Vladimír Szomosi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vladimír Szomosi has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
Július Šimčák
Technical university of Košice, Department of Electric Power Engineering, Košice
4 shared publications- Marek Bobček
Department of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Mäsiarska 74, 040 01 Kosice, Slovakia
4 shared publications Zsolt Čonka
Technical university of Košice, Department of Electric Power Engineering, Košice
4 shared publications- Zsolt Čonka
Department of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Mäsiarska 74, 040 01 Kosice, Slovakia
4 shared publications - Jozef Király
Department of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Mäsiarska 74, 040 01 Kosice, Slovakia
3 shared publications Róbert Štefko
Department of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Technical University of Košice
3 shared publications
Latest Publications
- Open Access
- 12 October 2026
- Published by MDPI AG in Electricity
- Vol. 7 (4) , 116
From Linear Regression to Temporal Fusion Transformers: Benchmarking Electricity Price Forecasting Models in Markets with Different Renewable Energy Shares
Rising renewable penetration increases wholesale price volatility and challenges traditional forecasting approaches. This paper benchmarks three methods—adaptive linear regression, Random Forest (RF), and the Temporal Fusion Transformer (TFT)—on hourly day-ahead prices in four European markets with contrasting generation mixes: Slovakia (nuclear-dominated), Spain (solar-rich), Denmark (wind-dominated), and Germany (mixed). Using Energy-Charts data for 2015–2025, all the models are evaluated under one day-ahead protocol on a common 12-month hold-out against naive 24-h persistence. With price-history features, the RF significantly outperforms persistence in three of four markets. A single cross-market five-seed TFT ensemble attains the lowest MAE everywhere, cutting the persistence error by 55.6% in Germany (to 12.88 €/MWh) and 21.7% in Slovakia. The improvement is generally larger in markets with higher variable-renewable penetration, though not strictly monotonic. Replacing the realized fundamentals with TSO day-ahead forecasts changes the MAE by at most 0.22 €/MWh: the day-ahead price is itself formed from those forecasts. Multivariate Diebold–Mariano tests confirm both advantages everywhere on absolute errors. Quantile averaging yields pinball losses of 3.87–6.53 €/MWh, but the 80% intervals cover only 71–78%. Variable importance ties the leading driver to each mix: wind in Denmark and Germany, load and solar in Spain, and load in Slovakia.
- 12 October 2026
- Published by MDPI AG in Electricity
- Vol. 7 (4) , 116
Open AccessFrom Linear Regression to Temporal Fusion Transformers: Benchmarking Electricity Price Forecasting Models in Markets with Different Renewable Energy Shares
Rising renewable penetration increases wholesale price volatility and challenges traditional forecasting approaches. This paper benchmarks three methods—adaptive linear regression, Random Forest (RF), and the Temporal Fusion Transformer (TFT)—on hourly day-ahead prices in four European markets with contrasting generation mixes: Slovakia (nuclear-dominated), Spain (solar-rich), Denmark (wind-dominated), and Germany (mixed). Using Energy-Charts data for 2015–2025, all the models are evaluated under one day-ahead protocol on a common 12-month hold-out against naive 24-h persistence. With price-history features, the RF significantly outperforms persistence in three of four markets. A single cross-market five-seed TFT ensemble attains the lowest MAE everywhere, cutting the persistence error by 55.6% in Germany (to 12.88 €/MWh) and 21.7% in Slovakia. The improvement is generally larger in markets with higher variable-renewable penetration, though not strictly monotonic. Replacing the realized fundamentals with TSO day-ahead forecasts changes the MAE by at most 0.22 €/MWh: the day-ahead price is itself formed from those forecasts. Multivariate Diebold–Mariano tests confirm both advantages everywhere on absolute errors. Quantile averaging yields pinball losses of 3.87–6.53 €/MWh, but the 80% intervals cover only 71–78%. Variable importance ties the leading driver to each mix: wind in Denmark and Germany, load and solar in Spain, and load in Slovakia.
