Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Darius Naujokaitis has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Memory-Based Particle Swarm Optimization for Smart Grid Virtual Power Plant Scheduling Using Fractional Calculus

    by Naiyer Mohammadi Lanbaran, Darius Naujokaitis, Gediminas Kairaitis, Virginijus Radziukynas, Arturas Klementavičius

    This paper presents an engineering framework for smart grid virtual power plant (VPP) day-ahead scheduling using fractional calculus-enhanced particle swarm optimization, targeting practical deployment in energy management systems. A fractional calculus-enhanced particle swarm optimization algorithm was developed and validated for day-ahead scheduling in virtual power plants using authentic market data and rigorous statistical analysis. The algorithm incorporates Grünwald–Letnikov fractional derivatives with adaptive memory into particle velocity updates, enabling trajectory-aware search that leverages historical exploration patterns. A factorial experiment across 500 independent test cases (50 dates × 10 trials) with controlled random seeds demonstrated that fractional particle swarm optimization increased mean daily profit by $205, representing a 4.1% improvement over standard particle swarm optimization. Wilcoxon signed-rank tests confirmed statistical significance (p < 0.0001, Cohen’s d = 1.08), with superior performance observed in 89.4% of cases. The factorial design identified fractional calculus as the primary performance driver, while advanced scenario generation provided no significant additional benefit. Sensitivity analysis indicated that wind generation variability was the primary predictor of performance variance, with profit difference standard deviations ranging from $34 to $325 depending on meteorological conditions, supporting the use of adaptive computational strategies. Computation required approximately two minutes per optimization on standard hardware. These findings establish fractional calculus as a credible enhancement for operational energy systems and demonstrate that the quality of optimization algorithms outweighs the complexity of forecast uncertainty modeling. The results extend fractional calculus applications from benchmark functions to practical infrastructure scheduling, with projected annual value exceeding $74,000 for a 50-megawatt system. The three-stage optimization architecture is designed for integration with standard energy management systems and SCADA platforms, offering a deployable pathway for smart grid operators.


  • Investigation of a Provable Data Possession Method for the Virtual Machine File System

    by Dangis Rimkus, Vytautas Barauskas, Darius Naujokaitis, KęStutis Paulikas, Aušra Gadeikytė

  • Open Access

    Hybrid Hourly Solar Energy Forecasting Using BiLSTM Networks with Attention Mechanism, General Type-2 Fuzzy Logic Approach: A Comparative Study of Seasonal Variability in Lithuania

    by Naiyer Mohammadi Lanbaran, Darius Naujokaitis, Gediminas Kairaitis, Virginijus Radziukynas

    This research introduces a novel hybrid forecasting framework for solar energy prediction in high-latitude regions with extreme seasonal variations. This approach uniquely employs General Type-2 Fuzzy Logic (GT2-FL) for data preprocessing and uncertainty handling, followed by two advanced neural architectures, including BiLSTM and SCINet with Time2Vec encoding and Variational Mode Decomposition (VMD) signal processing. Four configurations are systematically evaluated: BiLSTM-Time2Vec, BiLSTM-VMD, SCINet-Time2Vec, and SCINet-VMD, each tested with GT2-FL preprocessed data and raw input data. Using meteorological data from Lithuania (2023–2024) with extreme seasonal variations where daylight hours range from 17 h in summer to 7 h in winter, F-BiLSTM-Time2Vec achieved exceptional performance, with nRMSE = 1.188%, NMAE = 0.813%, and WMAE = 3.013%, significantly outperforming both VMD-based variants and SCINet architectures. Comparative analysis revealed that Time2Vec encoding proved more beneficial than VMD preprocessing, especially when enhanced with fuzzification. The results confirm that fuzzification, BiLSTM architecture, and Time2Vec encoding provide the most robust forecasting capability under various seasonal conditions.


