All issues

In various applications arise problems modeled by nonlinear partial differential equations on graphs (networks, trees). In order to study such problems and various extreme situations arose in the problems of designing and optimizing networks developed the computational model based on solving the corresponding boundary problems for partial differential equations of hyperbolic type on graphs (networks, trees). As applications, three different problems were chosen solved in the framework of the general approach of network computational models. The first was modeling of traffic flow. In solving this problem, a macroscopic approach was used in which the transport flow is described by a nonlinear system of second-order hyperbolic equations. The results of numerical simulations showed that the model developed as part of the proposed approach well reproduces the real situation various sections of the Moscow transport network on significant time intervals and can also be used to select the most optimal traffic management strategy in the city. The second was modeling of data flows in computer networks. In this problem data flows of various connections in packet data network were simulated as some continuous medium flows. Conceptual and mathematical network models are proposed. The numerical simulation was carried out in comparison with the NS-2 network simulation system. The results showed that in comparison with the NS-2 packet model the developed streaming model demonstrates significant savings in computing resources while ensuring a good level of similarity and allows us to simulate the behavior of complex globally distributed IP networks. The third was simulation of the distribution of gas impurities in ventilation networks. It was developed the computational mathematical model for the propagation of finely dispersed or gas impurities in ventilation networks using the gas dynamics equations by numerical linking of regions of different sizes. The calculations shown that the model with good accuracy allows to determine the distribution of gas-dynamic parameters in the pipeline network and solve the problems of dynamic ventilation management.

The paper proposes and investigates a mathematical model of a distributed computing system of parallel interacting processes competing for the use of a limited number of copies of a structured software resource. In cases of unlimited and limited parallelism by the number of processors of a multiprocessor system, the problems of determining operational and exact values of the execution time of heterogeneous and identically distributed competing processes in a synchronous mode are solved, which ensures a linear order of execution of blocks of a structured software resource within each of the processes without delays. The obtained results can be used in a comparative analysis of mathematical relationships for calculating the implementation time of a set of parallel distributed interacting competing processes, a mathematical study of the efficiency and optimality of the organization of distributed computing, solving problems of constructing an optimal layout of blocks of an identically distributed system, finding the optimal number of processors that provide the directive execution time of given volumes of computations. The proposed models and methods open up new prospects for solving problems of optimal distribution of limited computing resources, synchronization of a set of interacting competing processes, minimization of system costs when executing parallel distributed processes.

The paper presents a mathematical model to be used for design of cooling tanks for vapor desublimation. Results of calculations for the process of cooling of two tanks in a block of four are presented. Chart of the cooling air flow in the piping network is presented.

For the production of purified final product in chemical engineering used the process of desublimation. For this purpose, the tank is cooled by liquid nitrogen or cold air. The mixture of gases flows inside the tank and is cooled to the condensation or desublimation temperature some components of the gas mixture. The condensed components are deposited on the walls of the tank. The article presents a mathematical model to calculate the cooling air tanks for desublimation of vapours. A mathematical model based on equations of gas dynamics and describes the movement of cooled air in the duct and the heat exchanger with heat exchange and friction. The heat of the phase transition is taken into account in the boundary condition for the heat equation by setting the heat flux. Heat transfer in the walls of the pipe and in the tank wall is described by the nonstationary heat conduction equations. The solution of the system of equations is carried out numerically. The equations of gas dynamics are solved by the method of S. K. Godunov. The heat equation are solved by an implicit finite difference scheme. The article presents the results of calculations of the cooling of two successively installed tanks. The initial temperature of the tanks is equal to 298 K. Cold air flows through the tubing, through the heat exchanger of the first tank, then through conduit to the heat exchanger second tank. During the 20 minutes of tank cool down to operating temperature. The temperature of the walls of the tanks differs from the air temperature not more than 1 degree. The flow of cooling air allows to maintain constant temperature of the walls of the tank in the process of desublimation components from a gas mixture. The results of analytical evaluation of the time of cooling tank and temperature difference between the tank walls and air with the vapor desublimation. Analytical assessment is based on determining the time of heat relaxation temperature of the tank walls. The results of evaluations are satisfactorily coincide with the results of calculations by the present model. The proposed approach allows calculating the cooling tanks with a flow of cold air supplied via the pipeline system.

