All issues

Scheduling computational workflows represented by directed acyclic graphs (DAGs) is crucial in many areas of computer science, such as cloud/edge tasks with distributed workloads and data mining. The complexity of online DAG scheduling is compounded by the large number of computational nodes, data transfer delays, heterogeneity (by type and processing power) of executors, precedence constraints imposed by DAG, and the nonuniform arrival of tasks. This paper introduces the Multi-Agent Local Voting Protocol (MLVP), a novel approach focused on dynamic load balancing for DAG scheduling in heterogeneous computing environments, where executors are represented as agents. The MLVP employs a local voting protocol to achieve effective load distribution by formulating the problem as a differentiated consensus achievement. The algorithm calculates an aggregated DAG metric for each executor-node pair based on node dependencies, node availability, and executor performance. The balance of these metrics as a weighted sum is optimized using a genetic algorithm to assign tasks probabilistically, achieving efficient workload distribution via information sharing and reaching consensus among the executors across the system and thus improving makespan. The effectiveness of the MLVP is demonstrated through comparisons with the state-of-the-art DAG scheduling algorithm and popular heuristics such as DONF, FIFO, Min- Min, and Max-Min. Numerical simulations show that MLVP achieves makepsan improvements of up to 70% on specific graph topologies and an average makespan reduction of 23.99% over DONF (state-of-the-art DAG scheduling heuristic) across randomly generated diverse set of DAGs. Notably, the algorithm’s scalability is evidenced by enhanced performance with increasing numbers of executors and graph nodes.

The article presents updated technologies for solving two classes of linear resource allocation problems with dynamically changing characteristics of situational management systems and awareness of experts (and/or trained robots). The search for solutions is carried out in an interactive mode of computational experiment using updatable knowledge systems about problems considered as constructive objects (in accordance with the methodology of formalization of knowledge about programmable problems created in the theory of S-symbols). The technologies are focused on implementation in the form of Internet services. The first class includes resource allocation problems solved by the method of targeted solution movement. The second is the problems of allocating a single resource in hierarchical systems, taking into account the priorities of expense items, which can be solved (depending on the specified mandatory and orienting requirements for the solution) either by the interval method of allocation (with input data and result represented by numerical segments), or by the targeted solution movement method. The problem statements are determined by requirements for solutions and specifications of their applicability, which are set by an expert based on the results of the portraits of the target and achieved situations analysis. Unlike well-known methods for solving resource allocation problems as linear programming problems, the method of targeted solution movement is insensitive to small data changes and allows to find feasible solutions when the constraint system is incompatible. In single-resource allocation technologies, the segmented representation of data and results allows a more adequate (compared to a point representation) reflection of the state of system resource space and increases the practical applicability of solutions. The technologies discussed in the article are programmatically implemented and used to solve the problems of resource basement for decisions, budget design taking into account the priorities of expense items, etc. The technology of allocating a single resource is implemented in the form of an existing online cost planning service. The methodological consistency of the technologies is confirmed by the results of comparison with known technologies for solving the problems under consideration.

In this paper we present a mathematical model and numerical results on a propagation of the combustion front of the SHS compound, where the rate of chemical reaction at each point of the SHS sample is determined by solving the problem of diffusion and chemical reaction in the reaction cell. We obtained the dependence of the combustion front on the size of the average element of a heterogeneous structure with different values of the diffusion intensity. These dependences agree qualitatively with the experimental data. We studied the effect of activation energy for diffusion on the propagation velocity of combustion front. It is revealed the propagation of the combustion front transforms to an oscillatory regime at increase in activation energy of diffusion. A transition boundary of the combustion front propagation from the steady-state regime to the oscillatory one is defined.

The article is dedicated to choose of method for digital signal filtering with continuous 'on-line' data entry and to use of filtration algorithm based on the fast wavelet transform for special problem.

In this paper the problem of automated building of a citation graph from a collection of scientific documents is considered as a sequence of machine learning tasks. The overall data processing technology is described which consists of six stages: preprocessing, metainformation extraction, bibliography lists extraction, splitting bibliography lists into separate bibliography records, standardization of each bibliography record, and record linkage. The goal of this paper is to provide a survey of approaches and algorithms suitable for each stage, motivate the choice of the best combination of algorithms, and adapt some of them for multilingual bibliographies processing. For some of the tasks new algorithms and heuristics are proposed and evaluated on the mixed English and Russian documents corpora.

In the paper we consider the inverse problem of evaluating kinetic parameters of the model of dehydriding of metal powder using experimental data. The «blind search» in the space of parameters revealed multiple physically reasonable solutions. The solutions were obtained using high–performance computational modeling based on BOINC–grid.

In this paper, we propose a new software for simulation of fluid-structure interaction. The software is designed for solving coupled problems and provides an interface for synchronization synchronisation and data exchange between existing fluid and structural solvers. Algorithms of coupling solvers and mesh deformation are discussed. The software can be used on hybrid CPU/GPU platforms.

We study the motion and destruction of Chelyabinsk meteoroid using simple physical and mathematical models. We evaluate the parameters of the motion, taking into account the ablation and mechanical destruction of the meteoroid, and compare our results to the observation data.

The report presents a number of news and updates of the ALICE computing for RUN2 and RUN3.

This includes:

– implementation in production of a new system EOS;

– migration to the file system CVMFS to be used for storage of the software;

– the plan for solving the problem of “Long-Term Data Preservation”;

– overview of the concept of “O square”, combining offline and online data processing;

– overview of the existing models to use the virtual clouds for ALICE data processing. Innovations are shown on the example of the Russian sites.

We investigate machine learning methods with a certain kind of decision rule. In particular, inverse-distance method of interpolation, method of interpolation by radial basis functions, the method of multidimensional interpolation and approximation, based on the theory of random functions, the last method of interpolation is kriging. This paper shows a method of rapid retraining “model” when adding new data to the existing ones. The term “model” means interpolating or approximating function constructed from the training data. This approach reduces the computational complexity of constructing an updated “model” from $O(n^3)$ to $O(n^2)$. We also investigate the possibility of a rapid assessment of generalizing opportunities “model” on the training set using the method of cross-validation leave-one-out cross-validation, eliminating the major drawback of this approach — the necessity to build a new “model” for each element which is removed from the training set.