Roumen Trifonov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Roumen Trifonov has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Georgi Tsochev
Department of Intelligent Technologies in Industry, Faculty of Computer Systems and Technology, Technical University of Sofia, 1000 Sofia, Bulgaria
6 shared publications Galya Pavlova
Technical University of Sofia, 8 St. Kl. Ohridski bul., Sofia 1000, Bulgaria
5 shared publicationsSlavcho Manolov
Information Technologies In Industry, Technical University of Sofia, Sofia, Bulgaria
5 shared publicationsOgnian Nakov
FCST, Technical University of Sofia, Sofia, Bulgaria
4 shared publications- Radoslav Yoshinov
Laboratory of Telematics at the Bulgarian Academy of Sciences
4 shared publications - Galya Pavlova
TU Wien, Austria
3 shared publications
Latest Publications
- Open Access
- 21 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3746
Individual and Coordinated Mixed-Integer Linear Programming Dispatch of an Industrial Photovoltaic–Battery Prosumer Community on the Bulgarian Day-Ahead Market
Industrial consumers increasingly operate photovoltaic (PV) generation and battery energy storage systems (BESS) against volatile day-ahead electricity prices. This paper presents a simulation environment for a community of three heterogeneous industrial prosumers, anchored in twelve months of day-ahead prices from the Bulgarian Independent Energy Exchange (IBEX), commercial hardware envelopes, and the terms of a market offtake contract that indexes remuneration to the day-ahead price, passes negative prices through to the producer, and mandates curtailment in strongly negative periods. A mixed-integer linear programming (MILP) dispatch model with binary charge/discharge modes and endogenous PV curtailment is solved daily in independent and coordinated regimes, under cost-only and capacity-aware objectives, for Sofia and Stara Zagora. On an energy-only basis, before capacity charges, storage turns the community from a net payer (39.1 kEUR/yr grid-only; 13.1 kEUR/yr with PV) into a net earner (8.64 kEUR/yr independent; 10.12 kEUR/yr coordinated), and the battery retrofit more than doubles the merchant plant’s net revenue. Cost-optimal dispatch synchronizes charging and raises the coincident grid peak to 241 kW; a capacity-aware objective cuts it to 133–140 kW (−42–45%) for under 0.9 kEUR/yr foregone income; under the two tested capacity-charge conventions, only the capacity-aware schedule remains net-positive after the modeled charge. The coordination gain grows with the import price adder and remains positive across 15–45 EUR/MWh.
- 21 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3746
Open AccessIndividual and Coordinated Mixed-Integer Linear Programming Dispatch of an Industrial Photovoltaic–Battery Prosumer Community on the Bulgarian Day-Ahead Market
Industrial consumers increasingly operate photovoltaic (PV) generation and battery energy storage systems (BESS) against volatile day-ahead electricity prices. This paper presents a simulation environment for a community of three heterogeneous industrial prosumers, anchored in twelve months of day-ahead prices from the Bulgarian Independent Energy Exchange (IBEX), commercial hardware envelopes, and the terms of a market offtake contract that indexes remuneration to the day-ahead price, passes negative prices through to the producer, and mandates curtailment in strongly negative periods. A mixed-integer linear programming (MILP) dispatch model with binary charge/discharge modes and endogenous PV curtailment is solved daily in independent and coordinated regimes, under cost-only and capacity-aware objectives, for Sofia and Stara Zagora. On an energy-only basis, before capacity charges, storage turns the community from a net payer (39.1 kEUR/yr grid-only; 13.1 kEUR/yr with PV) into a net earner (8.64 kEUR/yr independent; 10.12 kEUR/yr coordinated), and the battery retrofit more than doubles the merchant plant’s net revenue. Cost-optimal dispatch synchronizes charging and raises the coincident grid peak to 241 kW; a capacity-aware objective cuts it to 133–140 kW (−42–45%) for under 0.9 kEUR/yr foregone income; under the two tested capacity-charge conventions, only the capacity-aware schedule remains net-positive after the modeled charge. The coordination gain grows with the import price adder and remains positive across 15–45 EUR/MWh.
- Open Access
- 22 July 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 150 (1) , 57
Heuristic Algorithm for Conceptual Learning
This article presents a new heuristic algorithm for conceptual learning. The process of constructing a decision tree through the minimization of a logical function is explained. This heuristic approach eliminates the need to expand the inverse property space into a full logical expression, which could be computationally expensive for large expressions. Tests were conducted using various sets of standardized machine learning benchmarks. They show that the algorithm operates with high precision and accuracy on noise-free data as well as on datasets that include noise through the presence of mislabeled examples. The algorithm’s ability to capture non-linear patterns was experimentally evaluated, where the target class is defined by the equality of two specified attributes. The application of the proposed algorithm for the creation of hybrid neuro-symbolic architectures is discussed, with the aim of achieving logically grounded and interpretable machine learning and machine reasoning.
