Nikita Nikolaevich Sergeev

@nstu.ru

Research Assistant, Electric Power Plants Department, Faculty of Power Engineering
Novosibirsk State Technical University

Nikita Nikolaevich Sergeev


            Download Compact PDF  
https://researchid.co/nikita_n_sergeev

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering
13

Scopus Publications

Scopus Publications

  • Analysis of the impact of geographical location on the accuracy of operational forecasting of renewable energy resources
    Nikita Sergeev, Pavel Matrenin
    Aip Conference Proceedings, 2025
  • Energy Transition in Myanmar: Exploring Renewable and Nuclear Options
    Lwin Ko Ko Oo, Nikita Sergeev, Valentin Loman, Anastasia Rusina
    International Conference of Young Specialists on Micro Nanotechnologies and Electron Devices Edm, 2025
    Myanmar faces a critical energy transition driven by rising electricity demand, limited rural electrification, and global climate commitments. This paper examines the country's renewable and nuclear energy prospects by modeling three development scenarios through 2030-Base Case, Pessimistic, and Optimistic-based on policy implementation and investment levels. Scenario results indicate that available generation capacity could range from 4.5 GW (-37%) in a worst-case scenario to over 8 GW in an accelerated transition. The share of renewables in electricity generation (including hydropower) could vary from under 50% to more than 60%, depending on project realization. While solar and hydro offer near-term potential, limited grid capacity and underinvestment pose persistent risks. Nuclear power, currently in early planning stages, could provide strategic baseload capacity in the 2030s if regulatory and institutional readiness is achieved. The study concludes with eight targeted policy recommendations, highlighting the need for updated national planning, diversified investment, and parallel development of renewable and nuclear pathways to ensure energy security and climate alignment. And also, a practical recommendation for increasing the reliability of the power system using a frequency-dependent device.
  • Development of a Methodology for Assessing the Effectiveness of a Frequency-Dependent Device for the Suppression of Switching and Lightning Overvoltages
    Sergey Korobeynikov, Valentin Loman, Alexander Ridel, Dmitriy Vedernikov, Nikita Sergeev
    Proceedings of the 17th International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering Apeie 2025, 2025
    The increasing share of wind power generation in the energy system highlights the growing importance of ensuring the reliability of wind farm equipment. This equipment is particularly threatened by lightning overvoltages with a high front steepness. Traditional protection means based on surge arresters are not always effective in suppressing the high-frequency components of such pulses. This article investigates the effectiveness of using a Frequency-Dependent Device for protecting wind power facilities. Full-scale experiments were conducted on a specially developed setup generating short pulses that simulate the impact of lightning overvoltages. The methodology involved recording pulse parameters at the input and output of the Frequency-Dependent Device, followed by computer modeling in the MATLAB Simulink environment to verify the results and evaluate the device's active resistance. The results demonstrate the high effectiveness of the Frequency-Dependent Device in reducing the front steepness and amplitude of high-frequency pulses (with frequencies above 200 kHz), with the device’s efficiency increasing as the frequency of the impacting signal rises.
  • Application of Metaheuristic Algorithms for Optimization of Recloser Placement in a Power Supply System with Distributed Generation
    N. N. Sergeev, P. V. Matrenin
    Doklady Mathematics, 2024
    Abstract Efficiency and reliability optimization of distribution networks is an important task in the design of power supply systems, and its complexity increases with the development of new technologies such as distributed generation. One way to improve network reliability is through the installation and optimal placement of automatic circuit reclosers. The presence of distributed generation units and reclosers significantly increases the dimensionality of the optimization problem, thus necessitating the use of alternative approaches to solve it. The goal of the research is to analyze the effectiveness of metaheuristic algorithms in the recloser quantity and allocation optimization problem in a distribution network. The scientific novelty of the study lies in simultaneously considering the failure rate of network elements and changes in operating condition in case of contingencies. The practical significance of the work is demonstrated through the effectiveness of using metaheuristic methods when selecting the optimal equipment configuration in electrical networks. To solve the optimization problem of recloser placement in a 24-bus 10 kV network, the genetic algorithm, evolutionary strategy, and adaptive particle swarm optimization were considered. Computational experiments showed that the genetic algorithm is the most efficient in this case. The results can be further used in the development of methodological guidelines for designing distribution networks of various voltage classes.
  • Optimal load management of autonomous power systems in conditions of water shortage
    Firdavs Rahimov, Alifbek Kirgizov, Murodbek Safaraliev, Inga Zicmane, Nikita Sergeev, Pavel Matrenin
    International Journal of Electrical and Computer Engineering, 2024
    The issues of optimizing the operation of micro hydropower plants in conditions of water scarcity, performed by additional connection to the grid of an energy storage system and wind power turbine, as well as optimal load management, are considered. It is assumed that the load of the system is a concentrated autonomous power facility that consumes only active power. The paper presents a rigorous mathematical formulation of the problem, the solution of which corresponds to the minimum cost of an energy storage system and a wind turbine, which allows for uninterrupted supply of electricity to power facilities in conditions of water shortage necessary for the operation of micro hydropower plants (under unfavorable hydrological conditions). The problem is formulated as a nonlinear multi-objective optimization problem to apply metaheuristic stochastic algorithms. At the same time, a significant part of the problem is taken out and framed as a subproblem of linear programming which will make it possible to solve it by a deterministic simplex method that guarantees to find the exact global optimum. This approach will significantly increase the efficiency of solving the entire problem by combining metaheuristic algorithms and taking into account expert knowledge about the problem being solved.
  • Comparative analysis of approaches to short-term forecasting of electricity generation of wind turbine