  • Open Access

    The Forecast of the Wind Turbine Generated Power Using Hybrid (LTC + XGBoost) Model

    by Justina Krevnevičiūtė, Arnas Mitkevičius, Darius Naujokaitis, Ingrida Lagzdinytė-Budnikė, Mantas Marčiukaitis

    This publication presents a novel approach to predicting the amount of electricity generated by wind power plants. The research focuses on data-driven models such as XGBoost, Liquid Time-constant Networks, and covers both the analysis of properties of individual forecasting models as well as aspects of their integration into a hybrid model. By analyzing real-world weather scenarios, the approach aims to identify the highest accuracy forecasting model for the short-term 24-h forecast of wind farm power output. A more accurate forecast allows for more efficient resource planning and better distribution of resources on the electricity grids, thus ensuring a greener approach to energy production. The study shows that the proposed Hybrid (XGBoost + LTC) model predicts wind power generation with an nMAE of 0.0856, representing an improvement over standalone XGBoost and LTC models, and outperforming classical approaches such as LSTM and statistical models like ARIMAX in terms of forecasting accuracy.


  • Open Access

    Power Quality Impact and Its Assessment: A Review and a Survey of Lithuanian Industrial Companies

    by Vladislav Liubčuk, Virginijus Radziukynas, Gediminas Kairaitis, Darius Naujokaitis

    Poor PQ is a partial case of power system impact on society and the environment. Although the significance of good PQ is generally understood, the topic has not yet been sufficiently explored in the scientific literature. Firstly, this paper discusses the role of PQ in sustainable development by distinguishing economic, environmental, and social parts, including the existing PQ impact assessment methods. PQ problems must be studied through such prisms as financial losses of industrial companies, damage to end-use equipment, natural phenomena, interaction with animals, and social issues related to law, people’s well-being, health and safety. Secondly, this paper presents the results of the survey of Lithuanian industrial companies, which focuses on the assessment of industrial equipment immunity to both voltage sags and supply interruptions, as well as a unique methodology based on expert assessment, IEEE Std 1564-2014 and EN 50160:2010 voltage sag tables, matrix theory, a statistical hypothesis test, and convolution-based sample comparison that was developed for this purpose. The survey was carried out during the PQ monitoring campaign in the Lithuanian DSO grid, and is one of the few PQ surveys presented in the scientific literature. After counting the votes and introducing the rating system (with and without weights), the samples are compared both qualitatively and quantitatively in order to determine whether the PQ impact on various end-use equipment is similar or not.


  • Open Access

    Overview of Startups Developing Artificial Intelligence for the Energy Sector

    by Naiyer Mohammadi Lanbaran, Darius Naujokaitis, Gediminas Kairaitis, Gabrielė Jenciūtė, Neringa Radziukynienė

    The energy industry is experiencing a major change due to fast progress in artificial intelligence (AI). Startup companies in this revolution use AI technologies like Machine Learning (ML), predictive analytics, and optimization algorithms to improve energy efficiency, optimize grid management, and incorporate renewable energy sources. AI-powered solutions allow for a more accurate prediction of demand, immediate monitoring, and automated decision-making processes, significantly enhancing operational efficiency and sustainability. Through promoting a more effective energy system, these advancements play a vital role in the worldwide battle against climate change and carbon dioxide emissions. Adding to the progress of AI, quantum computing (QC) shows great potential despite being a nascent area. The collaboration of AI and QC is poised to transform the energy industry by offering unmatched computational capabilities. This blend of technologies can tackle intricate energy obstacles like enhancing power grids and enhancing battery storage, which traditional computers cannot currently handle. Combining QC with AI speeds up innovation, providing advanced solutions that improve the resilience and efficiency of energy networks. This paper discusses the latest advancements, possible effects, and upcoming paths of new companies leading in AI and QC innovations within the energy industry. Their joint responsibility is highlighted in advancing a sustainable and intelligent energy future, as well as tackling crucial environmental issues and lessening the impact of climate change.


  • Open Access

    IIR Shelving Filter, Support Vector Machine and k-Nearest Neighbors Algorithm Application for Voltage Transients and Short-Duration RMS Variations Analysis

    by Vladislav Liubčuk, Gediminas Kairaitis, Virginijus Radziukynas, Darius Naujokaitis

    This paper focuses on both voltage transients and short-duration RMS variations, and presents a unique and heterogeneous approach to their assessment by applying AI tools. The database consists of both real (obtained from Lithuanian PQ monitoring campaigns) and synthetic data (obtained from the simulation and literature review). Firstly, this paper investigates the fundamental grid component and its harmonics filtering with an IIR shelving filter. Secondly, in a key part, both SVM and KNN are used to classify PQ events by their primary cause in the voltage–duration plane as well as by the type of short circuit in the three-dimensional voltage space. Thirdly, since it seemed to be difficult to interpret the results in the three-dimensional space, the new method, based on Clarke transformation, is developed to convert it to two-dimensional space. The method shows an outstanding performance by avoiding the loss of important information. In addition, a geometric analysis of the fault voltage in both two-dimensional and three-dimensional spaces revealed certain geometric patterns that are undoubtedly important for PQ classification. Finally, based on the results of a PQ monitoring campaign in the Lithuanian distribution grid, this paper presents a unique discussion regarding PQ assessment gaps that need to be solved in anticipation of a great leap forward and refers them to PQ legislation.