- Open Access
- 22 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9410
Observability-Aware Estimation of Tradeable Vehicle-to-Grid Capacity from Heterogeneous Charger Telemetry
Vehicle-to-grid (V2G) aggregators must commit energy and power that connected vehicles can actually deliver, yet they often observe only charger-side telemetry, and vehicle-reported state of charge (SOC) is optional or non-authoritative. This paper proposes an observability-aware framework for estimating tradeable V2G capacity: each session is classified by its measurement boundary, channels, sampling, latency, and setpoint control, then mapped to the battery through uncertain conversion paths. The estimator outputs conservative safe energy and safe power rather than absolute SOC, treats vehicle-reported values as noisy hints, and abstains when observability is insufficient. A reproducible synthetic study shows that regularization and a split-conformal margin bring the bound to the 95% target with a finite-sample guarantee under within-regime exchangeability, and that the required capacity haircut grows from about 2.6 through 4.3 to 6.5 SOC points as observability degrades. Coverage alone does not distinguish the method, since any conformalized predictor reaches the target; the observability-aware bound adds tradeable capacity at that coverage, and its advantage grows as telemetry degrades. End-to-end market deliverability is established only in synthesis: a laboratory proof of concept on one bidirectional charger with four production vehicles demonstrates AC-boundary telemetry ingestion and capability assignment, but measures realized throughput after the fact rather than a bound committed before dispatch.
- 22 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9410
Open AccessObservability-Aware Estimation of Tradeable Vehicle-to-Grid Capacity from Heterogeneous Charger Telemetry
Vehicle-to-grid (V2G) aggregators must commit energy and power that connected vehicles can actually deliver, yet they often observe only charger-side telemetry, and vehicle-reported state of charge (SOC) is optional or non-authoritative. This paper proposes an observability-aware framework for estimating tradeable V2G capacity: each session is classified by its measurement boundary, channels, sampling, latency, and setpoint control, then mapped to the battery through uncertain conversion paths. The estimator outputs conservative safe energy and safe power rather than absolute SOC, treats vehicle-reported values as noisy hints, and abstains when observability is insufficient. A reproducible synthetic study shows that regularization and a split-conformal margin bring the bound to the 95% target with a finite-sample guarantee under within-regime exchangeability, and that the required capacity haircut grows from about 2.6 through 4.3 to 6.5 SOC points as observability degrades. Coverage alone does not distinguish the method, since any conformalized predictor reaches the target; the observability-aware bound adds tradeable capacity at that coverage, and its advantage grows as telemetry degrades. End-to-end market deliverability is established only in synthesis: a laboratory proof of concept on one bidirectional charger with four production vehicles demonstrates AC-boundary telemetry ingestion and capability assignment, but measures realized throughput after the fact rather than a bound committed before dispatch.
- Open Access
Financial Payback and Return on Investment of Battery Energy Storage in Photovoltaic Systems: A Review of Economic Drivers and Vehicle-to-Grid Integration
Battery energy storage systems (BESSs) are increasingly coupled with photovoltaic (PV) generation, yet their deployment is governed by economics rather than by technical feasibility. This review synthesises 122 indexed Q1/Q2 studies (2016–2026) on the financial payback and return on investment of PV-coupled storage, extending the analysis to vehicle-to-grid (V2G) integration. Records retrieved from Scopus, Web of Science, IEEE Xplore, and the MDPI portal were screened to peer-reviewed journals, assigned to ten thematic clusters, appraised against a ten-criterion reporting-transparency rubric, and combined by narrative synthesis. Reported payback periods range from a few years to beyond the asset’s service life, and the levelized cost of storage spans roughly 170–350 USD/MWh. In the reviewed corpus, the retail-to-export price spread, the stacking of self-consumption, arbitrage, grid-service revenues, and degradation-aware operation each move returns in a consistent direction, whereas which of them binds hardest is a property of the case rather than a ranking the evidence supports. V2G is almost always analysed in isolation from stationary storage; an illustrative harmonised comparison indicates that it substitutes for stationary capacity rather than adding to it. The review maps the combined PV+BESS+V2G revenue stack and identifies an integrated, degradation-corrected, policy-sensitive economic model as the principal research gap.
Open AccessFinancial Payback and Return on Investment of Battery Energy Storage in Photovoltaic Systems: A Review of Economic Drivers and Vehicle-to-Grid Integration
Battery energy storage systems (BESSs) are increasingly coupled with photovoltaic (PV) generation, yet their deployment is governed by economics rather than by technical feasibility. This review synthesises 122 indexed Q1/Q2 studies (2016–2026) on the financial payback and return on investment of PV-coupled storage, extending the analysis to vehicle-to-grid (V2G) integration. Records retrieved from Scopus, Web of Science, IEEE Xplore, and the MDPI portal were screened to peer-reviewed journals, assigned to ten thematic clusters, appraised against a ten-criterion reporting-transparency rubric, and combined by narrative synthesis. Reported payback periods range from a few years to beyond the asset’s service life, and the levelized cost of storage spans roughly 170–350 USD/MWh. In the reviewed corpus, the retail-to-export price spread, the stacking of self-consumption, arbitrage, grid-service revenues, and degradation-aware operation each move returns in a consistent direction, whereas which of them binds hardest is a property of the case rather than a ranking the evidence supports. V2G is almost always analysed in isolation from stationary storage; an illustrative harmonised comparison indicates that it substitutes for stationary capacity rather than adding to it. The review maps the combined PV+BESS+V2G revenue stack and identifies an integrated, degradation-corrected, policy-sensitive economic model as the principal research gap.
