Перегляд за автором "Korablyov, M."
Зараз показано 1 - 3 з 3
Результатів на сторінку
Варіанти сортування
Публікація Comparative analysis of models for short-term forecasting of electricity consumption(2024) Korablyov, M.; Kobzev, I.; Chubukin, O.; Antonov, D.; Polous, V.; Tkachuk, O.Forecasting electricity consumption is an urgent task, and the solution significantly affects the efficiency of the use of energy resources. The paper considers short-term forecasting of electricity consumption, which predicts the amount of energy that will be used in a short period, from several hours to several days in advance. There are various short-term forecasting models, so it is important to reasonably choose a model that provides analysis and effective forecasting of electricity consumption to optimize the use of energy resources. The purpose of the work is to analyze the main forecasting models, such as statistical models (autoregressive model, moving average, exponential smoothing, moving average with autoregression and integration) and deep learning models (artificial neural network, recurrent neural network, long short-term memory, transformer), indicating their advantages and disadvantages, and choosing the best of them. The experimental results of a comparative analysis of power consumption forecasting models are presented, which showed that the transformer model was 1.5% - 2% more effective in power consumption forecasting according to various metrics. Its higher level of accuracy, reflected in low error values and high coefficient of determination, indicates its high adaptability to the dynamics of electricity consumption.Публікація Immune Model for Controlling Characters in Computer Games(CEUR Workshop Proceedings (CEUR-WS.org), 2023) Korablyov, M.; Fomichov, O.; Chubukin, O.; Antonov, D.; Dykyi, S.The rapid development of information technologies led to the emergence of new opportunities for game software developers. In the field of game application development, a large number of platforms and patterns of architecture development, as well as game environments, have appeared, which allow simplifying and automating the process of development and deployment of the game software. The game application used in the work simulates a futuristic space world where the player interacts with other characters in a free game space. An analysis of game resources, which can be controlled by the player and other game characters, has been carried out. The main features of the behavior of game characters controlling spaceships on the map of the game world are defined. The task of controlling the behavior of characters in game software can be considered as a classification problem, for which it is proposed to use artificial immune systems. Among the existing immune models, the most promising for practical application is the artificial immune network model, which was chosen as the basis for creating a model for controlling the behavior of characters in computer games. But it cannot be used to solve the problem of managing game characters without additional modifications. A modified model of the immune network – behavioral aiNET (baiNET) was proposed, which can be used to solve the problem under consideration. The software implementation of the game software tool, in which the control of the game characters is carried out using the baiNET model, has been completed. Experimental studies were carried out with different numbers of game characters on different-sized maps of the game world, which showed that the proposed baiNet immune model is effective and simple to implement and modify. This makes it possible to use it to control characters in games of other genres.Публікація System-information models for intelligent information processing(ХНУРЕ, 2022) Korablyov, M.; Lutskyy, S.The subject of the study is system-information models of processes and systems and their use for intelligent processing of information in production tasks. The use of intelligent information processing in production management systems is currently one of the key areas of development of informatics. The aim of the work is to develop system-information models of processes and systems for intelligent information processing allowing to analyze and solve production problems, in conditions of uncertainty. In the article the following tasks are solved: to analyze approaches to the definition of information characteristics of processes and systems; to develop the basis for modeling of system-information processes and systems for intelligent information processing; to develop system-information models and ways of their application for intelligent information processing in the tasks of production. The following methods are used: system-information approach to processes and systems; system-information modeling of processes and systems. The following results were obtained: the analysis of approaches to the definition of information characteristics of processes and systems; developed principles of modeling system-information processes and systems for intelligent processing of information; introduced the concepts of system information and information measure; developed system-information models and methods of their application for the intelligent processing of information in the tasks of production. Conclusions. The development of methods for solving various classes of practical problems using intelligent information processing is one of the key areas of research in computer science. The developed system-information models of processes and systems for intelligent information processing allow analyzing and solving problems. Thereby increase the efficiency of solving problems of analysis, synthesis and forecasting of production systems and technologies, as well as problems of production management. The system-information approach to processes and systems operates with new concepts – system information and information measure, it allowed developing system-information models for intelligent processing of information, as well as ways of their application at stages of product life cycle, which allowed solving problems of production. System-information models of processes and systems describe interaction between source and receiver on information level on the basis of sensitivity threshold. The communication channel between the source and the receiver of information operates, as a rule, under conditions of uncertainty, which can lead to the loss of information during transmission due to possible changes in the characteristics of the system. To describe their interaction, some models of intelligent information processing can be used, in particular, neural network models or fuzzy inference models. Their use will improve the efficiency of receiver state prediction, taking into account the state of the transmitter and the conditions of communication channel operation. The presented article has shown the relevance of developing system-information models for intelligent information processing at the levels of data reception, interpretation and ommunication, which allows expanding the class of solved production tasks.