR) are drawn. On the basis of the presented graphs, we quantify the amount of LCR affected by the presence of fading and interference. Additionally, we propose a classification-based predictive model which leverages the previously calculated LCR value as one of inputs among other variables (number of users, base station, the day of the week) with the aim of Quality of Service (QoS) level prediction.
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (24) , 24593-24606
UAV-Assisted Wireless Information and Power Transfer for Self-Sustained IoT Communications
This paper investigates the performance of an unmanned aerial vehicle (UAV)-assisted wireless power transfer (WPT)-enabled communications for energy-constrained wireless devices. Herein, a UAV serves as a radio-frequency (RF) energy harvesting transmitter for a pair of Internet of Things devices (IoDs). It also provides relay cooperation to IoDs using decode-and-forward operation. The composite fading channels associated with the UAV and IoDs are modeled by considering the probability of line-of-sight (LoS)/non-LoS and shadowing components, assuming log-normal distribution. Besides, the small-scale fading scenarios for LoS and non-LoS communications are assumed to follow Nakagami-m and Rayleigh distributions, respectively. In addition, considering relative mobility between the UAV and IoDs, we exploit the first-order autoregressive process to model the fading channels during the information transmission phase. For such a realistic system setup, we derive the expressions for the outage probability at the IoDs using Gauss-Hermite quadrature under different shadowing and fading channel combinations. The system throughput and energy efficiency are also quantified using the derived outage probability expressions. The analytical findings are verified through numerical and simulation results. Our results highlight the impact of various system/channel parameters on the system’s performance and provide significant insights into the system’s behavior.
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (24) , 24593-24606
UAV-Assisted Wireless Information and Power Transfer for Self-Sustained IoT Communications
This paper investigates the performance of an unmanned aerial vehicle (UAV)-assisted wireless power transfer (WPT)-enabled communications for energy-constrained wireless devices. Herein, a UAV serves as a radio-frequency (RF) energy harvesting transmitter for a pair of Internet of Things devices (IoDs). It also provides relay cooperation to IoDs using decode-and-forward operation. The composite fading channels associated with the UAV and IoDs are modeled by considering the probability of line-of-sight (LoS)/non-LoS and shadowing components, assuming log-normal distribution. Besides, the small-scale fading scenarios for LoS and non-LoS communications are assumed to follow Nakagami-m and Rayleigh distributions, respectively. In addition, considering relative mobility between the UAV and IoDs, we exploit the first-order autoregressive process to model the fading channels during the information transmission phase. For such a realistic system setup, we derive the expressions for the outage probability at the IoDs using Gauss-Hermite quadrature under different shadowing and fading channel combinations. The system throughput and energy efficiency are also quantified using the derived outage probability expressions. The analytical findings are verified through numerical and simulation results. Our results highlight the impact of various system/channel parameters on the system’s performance and provide significant insights into the system’s behavior.
- Open Access
- 8 April 2022
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2022, 1-23
Model-Driven Approach to Fading-Aware Wireless Network Planning Leveraging Multiobjective Optimization and Deep Learning
Efficient resource planning is recognized as one of the key enablers making the large-scale deployment of next-generation wireless networks available for mass usage. Modelling, planning, and software simulation tools reduce both the time needed and costs of their tuning and realization. In this paper, we propose a model-driven framework for proactive network planning relying on synergy of deep learning and multiobjective optimization. The predictions about service demand and energy consumption are taken into account. Also, the impact of degradations resulting from fading and cochannel interference (CCI) effects is also considered. The optimization task is treated as a component allocation problem (CAP) aiming to find the best possible base station allocation for the considered smart city locations with respect to performance and service demand constraints. The goal is to maximize Quality of Service (QoS) while keeping the costs and energy consumption as low as possible. The adoption of a model-driven approach in combination with model-to-model transformations and automated code generation does not only reduce the complexity, making experimentation more rapid and convenient at the same time, but also increase the overall reusability and expandability of the planning tool. According to the obtained results, the proposed solution seems to be promising not only due to achieved benefits but also regarding the execution time, which is shorter than that achieved in our previous works, especially for larger distances. Further, we adopt model-based representation of handover strategies within the planning tool, enabling examination of the dynamic behavior of user-created plan, which is not exploited in other similar works. The main contributions of the paper are (1) wireless network planning (WNP) metamodel, a modelling notation for network plans; (2) model-to-model transformation for conversion of WNP to generalized CAP metamodel; (3) prediction problem (PP) metamodel, high-level abstraction for representation of prediction-related regression and classification problems; (4) code generator that creates PyTorch neural network from PP representation; (5) service demand and energy consumption prediction modules performing regression; (6) multiobjective optimization model for base station allocation; (7) Handover Strategy (HS) metamodel used for description of dynamic aspects and adaptability relevant to network planning.
- 8 April 2022
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2022, 1-23
Open AccessModel-Driven Approach to Fading-Aware Wireless Network Planning Leveraging Multiobjective Optimization and Deep Learning
Efficient resource planning is recognized as one of the key enablers making the large-scale deployment of next-generation wireless networks available for mass usage. Modelling, planning, and software simulation tools reduce both the time needed and costs of their tuning and realization. In this paper, we propose a model-driven framework for proactive network planning relying on synergy of deep learning and multiobjective optimization. The predictions about service demand and energy consumption are taken into account. Also, the impact of degradations resulting from fading and cochannel interference (CCI) effects is also considered. The optimization task is treated as a component allocation problem (CAP) aiming to find the best possible base station allocation for the considered smart city locations with respect to performance and service demand constraints. The goal is to maximize Quality of Service (QoS) while keeping the costs and energy consumption as low as possible. The adoption of a model-driven approach in combination with model-to-model transformations and automated code generation does not only reduce the complexity, making experimentation more rapid and convenient at the same time, but also increase the overall reusability and expandability of the planning tool. According to the obtained results, the proposed solution seems to be promising not only due to achieved benefits but also regarding the execution time, which is shorter than that achieved in our previous works, especially for larger distances. Further, we adopt model-based representation of handover strategies within the planning tool, enabling examination of the dynamic behavior of user-created plan, which is not exploited in other similar works. The main contributions of the paper are (1) wireless network planning (WNP) metamodel, a modelling notation for network plans; (2) model-to-model transformation for conversion of WNP to generalized CAP metamodel; (3) prediction problem (PP) metamodel, high-level abstraction for representation of prediction-related regression and classification problems; (4) code generator that creates PyTorch neural network from PP representation; (5) service demand and energy consumption prediction modules performing regression; (6) multiobjective optimization model for base station allocation; (7) Handover Strategy (HS) metamodel used for description of dynamic aspects and adaptability relevant to network planning.