- Open Access
- 25 August 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (17) , 8695
Toward Sustainable Electromobility: Planning Electric Vehicle Charging Infrastructure with a Hierarchical Bayesian Model, Agent-Based Simulation and Multi-Criteria Decision Making
Electromobility is central to urban decarbonisation, but its charging infrastructure must be sized under substantial uncertainty about user behaviour that varies across stations, time of day and user type. This study couples a hierarchical Bayesian model with an agent-based, discrete-event simulation of a charging network. It is fitted by Markov chain Monte Carlo to the public ACN-Data dataset (13,694 sessions across 52 stations; 16,468 user requests), with partial pooling across stations. Posterior parameters drive a 24 h simulation of 500 vehicles across nine configurations and 30 to 180 slots. Service success rises from 19% to 81% and mean waiting falls from 110 to 62 min; long workplace dwell times limit turnover, so capacity rather than energy binds. TOPSIS with a paired bootstrap selects 160 slots under balanced weighting, but that optimum holds for only a tenth of the weight simplex, and the recommendation spans 140–180 slots. Spreading the arrival peak at fixed hardware raises service from 67% to 83%, matching a 29% expansion. Spatially explicit assignment costs three percentage points when stations are evenly sited, and six when clustered. The framework makes the cost of over-provisioning explicit and preference-conditional rather than naming a single optimum, giving a reproducible basis for sustainable capacity planning.
- 25 August 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (17) , 8695
Open AccessToward Sustainable Electromobility: Planning Electric Vehicle Charging Infrastructure with a Hierarchical Bayesian Model, Agent-Based Simulation and Multi-Criteria Decision Making
Electromobility is central to urban decarbonisation, but its charging infrastructure must be sized under substantial uncertainty about user behaviour that varies across stations, time of day and user type. This study couples a hierarchical Bayesian model with an agent-based, discrete-event simulation of a charging network. It is fitted by Markov chain Monte Carlo to the public ACN-Data dataset (13,694 sessions across 52 stations; 16,468 user requests), with partial pooling across stations. Posterior parameters drive a 24 h simulation of 500 vehicles across nine configurations and 30 to 180 slots. Service success rises from 19% to 81% and mean waiting falls from 110 to 62 min; long workplace dwell times limit turnover, so capacity rather than energy binds. TOPSIS with a paired bootstrap selects 160 slots under balanced weighting, but that optimum holds for only a tenth of the weight simplex, and the recommendation spans 140–180 slots. Spreading the arrival peak at fixed hardware raises service from 67% to 83%, matching a 29% expansion. Spatially explicit assignment costs three percentage points when stations are evenly sited, and six when clustered. The framework makes the cost of over-provisioning explicit and preference-conditional rather than naming a single optimum, giving a reproducible basis for sustainable capacity planning.
- Open Access
A Lightweight Support-Vector-Machine-Based Infrared Image Processing Workflow for Photovoltaic Module Thermal Anomaly Screening
Deep networks dominate photovoltaic (PV) thermographic fault detection but need large annotated datasets and resist interpretation. We present a lightweight, interpretable infrared workflow combining support-vector-machine (SVM) module/background segmentation from four handcrafted features with an adaptive grid analysis labelling regions as nominal-intensity, high-intensity anomaly or low-intensity anomaly relative to a module-internal reference; the anomaly classes are inspection candidates, not confirmed faults. Evaluation used 21 close-range images of one 20 W module—recorded with the camera’s visible-light edge fusion active, so they are fused infrared/visible frames—and all 596 of a public five-sector UAV dataset. Segmentation against manual masks reached a mean intersection-over-union of 0.64; a feature ablation shows intensity statistics dominate, and an end-to-end Otsu pipeline gives almost the same high-intensity share (4.54% versus 4.50%): the SVM contributes reproducibility—removing the manual segmentation threshold, though not the empirical +48/−60 offsets—not accuracy. High-intensity regions concentrated in the module’s lower half, co-locating with a bus-bar defect known from hardware inspection—suggestive, not validated. The single-module, image-level close-range evaluation is optimistic, and the UAV shares, from a separately trained SVM, illustrate cross-domain application only. Segmentation runs at about 15 images per second on CPU. The method is a relative-intensity thermal screening workflow, not a validated defect-diagnosis or plant-health assessment method, and applies only where acquisition is controlled and the offsets are recalibrated for the target camera and palette.
