All issues

The article deals with the problem of a distributed system operation reliability. The system core is an open integration platform that provides interaction of varied software for modeling gas transportation. Some of them provide an access through thin clients on the cloud technology “software as a service”. Mathematical models of operation, transmission and computing are to ensure the operation of an automated dispatching system for oil and gas transportation. The paper presents a system solution based on the theory of Markov random processes and considers the stable operation stage. The stationary operation mode of the Markov chain with continuous time and discrete states is described by a system of Chapman–Kolmogorov equations with respect to the average numbers (mathematical expectations) of the objects in certain states. The objects of research are both system elements that are present in a large number – thin clients and computing modules, and individual ones – a server, a network manager (message broker). Together, they are interacting Markov random processes. The interaction is determined by the fact that the transition probabilities in one group of elements depend on the average numbers of other elements groups.

The authors propose a multi-criteria dispersion model of risk assessment for such systems (both in the broad and narrow sense, in accordance with the IEC standard). The risk is the standard deviation of estimated object parameter from its average value. The dispersion risk model makes possible to define optimality criteria and whole system functioning risks. In particular, for a thin client, the following is calculated: the loss profit risk, the total risk of losses due to non-productive element states, and the total risk of all system states losses.

Finally the paper proposes compromise schemes for solving the multi-criteria problem of choosing the optimal operation strategy based on the selected set of compromise criteria.

The two significant geometric parameters are proposed that affect the physical quantities interpolation in the smoothed particle hydrodynamics method (SPH). They are: the smoothing coefficient which the particle size and the smoothing radius are connecting and the volume coefficient which determine correctly the particle mass for a given particles distribution in the medium.

In paper proposes a technique for these parameters influence assessing on the SPH method interpolations accuracy when the hydrostatic problem solving. The analytical functions of the relative error for the density and pressure gradient in the medium are introduced for the accuracy estimate. The relative error functions are dependent on the smoothing factor and the volume factor. Designating a specific interpolation form in SPH method allows the differential form of the relative error functions to the algebraic polynomial form converting. The root of this polynomial gives the smoothing coefficient values that provide the minimum interpolation error for an assigned volume coefficient.

In this work, the derivation and analysis of density and pressure gradient relative errors functions on a sample of popular nuclei with different smoothing radius was carried out. There is no common the smoothing coefficient value for all the considered kernels that provides the minimum error for both SPH interpolations. The nuclei representatives with different smoothing radius are identified which make it possible the smallest errors of SPH interpolations to provide when the hydrostatic problem solving. As well, certain kernels with different smoothing radius was determined which correct interpolation do not allow provide when the hydrostatic problem solving by the SPH method.

Actin is a conserved structural protein that is expressed in all eukaryotic cells. When polymerized, it forms long filaments of fibrillar actin, or F-actin, which are involved in the formation of the cytoskeleton, in muscle contraction and its regulation, and in many other processes. The dynamic and mechanical properties of actin are important for interaction with other proteins and the realization of its numerous functions in the cell. We performed 204.8 ns long molecular dynamics (MD) simulations of an actin filament segment consisting of 24 monomers in the absence and the presence of MgADP at 300 K in the presence of a solvent and at physiological ionic strength using the AMBER99SBILDN and CHARMM36 force fields in the GROMACS software environment, using modern structural models as the initial structure obtained by high-resolution cryoelectron microscopy. MD calculations have shown that the stationary regime of fluctuations in the structure of the F-actin long segment is developed 80–100 ns after the start of the MD trajectory. Based on the results of MD calculations, the main parameters of the actin helix and its bending, longitudinal, and torsional stiffness were estimated using a section of the calculation model that is far enough away from its ends. The estimated subunit axial (2.72–2.75 nm) and angular (165–168^◦) translation of the F-actin helix, its bending (2.8–4.7 · 10⁻²⁶ N·m²), longitudinal (36–47·10⁻⁹ N), and torsional (2.6–3.1·10⁻²⁶ N·m²) stiffness are in good agreement with the results of the most reliable experiments. The results of MD calculations have shown that modern structural models of F-actin make it possible to accurately describe its dynamics and mechanical properties, provided that computational models contain a sufficiently large number of monomers, modern force fields, and relatively long MD trajectories are used. The inclusion of actin partner proteins, in particular, tropomyosin and troponin, in the MD model can help to understand the molecular mechanisms of such important processes as the regulation of muscle contraction.