- 22 July 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 150 (1) , 57
Open AccessHeuristic Algorithm for Conceptual Learning
This article presents a new heuristic algorithm for conceptual learning. The process of constructing a decision tree through the minimization of a logical function is explained. This heuristic approach eliminates the need to expand the inverse property space into a full logical expression, which could be computationally expensive for large expressions. Tests were conducted using various sets of standardized machine learning benchmarks. They show that the algorithm operates with high precision and accuracy on noise-free data as well as on datasets that include noise through the presence of mislabeled examples. The algorithm’s ability to capture non-linear patterns was experimentally evaluated, where the target class is defined by the equality of two specified attributes. The application of the proposed algorithm for the creation of hybrid neuro-symbolic architectures is discussed, with the aim of achieving logically grounded and interpretable machine learning and machine reasoning.
- Open Access
- 23 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (3) , 502
Development of an IoT System for Acquisition of Data and Control Based on External Battery State of Charge
In the context of small, battery-powered systems, a lightweight, reusable architecture is needed for integrated measurement, visualization, and cloud telemetry that minimizes hardware complexity and energy footprint. Existing solutions require high resources. This limits their applicability in Internet of Things (IoT) devices with low power consumption. The present work demonstrates the process of design, implementation and experimental evaluation of a single-cell lithium-ion battery monitoring prototype, intended for standalone operation or integration into other systems. The architecture is compact and energy efficient, with a reduction in complexity and memory usage: modular architecture with clearly distinguished responsibilities, avoidance of unnecessary dynamic memory allocations, centralized error handling, and a low-power policy through the usage of deep sleep mode. The data is stored in a cloud platform, while minimal storage is used locally. The developed system combines the functional requirements for an embedded external battery monitoring system: local voltage and current measurement, approximate estimation of the State of Charge (SoC) using a look-up table (LUT) based on the discharge characteristic, and visualization on a monochrome OLED display. The conducted experiments demonstrate the typical U(t) curve and the triggering of the indicator at low charge levels (LOW − SoC ≤ 20% and CRITICAL − SoC ≤ 5%) in real-world conditions and the absence of unwanted switching of the state near the voltage thresholds.
- 23 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (3) , 502
Open AccessDevelopment of an IoT System for Acquisition of Data and Control Based on External Battery State of Charge
In the context of small, battery-powered systems, a lightweight, reusable architecture is needed for integrated measurement, visualization, and cloud telemetry that minimizes hardware complexity and energy footprint. Existing solutions require high resources. This limits their applicability in Internet of Things (IoT) devices with low power consumption. The present work demonstrates the process of design, implementation and experimental evaluation of a single-cell lithium-ion battery monitoring prototype, intended for standalone operation or integration into other systems. The architecture is compact and energy efficient, with a reduction in complexity and memory usage: modular architecture with clearly distinguished responsibilities, avoidance of unnecessary dynamic memory allocations, centralized error handling, and a low-power policy through the usage of deep sleep mode. The data is stored in a cloud platform, while minimal storage is used locally. The developed system combines the functional requirements for an embedded external battery monitoring system: local voltage and current measurement, approximate estimation of the State of Charge (SoC) using a look-up table (LUT) based on the discharge characteristic, and visualization on a monochrome OLED display. The conducted experiments demonstrate the typical U(t) curve and the triggering of the indicator at low charge levels (LOW − SoC ≤ 20% and CRITICAL − SoC ≤ 5%) in real-world conditions and the absence of unwanted switching of the state near the voltage thresholds.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3104 (1) , 060003
Analysis of deep learning methods for cybersecurity in industry 4.0
Nowadays the use of Artificial Intelligence (AI) around the globe is constantly growing. These processes were accelerated even more due to the COVID-19 pandemic
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3104 (1) , 060003
Analysis of deep learning methods for cybersecurity in industry 4.0
Nowadays the use of Artificial Intelligence (AI) around the globe is constantly growing. These processes were accelerated even more due to the COVID-19 pandemic
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2939 (1)
Artificial intelligence methods suitable for lateral movement detection
The COVID-19 pandemic forced many companies to send their employees to work from home, which led to a significant increase in cyberattacks over RDP. Remote Desktop Protocol (RDP) is a Microsoft protocol that allows administrators to access desktop computers remotely. As it gives the user full control over the device, it is a valuable entry point for adversaries. Every cyberattack goes through several stages before its termination. Lateral Movement is one of those stages that is of particular importance. This article presents the first step of a project for Designing a remote connection protection system based on artificial intelligence methods. The research reviews the problems in lateral movement detection. A literature review is conducted, outlining techniques for automatic detection of malicious lateral movements. There is a discussion about the possibility of using artificial intelligence methods in lateral movement detection and the choice of an appropriate method.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2939 (1)
Open AccessArtificial intelligence methods suitable for lateral movement detection
The COVID-19 pandemic forced many companies to send their employees to work from home, which led to a significant increase in cyberattacks over RDP. Remote Desktop Protocol (RDP) is a Microsoft protocol that allows administrators to access desktop computers remotely. As it gives the user full control over the device, it is a valuable entry point for adversaries. Every cyberattack goes through several stages before its termination. Lateral Movement is one of those stages that is of particular importance. This article presents the first step of a project for Designing a remote connection protection system based on artificial intelligence methods. The research reviews the problems in lateral movement detection. A literature review is conducted, outlining techniques for automatic detection of malicious lateral movements. There is a discussion about the possibility of using artificial intelligence methods in lateral movement detection and the choice of an appropriate method.