Open AccessA Lightweight Support-Vector-Machine-Based Infrared Image Processing Workflow for Photovoltaic Module Thermal Anomaly Screening
Deep networks dominate photovoltaic (PV) thermographic fault detection but need large annotated datasets and resist interpretation. We present a lightweight, interpretable infrared workflow combining support-vector-machine (SVM) module/background segmentation from four handcrafted features with an adaptive grid analysis labelling regions as nominal-intensity, high-intensity anomaly or low-intensity anomaly relative to a module-internal reference; the anomaly classes are inspection candidates, not confirmed faults. Evaluation used 21 close-range images of one 20 W module—recorded with the camera’s visible-light edge fusion active, so they are fused infrared/visible frames—and all 596 of a public five-sector UAV dataset. Segmentation against manual masks reached a mean intersection-over-union of 0.64; a feature ablation shows intensity statistics dominate, and an end-to-end Otsu pipeline gives almost the same high-intensity share (4.54% versus 4.50%): the SVM contributes reproducibility—removing the manual segmentation threshold, though not the empirical +48/−60 offsets—not accuracy. High-intensity regions concentrated in the module’s lower half, co-locating with a bus-bar defect known from hardware inspection—suggestive, not validated. The single-module, image-level close-range evaluation is optimistic, and the UAV shares, from a separately trained SVM, illustrate cross-domain application only. Segmentation runs at about 15 images per second on CPU. The method is a relative-intensity thermal screening workflow, not a validated defect-diagnosis or plant-health assessment method, and applies only where acquisition is controlled and the offsets are recalibrated for the target camera and palette.
- Open Access
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Comparative experimental study of DC breakdown strength of Polypropylene film under various layer arrangements
This paper deals with the DC electrical breakdown strength (DC BDS) of polypropylene (PP) film, a material used in high-performance capacitors. The objective of this paper is to compare the DC breakdown strength of PP films of various layer arrangements, dry or oil impregnated. The experimental part focused on a comparative study of the DC BDS across two distinct types of PP film of different space factors. To investigate the impact of the dielectric material’s overall thickness, test samples were created in one-, two-, and three-layer wound scroll configurations. A significant element of the study was the assessment of impregnation effects on the DC BDS across all samples. Acquired experimental data were analysed with various statistical tools, including the Grubbs’ test for outlier detection and the Weibull analysis for determining the probability of failure. The conclusion provides robust information on the DC breakdown strength of different configurations of layered PP films under test.
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Open AccessComparative experimental study of DC breakdown strength of Polypropylene film under various layer arrangements
This paper deals with the DC electrical breakdown strength (DC BDS) of polypropylene (PP) film, a material used in high-performance capacitors. The objective of this paper is to compare the DC breakdown strength of PP films of various layer arrangements, dry or oil impregnated. The experimental part focused on a comparative study of the DC BDS across two distinct types of PP film of different space factors. To investigate the impact of the dielectric material’s overall thickness, test samples were created in one-, two-, and three-layer wound scroll configurations. A significant element of the study was the assessment of impregnation effects on the DC BDS across all samples. Acquired experimental data were analysed with various statistical tools, including the Grubbs’ test for outlier detection and the Weibull analysis for determining the probability of failure. The conclusion provides robust information on the DC breakdown strength of different configurations of layered PP films under test.
- Open Access
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Vehicle-to-grid (V2G) integration a comprehensive review of technologies, challenges, and opportunities in modern power systems
This comprehensive review explores V2G, where electric vehicles act as mobile energy storage assets for the grid. We systematically analyze the core components of the V2G ecosystem, including bidirectional power electronics, advanced communication protocols such as ISO 15118, and emerging control architectures. The paper evaluates the portfolio of ancillary services that V2G can provide, such as frequency regulation, peak load shaving, and renewable energy firming, while also quantifying the potential adverse impacts on grid stability, including harmonic distortion and voltage fluctuations. Critical barriers to widespread adoption are examined in depth, with a particular focus on the techno-economic implications of battery degradation and the systemic vulnerabilities introduced by cybersecurity threats. Mitigation strategies, including degradation-aware charging algorithms and robust security frameworks leveraging Public Key Infrastructure (PKI) and Transport Layer Security (TLS), are discussed. A techno-economic analysis reveals that V2G profitability is highly contingent on regional electricity market structures and battery chemistry. Our Levelized Cost of Storage (LCOS) analysis indicates that Lithium Iron Phosphate (LFP) chemistry reduces costs by up to 76.3%. Synthesizing findings from international pilots, we highlight deployment status and lessons learned. V2G grid resilience requires overcoming technical, economic, and security challenges.