This article reviews both historical achievements and modern results in the field of Markov Decision Process (MDP) and convex optimization. This review is the first attempt to cover the field of reinforcement learning in Russian in the context of convex optimization. The fundamental Bellman equation and the criteria of optimality of policy — strategies based on it, which make decisions based on the known state of the environment at the moment, are considered. The main iterative algorithms of policy optimization based on the solution of the Bellman equations are also considered. An important section of this article was the consideration of an alternative to the $Q$-learning approach — the method of direct maximization of the agent’s average reward for the chosen strategy from interaction with the environment. Thus, the solution of this convex optimization problem can be represented as a linear programming problem. The paper demonstrates how the convex optimization apparatus is used to solve the problem of Reinforcement Learning (RL). In particular, it is shown how the concept of strong duality allows us to naturally modify the formulation of the RL problem, showing the equivalence between maximizing the agent’s reward and finding his optimal strategy. The paper also discusses the complexity of MDP optimization with respect to the number of state–action–reward triples obtained as a result of interaction with the environment. The optimal limits of the MDP solution complexity are presented in the case of an ergodic process with an infinite horizon, as well as in the case of a non-stationary process with a finite horizon, which can be restarted several times in a row or immediately run in parallel in several threads. The review also reviews the latest results on reducing the gap between the lower and upper estimates of the complexity of MDP optimization with average remuneration (Averaged MDP, AMDP). In conclusion, the real-valued parametrization of agent policy and a class of gradient optimization methods through maximizing the $Q$-function of value are considered. In particular, a special class of MDPs with restrictions on the value of policy (Constrained Markov Decision Process, CMDP) is presented, for which a general direct-dual approach to optimization with strong duality is proposed.

The course and outcome of the battle is largely dependent on the morale of the troops, characterized by the percentage of loss in killed and wounded, in which the troops still continue to fight. Every fight is a psychological act of ending his rejection of one of the parties. Typically, models of battle psychological factor taken into account in the decision of Lanchester equations (the condition of equality of forces, when the number of one of the parties becomes zero). It is emphasized that the model Lanchester type satisfactorily describe the dynamics of the battle only in the initial stages. To resolve this contradiction is proposed to use a modification of Lanchester's equations, taking into account the fact that at any moment of the battle on the enemy firing not affected and did not abandon the battle fighters. The obtained differential equations are solved by numerical method and allow the dynamics to take into account the influence of psychological factor and evaluate the completion time of the conflict. Computational experiments confirm the known military theory is the fact that the fight usually ends in refusal of soldiers of one of the parties from its continuation (avoidance of combat in various forms). Along with models of temporal and spatial dynamics proposed to use a modification of the technology features of the conflict of S. Skaperdas, based on the principles of combat. To estimate the probability of victory of one side in the battle takes into account the interest of the maturing sides of the bloody casualties and increased military superiority.

The paper proposes a mathematical model for the therapy of glioma, taking into account the blood-brain barrier, radiotherapy and antibody therapy. The parameters were estimated from experimental data and the evaluation of the effect of parameter values on the effectiveness of treatment and the prognosis of the disease were obtained. The possible variants of sequential use of radiotherapy and the effect of antibodies have been explored. The combined use of radiotherapy with intravenous administration of $mab$ $Cx43$ leads to a potentiation of the therapeutic effect in glioma.

Radiotherapy must precede chemotherapy, as radio exposure reduces the barrier function of endothelial cells. Endothelial cells of the brain vessels fit tightly to each other. Between their walls are formed so-called tight contacts, whose role in the provision of BBB is that they prevent the penetration into the brain tissue of various undesirable substances from the bloodstream. Dense contacts between endothelial cells block the intercellular passive transport.

The mathematical model consists of a continuous part and a discrete one. Experimental data on the volume of glioma show the following interesting dynamics: after cessation of radio exposure, tumor growth does not resume immediately, but there is some time interval during which glioma does not grow. Glioma cells are divided into two groups. The first group is living cells that divide as fast as possible. The second group is cells affected by radiation. As a measure of the health of the blood-brain barrier system, the ratios of the number of BBB cells at the current moment to the number of cells at rest, that is, on average healthy state, are chosen.

