Overheating of photovoltaic modules (PVMs) is a key problem leading to a decrease in their efficiency and service life, especially in regions with high levels of solar radiation. The existing models are not detailed enough to accurately predict the thermal conditions of thin-film micromorphic modules under real-world operating conditions. The paper develops a three-dimensional finite element model of the Pramac 125 micromorphic module in the Ansys software package, which takes into account the geometric, optical and thermodynamic characteristics of all layers. To verify the model, a field experiment was conducted in the Astrakhan region with the registration of the module temperature and meteorological parameters. The validation confirmed the high accuracy of the model: the coefficient of determination R² between the calculated and experimental data was 0.9991. The model makes it possible to estimate thermal conditions and associated energy losses, which justifies the need to use cooling systems in the southern regions of Russia.

Keywords: photovoltaic module, micromorphic technology, solar radiation, temperature regime, output power, mathematical modeling, finite element method, thermal regimes, model validation, numerical experiment

Numerical values of the functional extrapolator of a fractal L–Markov process with a quasi-rational spectrum are obtained. The methods of correlation and regression analysis were used to calculate the predicted complex values for the lead time t. The analysis of the real and imaginary parts of the optimal extrapolator is carried out for all correct values of the lead time t. The coefficients of Pearson linear correlation and Kendall rank correlation are calculated, which indicate a high linear correlation between the real and imaginary parts of the extrapolator and their noticeable rank correlation. The representability of the optimal extrapolator for the lead time t in the form of a linear combination of the values of the fractal L–Markov process under study at five points of the L–boundary is proved. The calculated values of the beta coefficient and the Hurst index indicate the high reliability of the forecast constructed in the work.

Keywords: extrapolation, L – Markov process, fractality, trend tolerance, spectral characteristic, correlation and regression analysis, optimal extrapolator, risk

Modern retail is faced with the need to simultaneously improve customer service and optimize operating costs, which is driving the active adoption of digital solutions to automate customer interactions. This article examines the use of dialog agents to automate key processes in retail—from initial consultation to order processing and follow-up. The aim of the study is to develop and evaluate an integrated system based on a dialog agent interacting with the 1C: Trade Management corporate system. The paper presents an analysis of the retail network's domain, describes the key business processes subject to automation, and proposes a dialog agent architecture and its integration with 1C. The paper also examines CASE tools for functional modeling and analysis of company operations and presents a rule-based approach to developing conversational agents based on a dictionary-pattern concept with regular expressions and keywords. The results showed that the use of conversational agents not only reduces operating costs but also increases sales conversion. The study confirms that conversational agents are an effective tool for digital retail transformation, combining scalability, personalization, and cost effectiveness

Keywords: Sales automation, retail, conversational agent, integration, online ordering, business processes, chatbot, trade management

An asynchronous electric motor is the foundation of virtually every modern industrial machine. They are widely used in various industries and agriculture across the country. Starting electric drives for machines equipped with asynchronous motors poses a serious challenge for private workshop owners and farmers working in rural areas. This article presents a method for starting an asynchronous motor using a combination of a voltage multiplier and a frequency converter, ensuring the maintenance of the rated torque and full power of the electric drive. Using voltage multipliers to start industrial variable-frequency electric drives is an innovative solution that helps eliminate problems caused by low input voltage from the electrical grid. This is especially relevant when the actual grid voltage is below the minimum required value specified by the electrical equipment manufacturer

Keywords: automated electric drive, frequency regulation, woodworking, metalworking, voltage multiplier

The problem of managing the risks of life safety in the transport sector in modern conditions is considered. The analysis of theoretical approaches to the risk management of life safety is carried out. It is proposed to consider a set of risks consisting of typical and atypical risks. Based on the consideration of typical risk management methods, problematic areas of the risk management mechanism in the transport sector have been identified. The directions of minimizing atypical risks through the digitalization of the transport industry and the application of the "system of many units" method are formulated. Based on the analysis of environmental factors and vulnerability of a technical facility, a model for assessing typical and atypical vulnerability of a vehicle is proposed, which makes it possible to establish a relationship between vehicle vulnerability and the processes of generating safety risks. To improve the mechanism for managing atypical risks of life safety, it is proposed to use the tools of digitalization of the transport sector. It is emphasized that in order to ensure a high-tech safe transport system, it is necessary to combine the efforts of all participants in the transport process, including the Institute of Science and Education. It requires the training of modern personnel with knowledge, skills and abilities in various fields of theory and practice, as well as modern environmentally-oriented and risk-oriented thinking, taking into account the co-evolution of the human mind and artificial intelligence.

Keywords: vehicle, life safety, vulnerability, risk, risk management mechanism, vehicle vulnerability assessment model, personnel training, risk-oriented thinking, environmental-oriented thinking

This paper examines the pressing issue of designing multi-agent systems (MAS) that require high adaptability in the face of dynamically changing environmental parameters, task conditions, and the internal structure of the MAS. A comprehensive method is proposed that combines the processes of synthesizing the initial architecture and subsequently automatically adapting both the MAS architecture, which defines the basic rules of its operation, and the organizational structure, which represents a hierarchical attributed directed graph in which the vertices are agents, and the edges correspond to the relationships between them. The method is based on the author's "zoosocial model" for representing the MAS architecture. It also utilizes an artificial neural network to predict optimal actions for modifying the MAS architecture in the event of changes in environmental parameters and task conditions. The REINFORCE algorithm is used for training the ANS, and a genetic algorithm is used to generate the training sample.