  • Open Access

    Power Quality Monitors Displacement Based on Voltage Sags Propagation Mechanism and Grid Reliability Indexes

    by Vladislav Liubčuk, Virginijus Radziukynas, Gediminas Kairaitis, Darius Naujokaitis

    Nowadays, voltage sag continues to remain a critical PQ issue in the industry. Since it is not possible to install a voltage analyzer on every node, optimal monitoring locations must be determined. However, during the PQ monitoring campaign of the Lithuanian DSO grid, the execution of this task was inhibited by the lack of knowledge and literature about the fundamentals of voltage sags propagation. Therefore, the first part of this paper investigates the propagation paths of voltage sags by using a voltage sag matrix method on the created test grid, which for the first time is BRELL-based. This paper is the first to not only investigate voltage sags propagation paths (both downward and upward) in detail, but also to investigate them complexly, encompassing all four types of short-circuits, both voltages (phase-to-phase and phase-to-ground), and interconnections with other PQ events (interruption, transient, unbalance). The result has established a generalization of voltage sags propagation mechanisms by inductive reasoning and laid the foundation for the further development of PQ theory. The second part of this paper focuses on the Lithuanian DSO grid and is one of the first to investigate voltage sags/interruptions through the prism of both relationship with reliability indexes (SAIFI and SAIDI) and primary causes. For this purpose, we created our own scientific methodology, applying known probabilistic and statistical methods along with newly proposed approaches, in particular for ACR success evaluation and estimation of functions similarity.


  • Open Access

    Grid Nodes Selection Strategies for Power Quality Monitoring

    by Vladislav Liubčuk, Virginijus Radziukynas, Darius Naujokaitis, Gediminas Kairaitis

    In the past few years, technical progress has determined traditional electric power system conversion to Smart Grids, and consequently empowered a worldwide renaissance in the forgotten PQ field. Since the installation of PQ monitors is currently associated with high investments and operational costs, it is inappropriate to install a monitor on each grid busbar. Hence, grid operators must establish the best cost–benefit scenario for monitors installation and achieve maximal observability with a limited number of analyzers. Firstly, this paper presents a review of the state-of-the-art of displacement strategies, and discusses them regarding the tendencies of node selection criteria, the test schemes used, and the grid size. Secondly, the relevant fundamental issues which must be solved in the future in order to eliminate restrictions in PQ monitors’ allocation planning are presented and discussed. These issues concern the treatment, interpretation, and assessment of PQ events, measurement chain technical features, PQ’s role in the grid planning stage, communication technologies, and other remote monitoring aspects, and integration with other Smart Grid applications. The provided insights are based on experience which has been obtained during the PQ measurement campaign in the Lithuanian DSO grid. Finally, a PQ system development strategy—both short-term and long-term perspectives—in the Lithuanian distribution grid is presented, including monitors allocation criteria.


  • Utility of statistical model checking of stochastic hybrid automata for patient controlled analgesia

    by Darius Naujokaitis, Henrikas Pranevicius, Vytautas Pilkauskas, Osvaldas Pranevicius, Mindaugas Pranevicius

    Opiate concentration in the effect compartment of the brain (OCEC) determines both, the pain control and the side effects. This concentration can be estimated using pharmacodynamics models; however, these models do not predict OCEC when delivery of the drug is random.We are proposing to use stochastic hybrid automata for the verification of individualized model of patient’s drug demands and model of patient’s pharmacokinetics for the estimation of OCEC, and to express results as the probability of falling below the minimum effective analgesic concentration (MEAC) and/or probability of exceeding toxic concentration threshold. Patient controlled analgesia (PCA) model was based on the stochastic hybrid automata, while the verification of the model was done using UPPALL-SMC tool. The suggested approach allowed for quantitative prediction of the OCEC.DOI: http://dx.doi.org/10.5755/j01.eie.23.6.17572