The continuous part of the model includes a description of the division of both types of glioma cells, the recovery of BBB cells, and the dynamics of the drug. Reducing the number of well-functioning BBB cells facilitates the penetration of the drug to brain cells, that is, enhances the action of the drug. At the same time, the rate of division of glioma cells does not increase, since it is limited not by the deficiency of nutrients available to cells, but by the internal mechanisms of the cell. The discrete part of the mathematical model includes the operator of radio interaction, which is applied to the indicator of BBB and to glial cells.

Within the framework of the mathematical model of treatment of a cancer tumor (glioma), the problem of optimal control with phase constraints is solved. The patient’s condition is described by two variables: the volume of the tumor and the condition of the BBB. The phase constraints delineate a certain area in the space of these indicators, which we call the survival area. Our task is to find such treatment strategies that minimize the time of treatment, maximize the patient’s rest time, and at the same time allow state indicators not to exceed the permitted limits. Since the task of survival is to maximize the patient’s lifespan, it is precisely such treatment strategies that return the indicators to their original position (and we see periodic trajectories on the graphs). Periodic trajectories indicate that the deadly disease is translated into a chronic one.

The short-term prediction of road traffic condition is one of the main tasks of transportation modelling. The main purpose of which are traffic control, reporting of accidents, avoiding traffic jams due to knowledge of traffic flow and subsequent transportation planning. A number of solutions exist — both model-driven and data driven had proven to be successful in capturing the dynamics of traffic flow. Nevertheless, most space-time models suffer from high mathematical complexity and low efficiency. Artificial Neural Networks, one of the prominent datadriven approaches, show promising performance in modelling the complexity of traffic flow. We present a neural network architecture for traffic flow prediction on a real-world road network graph. The model is based on the combination of a recurrent neural network and graph convolutional neural network. Where a recurrent neural network is used to model temporal dependencies, and a convolutional neural network is responsible for extracting spatial features from traffic. To make multiple few steps ahead predictions, the encoder-decoder architecture is used, which allows to reduce noise propagation due to inexact predictions. To model the complexity of traffic flow, we employ multilayered architecture. Deeper neural networks are more difficult to train. To speed up the training process, we use skip-connections between each layer, so that each layer teaches only the residual function with respect to the previous layer outputs. The resulting neural network was trained on raw data from traffic flow detectors from the US highway system with a resolution of 5 minutes. 3 metrics: mean absolute error, mean relative error, mean-square error were used to estimate the quality of the prediction. It was found that for all metrics the proposed model achieved lower prediction error than previously published models, such as Vector Auto Regression, LSTM and Graph Convolution GRU.

The method of balanced identification was used to describe the response of Net Ecosystem Exchange of CO₂ (NEE) to change of environmental factors, and to fill the gaps in continuous CO₂ flux measurements in a sphagnum peat bog in the Tver region. The measurements were provided in the peat bog by the eddy covariance method from August to November of 2017. Due to rainy weather conditions and recurrent periods with low atmospheric turbulence the gap proportion in measured CO₂ fluxes at our experimental site during the entire period of measurements exceeded 40%. The model developed for the gap filling in long-term experimental data considers the NEE as a difference between Ecosystem Respiration (RE) and Gross Primary Production (GPP), i.e. key processes of ecosystem functioning, and their dependence on incoming solar radiation (Q), soil temperature (T), water vapor pressure deficit (VPD) and ground water level (WL). Applied for this purpose the balanced identification method is based on the search for the optimal ratio between the model simplicity and the data fitting accuracy — the ratio providing the minimum of the modeling error estimated by the cross validation method. The obtained numerical solutions are characterized by minimum necessary nonlinearity (curvature) that provides sufficient interpolation and extrapolation characteristics of the developed models. It is particularly important to fill the missing values in NEE measurements. Reviewing the temporary variability of NEE and key environmental factors allowed to reveal a statistically significant dependence of GPP on Q, T, and VPD, and RE — on T and WL, respectively. At the same time, the inaccuracy of applied method for simulation of the mean daily NEE, was less than 10%, and the error in NEE estimates by the method was higher than by the REddyProc model considering the influence on NEE of fewer number of environmental parameters. Analyzing the gap-filled time series of NEE allowed to derive the diurnal and inter-daily variability of NEE and to obtain cumulative CO₂ fluxs in the peat bog for selected summer-autumn period. It was shown, that the rate of CO₂ fixation by peat bog vegetation in August was significantly higher than the rate of ecosystem respiration, while since September due to strong decrease of GPP the peat bog was turned into a consistent source of CO₂ for the atmosphere.