- 1 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 41-45
Cyber Trends in Industrial Control Systems
The development of technologies reaches new heights, but with them come new security issues. With some of the biggest data breaches in history made in 2019 alone, it is clear that cyber-attacks will not go away any time soon. In the recent past, security concerns for control systems have focused on limiting physical attacks. Industrial systems today use the Internet and cloud technologies, making them vulnerable to modern attacks. With the COVID-19 pandemic many people moved to work from home, which led to an increase in cyber-attacks. This article presents a study of current threats to industrial systems and some perspectives on them.
- 1 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 41-45
Cyber Trends in Industrial Control Systems
The development of technologies reaches new heights, but with them come new security issues. With some of the biggest data breaches in history made in 2019 alone, it is clear that cyber-attacks will not go away any time soon. In the recent past, security concerns for control systems have focused on limiting physical attacks. Industrial systems today use the Internet and cloud technologies, making them vulnerable to modern attacks. With the COVID-19 pandemic many people moved to work from home, which led to an increase in cyber-attacks. This article presents a study of current threats to industrial systems and some perspectives on them.
- 29 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 125-128
Analysis of the Principles and Criteria for Secure Software Development
An overview and analysis of security development standards and best practices, as well as comparison of programming languages from the security position of the code are presented in this paper. As a result of conducted analysis, a set of principles and criteria for development of secure software are defined in order to prevent accidental vulnerabilities in the programs.
- 29 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 125-128
Analysis of the Principles and Criteria for Secure Software Development
An overview and analysis of security development standards and best practices, as well as comparison of programming languages from the security position of the code are presented in this paper. As a result of conducted analysis, a set of principles and criteria for development of secure software are defined in order to prevent accidental vulnerabilities in the programs.
- 29 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 137-140
Colony Intelligence for Autonomous Wheeled Robot Path Planning
Mobile robot path planning in dynamic environments answers the question of how to find the shortest path from the initial position to its final destination by avoiding any obstacle. This paper is trying to improve known probabilistic sampling-based algorithms for the road map robot planning introducing a hybrid between wave-front planner cell technique, tangent bug algorithm, and ant colony intelligence strategies, thus minimize the heuristic logic dropping ineffective paths to the target. The proposed colony intelligence tangent bug algorithm (CITBA) determines the shortest path taking into account available historical sensor data for the dynamic surroundings inside the landscape and collected from all autonomous robots while travailing.
- 29 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 137-140
Colony Intelligence for Autonomous Wheeled Robot Path Planning
Mobile robot path planning in dynamic environments answers the question of how to find the shortest path from the initial position to its final destination by avoiding any obstacle. This paper is trying to improve known probabilistic sampling-based algorithms for the road map robot planning introducing a hybrid between wave-front planner cell technique, tangent bug algorithm, and ant colony intelligence strategies, thus minimize the heuristic logic dropping ineffective paths to the target. The proposed colony intelligence tangent bug algorithm (CITBA) determines the shortest path taking into account available historical sensor data for the dynamic surroundings inside the landscape and collected from all autonomous robots while travailing.
- Open Access
- 26 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Trends Review of the Contemporary Security Problems in the Cyberspace
- 26 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessTrends Review of the Contemporary Security Problems in the Cyberspace