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Open AccessVehicle-to-grid (V2G) integration a comprehensive review of technologies, challenges, and opportunities in modern power systems
This comprehensive review explores V2G, where electric vehicles act as mobile energy storage assets for the grid. We systematically analyze the core components of the V2G ecosystem, including bidirectional power electronics, advanced communication protocols such as ISO 15118, and emerging control architectures. The paper evaluates the portfolio of ancillary services that V2G can provide, such as frequency regulation, peak load shaving, and renewable energy firming, while also quantifying the potential adverse impacts on grid stability, including harmonic distortion and voltage fluctuations. Critical barriers to widespread adoption are examined in depth, with a particular focus on the techno-economic implications of battery degradation and the systemic vulnerabilities introduced by cybersecurity threats. Mitigation strategies, including degradation-aware charging algorithms and robust security frameworks leveraging Public Key Infrastructure (PKI) and Transport Layer Security (TLS), are discussed. A techno-economic analysis reveals that V2G profitability is highly contingent on regional electricity market structures and battery chemistry. Our Levelized Cost of Storage (LCOS) analysis indicates that Lithium Iron Phosphate (LFP) chemistry reduces costs by up to 76.3%. Synthesizing findings from international pilots, we highlight deployment status and lessons learned. V2G grid resilience requires overcoming technical, economic, and security challenges.
- Open Access
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Integrated multi-layer protection of bidirectional vehicle-to-grid (V2G) charging systems with emphasis on compliance with IEEE 1547 and 519 standards
This paper proposes a comprehensive multi-layer protection architecture for bidirectional Vehicle-to-Grid (V2G) systems acting as distributed energy resources. The study addresses the integration challenges defined by IEEE 1547 (anti-islanding) and IEEE 519 (power quality) standards. The proposed solution integrates mandatory DC leakage protection (RCD Type B/RCM), hybrid circuit breakers (HCB) for ultra-fast DC fault interruption and coordinated AC/DC surge protection. The design is validated through normative analysis, time-response coordination logic, and economic ROI estimation. The results confirm that while advanced protection increases initial costs, it is critical for preventing catastrophic failures in high-power V2G applications.
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Open AccessIntegrated multi-layer protection of bidirectional vehicle-to-grid (V2G) charging systems with emphasis on compliance with IEEE 1547 and 519 standards
This paper proposes a comprehensive multi-layer protection architecture for bidirectional Vehicle-to-Grid (V2G) systems acting as distributed energy resources. The study addresses the integration challenges defined by IEEE 1547 (anti-islanding) and IEEE 519 (power quality) standards. The proposed solution integrates mandatory DC leakage protection (RCD Type B/RCM), hybrid circuit breakers (HCB) for ultra-fast DC fault interruption and coordinated AC/DC surge protection. The design is validated through normative analysis, time-response coordination logic, and economic ROI estimation. The results confirm that while advanced protection increases initial costs, it is critical for preventing catastrophic failures in high-power V2G applications.
- Open Access
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Integration of renewables and storage for maximum flexibility: A digital design of low-carbon grids (smart grids)
The transition to a low-carbon energy system is conditioned by the successful integration of highly variable, yet advanced, renewable energy sources (RES). This paper analyzes the transformative synergy between the next generation of RES, the increasing capacity of Battery Energy Storage Systems (BESS), and the development of intelligent electricity networks (Smart Grids). We focus on how the deployment of distributed BESS and centralized storage solutions not only stabilizes fluctuations in generation from advanced solar and wind sources but also provides critical network services, such as frequency regulation and optimized power flow. We examine the role of Smart Grids, which serve as the digital backbone enabling two-way communication, predictive load management, and efficient resource allocation in real-time. The paper presents a quantitative analysis of the impact of these three technologies on reducing operational costs, minimizing transmission capacity losses, and accelerating decarbonization. In conclusion, we emphasize the regulatory and investment reforms necessary to fully utilize the potential of these technologies, demonstrating that their synergy is essential for creating a resilient, flexible, and fully decarbonized energy infrastructure of the future.