Keywords: multi-agent system, architecture, organizational structure, automatic adaptation, synthesis, genetic algorithm, reinforcement learning

This paper considers the use of remote sensing of the Earth as a method of monitoring the mouth of the Don River. Particular attention is paid to the dynamics of vegetation cover and landscape changes in the period from 2015 to 2023 based on satellite images and a normalized vegetation index. According to the results of the observation, the largest area with high vegetation activity is recorded in 2023 (normalized difference vegetation index > 0.5), which is almost 1.5 times more than in 2015. This is primarily due to differences in hydrometeorological conditions. At the same time, there is an increase in anthropogenic pressure on the territory. The work highlights the effectiveness of aerospace methods for the comprehensive study of hard-to-reach delta systems.

Keywords: remote sensing of the earth, Don river delta, normalized vegetation difference index, landscape dynamics, anthropogenic impact, aerospace survey, sustainable environmental management

The article presents a new architecture for adaptive parameter tuning of population algorithms based on a combination of reinforcement learning, evolutionary selection mechanisms, and a fuzzy logic system. The developed model allows for dynamic optimization of parameters such as mutation rate, crossbreeding probability, and population size, without the need to retrain the algorithm. The practical approbation was carried out on the task of forecasting the time series of urban traffic in Beijing. The results showed an improvement in accuracy compared to modern analogues, confirming the high efficiency of the proposed approach in dynamically changing environments.

Keywords: adaptive parameter setting, reinforcement learning, population algorithms, fuzzy logic, hyperoptimization, time series forecasting

The article is devoted to solving the problem of detecting camouflaged (hidden) network connections based on the DNS protocol (Domain Name System) in an organization's corporate network. The research is aimed at developing a method for detecting camouflaged (hidden) network connections in an organization's corporate network. The proposed method is based on calculating the entropy of subdomain names, thresholds for the number of responses received from the DNS server, and the proportion of unique subdomains for each domain. Its use makes it possible to detect all types of DNS tunnels in the circulating network traffic of the corporate network, which is confirmed by the results of the experiment conducted as part of the study.

Keywords: tunneling, DNS protocol, camouflaged network connection, entropy, network connection analysis, information security

This article examines the high transaction costs of finding and verifying partners in modern business communities. It proposes a conceptual approach to networking algorithms based on predictive analytics and digital participant profiling. A three-tier interaction management model is described that enables the transformation of trust from a stochastic social resource into a manageable economic asset. Empirical data is presented confirming a 60–80% reduction in the time spent searching for relevant contacts.

Keywords: graph theory, maximum clique problem, link management

This article examines the history of the Rostov State Medical University complex in Rostov-on-Don, both as a hospital and as a higher education institution. In 1890, the foundation stone of the Nikolaevskaya Hospital, which stood on this site, was laid, and in 1915, it became the home of the Faculty of Medicine of the University of Warsaw. Today, the university continues to expand: new buildings are being built, and specialized research institutes are being established within them. The collaboration of practicing specialists and researchers facilitates the introduction of new treatment methods and improves the quality of education for students, who can gain not only theoretical but also practical knowledge.

Keywords: architecture, hospital, higher education institution, brick style, medicine, reconstruction, university, faculty

Developing video surveillance systems is a relevant and in-demand topic today. Increasing security requirements are leading to an increasing number of cameras in a system and creating a greater workload, prompting a reconsideration of video surveillance system design methods. This article describes an algorithm developed by the authors for automatically selecting a video stream processing codec in video surveillance systems. Modern video surveillance systems generate enormous volumes of data, requiring effective compression methods for storing, transmitting, and processing video streams. Selecting the appropriate codec affects image quality, network load, and computing resources, which is especially important in the context of increasing camera resolutions (4K, 8K) and the development of intelligent video analytics. In this regard, this article discusses an approach to improving video stream transmission efficiency based on the automatic selection of data processing codecs. The proposed algorithm adapts compression parameters to the current state of the scene, illumination levels, and the dynamics of objects in the frame. Using this approach allows us to reduce the requirements for communication channel bandwidth and storage capacity without significantly degrading image quality, which is especially important for distributed video surveillance systems.

Keywords: video surveillance, compression codec, video stream, automatic codec selection algorithm for video stream processing, frame difference method, signal-to-noise ratio, video coding, adaptive coding

Regression analysis is an effective tool for estimating and planning budget allocations, which allows us to identify statistical dependencies between socio-economic indicators. In this paper, based on open statistical data for 80 subjects of the Russian Federation, an analysis of the distribution of IT infrastructure financing for 2025 is carried out. The population of the region was used as an independent variable, and the planned amount of funding was used as a dependent variable. The proposed approach based on the cluster regression model has proved to be a fairly effective tool for targeted diagnostics of the state and planning of financing digital infrastructure. The results obtained make it possible to move from a unified to a differentiated regional policy in the field of digitalization, which in the future may increase the efficiency of budget expenditures and will help reduce digital inequality.

Keywords: IT infrastructure, adequacy criteria, cluster regression model, financing, forecasting, regression analysis, budget planning

The paper presents a physical model of an electric power consumer designed to reproduce the stochastic nature of phase unbalance in daily load profiles of autonomous facilities and to be used as part of a hardware-in-the-loop modeling complex for autonomous power supply systems during the development and tuning of hybrid power plant control systems. The architecture of the complex, including mathematical models of generation sources, control systems, and a physical model of the electric power consumer, is described. An approach to forming an active-reactive load based on discretely switched resistive and inductive elements is proposed, a mechanism for selecting load configurations according to specified operating parameters is implemented, and a method for scaling operating modes based on similarity theory is presented.

Keywords: physical model, autonomous power supply systems, hardware-in-the-loop modeling, hybrid power plants, Arctic zone, Far North, power supply of remote areas, active-reactive load, phase unbalance, daily load profiles, similarity theory