Inhibitors of histone deacetylases (HDACi) have considered as a promising class of drugs for the treatment of cancers because of their effects on cell growth, differentiation, and apoptosis. Angiogenesis play an important role in the growth of most solid tumors and the progression of metastasis. The vascular endothelial growth factor (VEGF) is a key angiogenic agent, which is secreted by malignant tumors, which induces the proliferation and the migration of vascular endothelial cells. Currently, the most promising strategy in the fight against cancer is the creation of hybrid drugs that simultaneously act on several physiological targets. In this work, a series of hybrids bearing N-phenylquinazolin-4-amine and hydroxamic acid moieties were studied as dual VEGFR-2/HDAC inhibitors using simplex representation of the molecular structure and Support Vector Machine (SVM). The total sample of 42 compounds was divided into training and test sets. Five-fold cross-validation (5-fold) was used for internal validation. Satisfactory quantitative structure—activity relationship (QSAR) models were constructed (R²_test = 0.64–0.87) for inhibitors of HDAC, VEGFR-2 and human breast cancer cell line MCF-7. The interpretation of the obtained QSAR models was carried out. The coordinated effect of different molecular fragments on the increase of antitumor activity of the studied compounds was estimated. Among the substituents of the N-phenyl fragment, the positive contribution of para bromine for all three types of activity can be distinguished. The results of the interpretation were used for molecular design of potential dual VEGFR-2/HDAC inhibitors. For comparative QSAR research we used physicochemical descriptors calculated by the program HYBOT, the method of Random Forest (RF), and on-line version of the expert system OCHEM (https://ochem.eu). In the modeling of OCHEM PyDescriptor descriptors and extreme gradient boosting was chosen. In addition, the models obtained with the help of the expert system OCHEM were used for virtual screening of 300 compounds to select promising VEGFR-2/HDAC inhibitors for further synthesis and testing.

In this paper, we consider two variants of the concept of sharp minimum for mathematical programming problems with quasiconvex objective function and inequality constraints. It investigated the problem of describing a variant of a simple subgradient method with switching along productive and non-productive steps, for which, on a class of problems with Lipschitz functions, it would be possible to guarantee convergence with the rate of geometric progression to the set of exact solutions or its vicinity. It is important that to implement the proposed method there is no need to know the sharp minimum parameter, which is usually difficult to estimate in practice. To overcome this problem, the authors propose to use a step adjustment procedure similar to that previously proposed by B. T. Polyak. However, in this case, in comparison with the class of problems without constraints, it arises the problem of knowing the exact minimal value of the objective function. The paper describes the conditions for the inexactness of this information, which make it possible to preserve convergence with the rate of geometric progression in the vicinity of the set of minimum points of the problem. Two analogs of the concept of a sharp minimum for problems with inequality constraints are considered. In the first one, the problem of approximation to the exact solution arises only to a pre-selected level of accuracy, for this, it is considered the case when the minimal value of the objective function is unknown; instead, it is given some approximation of this value. We describe conditions on the inexact minimal value of the objective function, under which convergence to the vicinity of the desired set of points with a rate of geometric progression is still preserved. The second considered variant of the sharp minimum does not depend on the desired accuracy of the problem. For this, we propose a slightly different way of checking whether the step is productive, which allows us to guarantee the convergence of the method to the exact solution with the rate of geometric progression in the case of exact information. Convergence estimates are proved under conditions of weak convexity of the constraints and some restrictions on the choice of the initial point, and a corollary is formulated for the convex case when the need for an additional assumption on the choice of the initial point disappears. For both approaches, it has been proven that the distance from the current point to the set of solutions decreases with increasing number of iterations. This, in particular, makes it possible to limit the requirements for the properties of the used functions (Lipschitz-continuous, sharp minimum) only for a bounded set. Some computational experiments are performed, including for the truss topology design problem.