This paper investigates the effectiveness of Retrieval-Augmented Generation (RAG) combined with various Large Language Models (LLMs) for document retrieval and information access in corporate information systems. We survey typical use-cases of LLMs in enterprise environments, outline the RAG architecture, and discuss the major challenges that arise when integrating LLMs into a RAG pipeline. A system architecture is proposed that couples a text-vector encoder with an LLM. The encoder builds a vector database that indexes a library of corporate documents. For every user query, relevant contextual fragments are retrieved from this library via the FAISS engine and appended to the prompt given to the LLM. The LLM then generates an answer grounded in the supplied context. The overall structure and workflow of the proposed RAG solution are described in detail. To justify the choice of the generative component, we benchmark a set of widely used LLMs — ChatGPT, GigaChat, YandexGPT, Llama, Mistral, Qwen, and others — when employed as the answer-generation module. Using an expert-annotated test set of queries, we evaluate the accuracy, completeness, linguistic quality, and conciseness of the responses. Model-specific characteristics and average response latencies are analysed; the study highlights the significant influence of available GPU memory on the throughput of local LLM deployments. An overall ranking of the models is derived from an aggregated quality metric. The results confirm that the proposed RAG architecture provides efficient document retrieval and information delivery in corporate environments. Future research directions include richer context augmentation techniques and a transition toward agent-based LLM architectures. The paper concludes with practical recommendations on selecting an optimal RAG–LLM configuration to ensure fast and precise access to enterprise knowledge assets.

The fast-paced environment of DevSecOps requires integrating security at every stage of software development to ensure secure, compliant applications. Traditional methods of security testing, often performed late in the development cycle, are insufficient to address the unique challenges of continuous integration and continuous deployment (CI/CD) pipelines, particularly in complex, high-stakes sectors such as industrial automation. In this paper, we propose an approach that automates the analysis and testing of security requirements by embedding requirements verification into the CI/CD pipeline. Our method employs the ARQAN tool to map high-level security requirements to Security Technical Implementation Guides (STIGs) using semantic search, and RQCODE to formalize these requirements as code, providing testable and enforceable security guidelines.We implemented ARQAN and RQCODE within a CI/CD framework, integrating them with GitHub Actions for realtime security checks and automated compliance verification. Our approach supports established security standards like IEC 62443 and automates security assessment starting from the planning phase, enhancing the traceability and consistency of security practices throughout the pipeline. Evaluation of this approach in collaboration with an industrial automation company shows that it effectively covers critical security requirements, achieving automated compliance for 66.15% of STIG guidelines relevant to the Windows 10 platform. Feedback from industry practitioners further underscores its practicality, as 85% of security requirements mapped to concrete STIG recommendations, with 62% of these requirements having matching testable implementations in RQCODE. This evaluation highlights the approach’s potential to shift security validation earlier in the development process, contributing to a more resilient and secure DevSecOps lifecycle.

The method for mapping of intermediate representations (IR) set of C, C++ programs to vector embedding space is considered to create an empirical estimation framework for static performance prediction using LLVM compiler infrastructure. The usage of embeddings makes programs easier to compare due to avoiding Control Flow Graphs (CFG) and Data Flow Graphs (DFG) direct comparison. This method is based on transformation series of the initial IR such as: instrumentation — injection of artificial instructions in an instrumentation compiler’s pass depending on load offset delta in the current instruction compared to the previous one, mapping of instrumented IR into multidimensional vector with IR2Vec and dimension reduction with t-SNE (t-distributed stochastic neighbor embedding) method. The D1 cache miss ratio measured with perf stat tool is considered as performance metric. A heuristic criterion of programs having more or less cache miss ratio is given. This criterion is based on embeddings of programs in 2D-space. The instrumentation compiler’s pass developed in this work is described: how it generates and injects artificial instructions into IR within the used memory model. The software pipeline that implements the performance estimation based on LLVM compiler infrastructure is given. Computational experiments are performed on synthetic tests which are the sets of programs with the same CFGs but with different sequences of offsets used when accessing the one-dimensional array of a given size. The correlation coefficient between performance metric and distance to the worst program’s embedding is measured and proved to be negative regardless of t-SNE initialization. This fact proves the heuristic criterion to be true. The process of such synthetic tests generation is also considered. Moreover, the variety of performance metric in programs set in such a test is proposed as a metric to be improved with exploration of more tests generators.

Processing of large amounts of data often consists of several steps, e.g. pre- and post-processing stages, which are executed sequentially with data written to disk after each step, however, when pre-processing stage for each task is different the more efficient way of processing data is to construct a pipeline which streams data from one stage to another. In a more general case some processing stages can be factored into several parallel subordinate stages thus forming a distributed pipeline where each stage can have multiple inputs and multiple outputs. Such processing pattern emerges in a problem of classification of wave energy spectra based on analytic approximations which can extract different wave systems and their parameters (e.g. wave system type, mean wave direction) from spectrum. Distributed pipeline approach achieves good performance compared to conventional “sequential-stage” processing.