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Open AccessIntegration of renewables and storage for maximum flexibility: A digital design of low-carbon grids (smart grids)
The transition to a low-carbon energy system is conditioned by the successful integration of highly variable, yet advanced, renewable energy sources (RES). This paper analyzes the transformative synergy between the next generation of RES, the increasing capacity of Battery Energy Storage Systems (BESS), and the development of intelligent electricity networks (Smart Grids). We focus on how the deployment of distributed BESS and centralized storage solutions not only stabilizes fluctuations in generation from advanced solar and wind sources but also provides critical network services, such as frequency regulation and optimized power flow. We examine the role of Smart Grids, which serve as the digital backbone enabling two-way communication, predictive load management, and efficient resource allocation in real-time. The paper presents a quantitative analysis of the impact of these three technologies on reducing operational costs, minimizing transmission capacity losses, and accelerating decarbonization. In conclusion, we emphasize the regulatory and investment reforms necessary to fully utilize the potential of these technologies, demonstrating that their synergy is essential for creating a resilient, flexible, and fully decarbonized energy infrastructure of the future.
- Open Access
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
The future of electrical power grid protection: Adaptive, intelligent, and cyber-resilient architectures for dynamic systems
The modernization of the electrical power grid, driven by high penetration of Distributed Energy Resources (DERs) and Inverter-Based Resources (IBRs), has rendered conventional phasor-based protection schemes inadequate. Bidirectional power flows, significantly limited fault current contributions, and diminished inertia fundamentally challenge the selectivity and reliability of traditional protective IEDs. To address these challenges, this paper proposes a paradigm shift towards a centralized, software-defined protection architecture designed as an intelligent overlay to existing infrastructure. The core of the proposed system lies in a dual-stream data acquisition framework: integrating real-time data from legacy digital relays with high-precision measurements from a specialized monitoring unit (as pioneered by Bencsik and Bobček). Central to this architecture is a ‘Value Approve’ mechanism, which utilizes advanced data validation techniques to ensure the integrity of measurements before processing. This enables an Adaptive Protection (AP) engine to dynamically reconfigure protection settings based on real-time topology and IBR penetration levels. A key innovation of this approach is the transition to a fully software-driven trip logic, allowing for the temporary bypassing of local hardware settings in favour of centralized, optimized decision- making. By leveraging Machine Learning for event prediction and Explainable AI (XAI) for transparency, the system mitigates the ‘black box’ risks associated with automated protection. Furthermore, the architecture integrates cyber-physical defence strategies compliant with IEC 62443 to secure the digitized communication backbone. The result is a verifiable, autonomous, and resilient protection system capable of managing the complexities of the future grid through software agility.
- 11 June 2026
- Published by EDP Sciences in EPJ Web of Conferences
- Vol. 372
Open AccessThe future of electrical power grid protection: Adaptive, intelligent, and cyber-resilient architectures for dynamic systems
The modernization of the electrical power grid, driven by high penetration of Distributed Energy Resources (DERs) and Inverter-Based Resources (IBRs), has rendered conventional phasor-based protection schemes inadequate. Bidirectional power flows, significantly limited fault current contributions, and diminished inertia fundamentally challenge the selectivity and reliability of traditional protective IEDs. To address these challenges, this paper proposes a paradigm shift towards a centralized, software-defined protection architecture designed as an intelligent overlay to existing infrastructure. The core of the proposed system lies in a dual-stream data acquisition framework: integrating real-time data from legacy digital relays with high-precision measurements from a specialized monitoring unit (as pioneered by Bencsik and Bobček). Central to this architecture is a ‘Value Approve’ mechanism, which utilizes advanced data validation techniques to ensure the integrity of measurements before processing. This enables an Adaptive Protection (AP) engine to dynamically reconfigure protection settings based on real-time topology and IBR penetration levels. A key innovation of this approach is the transition to a fully software-driven trip logic, allowing for the temporary bypassing of local hardware settings in favour of centralized, optimized decision- making. By leveraging Machine Learning for event prediction and Explainable AI (XAI) for transparency, the system mitigates the ‘black box’ risks associated with automated protection. Furthermore, the architecture integrates cyber-physical defence strategies compliant with IEC 62443 to secure the digitized communication backbone. The result is a verifiable, autonomous, and resilient protection system capable of managing the complexities of the future grid through software agility.