Aliaksey A. Kapanski

Mr. Aliaksey A. Kapanski

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2025 in Smart Cities
Verified
Journal Article
Open access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
Roman Vladimirovich KlyuevRoman Vladimirovich Klyuev
Roman Vladimirovich Klyuev
ABAleksandr E. Boltrushevich
Aleksandr E. Boltrushevich
SSSvetlana N. Sorokova
Svetlana N. Sorokova
EEEgor Alekseevich Efremenkov
Egor Alekseevich Efremenkov
Nikita MartyushevNikita Martyushev
Nikita Martyushev
For large cities with developing infrastructures, optimising water supply systems plays a crucial role. However, without a clear understanding of the network structure and water consumption patterns, addressing these challenges becomes significantly more complex. This paper proposes a methodology for geospatial data analysis aimed at solving two key tasks. The first is the delineation of service zones for infrastructure objects to enhance system manageability. The second involves the development of an approach for the optimal placement of devices to collect and transmit hydraulic network parameters, ensuring their alignment with both water supply sources and serviced areas. The study focuses on data from the water supply network of a city with a population exceeding half a million people, where hierarchical clustering using Ward’s method was applied to analyse territorial distribution. Four territorial clusters were identified, each characterised by unique attributes reflecting consumer concentration and water consumption volumes. The cluster boundaries were compared with the existing service scheme of the system, confirming their alignment with real infrastructure. The quality of clustering was further evaluated using the silhouette coefficient, which validated the high accuracy and reliability of the chosen approach. The paper demonstrates the effectiveness of cluster boundary visualisation for assessing the uniform distribution of pressure sensors within the urban water supply network. The results of the study show that integrating geographic data with water consumption information not only facilitates effective infrastructure planning and resource allocation but also lays the foundation for the digitalization of the hydraulic network, a critical component of sustainable development in modern smart cities.

2 May 2025 in Water Conservation Science and Engineering
Verified
Journal Article
Closed access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
NHNadzeya V. Hruntovich
Nadzeya V. Hruntovich
Roman Vladimirovich KlyuevRoman Vladimirovich Klyuev
Roman Vladimirovich Klyuev
Vladimir BrigidaVladimir Brigida
Vladimir Brigida

2 April 2025 in Smart Cities
Verified
Journal Article
Open access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
NHNadezeya V. Hruntovich
Nadezeya V. Hruntovich
Roman Vladimirovich KlyuevRoman Vladimirovich Klyuev
Roman Vladimirovich Klyuev
ABAleksandr E. Boltrushevich
Aleksandr E. Boltrushevich
SSSvetlana N. Sorokova
Svetlana N. Sorokova
Nikita MartyushevNikita Martyushev
Nikita Martyushev
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data pre-processing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt–Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.

9 July 2020 in E3S Web of Conferences
Verified
Conference Paper
Open access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
NHNadezhda Hruntovich
Nadezhda Hruntovich
SBSiarhei Bakhur
Siarhei Bakhur
LMLarisa Markaryants
Larisa Markaryants
LDLeonid Dolomanyak
Leonid Dolomanyak
The article considers the method of optimizing the pumps in the water supply system of the first water rise station in the zones of the day, where there is a different system of payment for electric energy. To assess the regulatory capacity of pumps on a temporary parameter, the authors of the article propose to use existing water tanks in the water supply system, which act as a buffer, smoothing the unevenness of water consumption. The studies have revealed that the comprehensive optimization of pumps on the criterion of minimizing specific electricity consumption by lifting water and optimizing the operation of pumps in the zones of the day allows to significantly improve energy efficiency and reduce the cost of extraction and transportation of water to the consumer. In the article, the authors examine an algorithm that allows us to assess the economic potential of pump regulation in the real-world conditions of the system.

7 February 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
NHNadezeya V. Hruntovich
Nadezeya V. Hruntovich
Roman Vladimirovich KlyuevRoman Vladimirovich Klyuev
Roman Vladimirovich Klyuev
ABAleksandr E. Boltrushevich
Aleksandr E. Boltrushevich
SSSvetlana N. Sorokova
Svetlana N. Sorokova
Nikita MartyushevNikita Martyushev
Nikita Martyushev
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data preprocessing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt-Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.

21 February 2025 in Science & Technique
Verified
Journal Article
Open access
PDF file
Aliaksey A. KapanskiAliaksey A. Kapanski
Aliaksey A. Kapanski
The article considers the influence of climatic factors on energy and water consumption of the urban water supply system. The purpose of the study is to identify the relationships between outdoor air temperature, precipitation and load on the water supply system to substantiate the factors necessary for creating seasonal models of water consumption and increаsing the energy efficiency of water intakes. The objective of the scientific work was to test the hypothesis, according to which an increase in air temperature leads to an increase in water consumption and, as a consequence, to an increase in energy costs for the operation of pumping stations and water treatment systems. At the same time, it was assumed that precipitation would have the opposite effect, reducing water consumption during periods of intense rainfall. The work used correlation analysis to assess the strength and direction of the relationships between air temperature, precipitation and energy and water consumption parameters. Regression analysis was used to quantitatively assess the impact of climatic factors. The moving average method was used to smooth the data and reduce the spread of random fluctuations. Data filtering and cutting methods were also used, which made it possible to divide them by temperature thresholds and conduct separate studies for different ranges. The obtained results demonstrate that the growth of energy consumption is closely related to the increase in water demand, which increases with each degree of outside air temperature. This is explained by the expected increase in water consumption for irrigation and household needs during warm periods. Above 25 °C, the temperature factor determined 15.8 % of water consumption, which also coincided with the growth of this contribution to the electricity consumption of the system (15.6 %). However, when analyzing data in the area of negative temperatures, no obvious relationship was observed between temperature and water demand. At the same time, a correlation was found between temperature and electricity consumption, which is associated with additional costs for maintaining the water supply system in cold climates. Conclusions are made about the need for further study of additional variables, such as types of weekdays (working days, weekends, holidays), seasons of the year, as well as other socio-economic factors affecting water consumption and energy costs. The comprehensive results of the work can be used for planning the work of water utilities, managing energy resources and developing strategies to improve energy efficiency in water supply systems.