    N. Sergeev, P. Matrenin, N. Zubova
    Aip Conference Proceedings, 2023
  • Improving Accuracy of Machine Learning Based Short-Term Load Forecasting Models with Correlation Analysis and Feature Engineering
    Nikita Sergeev, Pavel Matrenin
    International Conference of Young Specialists on Micro Nanotechnologies and Electron Devices Edm, 2023
    Short-term load forecasting is an integral part of the electric power system management and is necessary to ensure the electricity market operation. Load forecasting of individual market participants, especially industrial enterprises, can be particularly challenging due to many external factors that influence the load pattern. These factors may include a change in weather conditions, holidays and days off, economic trends, etc. Therefore, there is a need to develop new and more advanced forecasting models that are able to produce adequate predictions of future power consumption under such conditions. This study considers the task of day-ahead load forecasting of a mining and processing plant in Yakutia. The analysis of the exogenous data use impact on its load pattern was carried out. The forecasting models were built using two machine learning methods: decision tree ensembles (Adaptive Boosting, Gradient Boosting and Random Forest) and artificial neural networks (Deep Feedforward Neural Network). To improve the model performance, the following data preprocessing techniques were used: correlation analysis, feature engineering, and intelligent feature selection. The experiments show that the appropriate feature selection can significantly increase the accuracy of the forecasting models. In this case, taking into account the weather data allowed to reduce the average forecasting error by 22% for the neural network model, yielding the best result among the considered models.
  • Prediction the Power Generated Low-Power Wind Turbine Based on Multilayer Perceptron
    Natalia Zubova, Sergey Mitrofanov, Nikita Sergeev, Pavel Matrenin
    Proceedings of the 2023 Belarusian Ural Siberian Smart Energy Conference Bussec 2023, 2023
    The trend towards the development of renewable energy sources, including wind energy and their integration into energy systems leads to the emergence of various problems related to the dependence of such energy sources on weather conditions. Therefore, successful management of energy systems with a high share of wind power in the generating capacity requires the ability to predict their output with sufficiently high accuracy. Currently, various power output prediction methods are being studied in order to achieve the best possible performance, and artificial neural networks are among the most popular in that regard. This paper addresses the task of generation forecasting of an individual wind turbine using real data. The shallow feed forward neural network was created using the Neural Network Toolbox in MATLAB Software. The power generation forecasting results of the considered low- power wind turbine are presented. To evaluate proposed forecasting model performance, the mean squared error metric was used.
  • Options Analysis for the Use of Solar Generation Systems on the Territory of Hydropower Plants
    Sergey V. Mitrofanov, Nikita N. Sergeev, Natalia V. Zubova, Maria M. Zhilnikova, Pavel V. Matrenin
    International Conference of Young Specialists on Micro Nanotechnologies and Electron Devices Edm, 2023
    In this article the options for the useful use of the area of hydraulic structures and the adjacent territory of hydropower plants in order to accommodate photovoltaic panels are analyzed. The own needs of the hydropower plant are the main consumer of power for photo panels. Potentially accessible places for installation of photo panels are considered on the example of the Ust-Kamenogorsk hydropower plant. The principles and criteria for preliminary screening are formulated on the basis of a qualitative analysis of options for placing photo panels. A quantitative analysis of the technical potential of solar radiation and an assessment of the degree of coverage of the hydropower plant's own needs with the help of photo panels over the annual interval were made. Based on the results obtained, recommendations were formulated for the optimal location of photovoltaic panels on the territory of a hydroelectric power plant, in particular, on its hydraulic structures.
  • Enhancing Efficiency of Ensemble Machine Learning Models for Short-Term Load Forecasting through Feature Selection
    Nikita N. Sergeev, Pavel V. Matrenin
    International Conference of Young Specialists on Micro Nanotechnologies and Electron Devices Edm, 2022
    Electric load forecasting directly affects management planning and is necessary for the reliable functioning of electric power systems. Furthermore, accurate forecasts are required by power companies for electricity generation and distribution planning. This paper compares different approaches to the feature selection process for solving the problem of short-term forecasting of industrial enterprise power consumption using machine learning methods. A comparative analysis of the following machine learning methods was carried out: adaptive boosting over decision trees (AdaBoost), gradient boosting over decision trees (Gradient Boosting), and random forest (Random Forest). The choice of such models is due to the presence of binary features in the original data, which are best handled by decision trees. The selection of the most significant features for these models is especially important as they are prone to overfitting when the input data set is large. The most significant features of the original time series were determined by calculating the correlation coefficients between the predicted hour and the preceding hours. Moreover, the repair schedule is used as an additional feature. Several approaches to feature selection were considered. The results showed that using data only on selected hours instead of the entire time series improves the accuracy of the model and the speed of its training. It was found that the use of the maintenance schedule also significantly increases the accuracy of the forecast. The Gradient Boosting model showed the best result with an average error of 5.48 %.
  • Limitations and Perspectives of Short-Term Renewable Energy Generation Forecasting Methods
    Pavel V. Matrenin, Lola Sh. Atabaeva, Nikita N. Sergeev
    2022 IEEE International Multi Conference on Engineering Computer and Information Sciences Sibircon 2022, 2022
  • Overview of Renewable Energy Sources in Mongolia
    Pavel V. Matrenin, Tuvshin Osgonbaatar, Nikita N. Sergeev
    2022 IEEE International Multi Conference on Engineering Computer and Information Sciences Sibircon 2022, 2022
  • Short-Term Wind Speed Forecasting for an Autonomous Hybrid Power Plant of a Traction Railway Substation
    Pavel V. Matrenin, Anastasia G. Rusina, Natalya G. Kyrianova, Nikita N. Sergeev
    International Conference of Young Specialists on Micro Nanotechnologies and Electron Devices Edm, 2022