Eastern-European Journal of Enterprise Technologies

Development of a method for evaluating complex organizational and technical systems using neuro-fuzzy expert systems

Andrii Shyshatskyi — 2025-12-17

Complex organizational and technical systems are the object of research. The problem that is solved in the study is an increase in the efficiency of the assessment of the process of operation of complex organizational and technical systems (OTS) while maintaining a given level of reliability. A method of evaluating complex organizational and technical systems using neuro-fuzzy expert systems was developed. The originality of the research is:

– in full coverage of critical events occurring during the OTS operation. This is achieved due to the use of the Dempster-Schafer theory, which achieves the completeness of the assessment of the entire spectrum of critical events in the OTS;

– in a comprehensive description of the process of OTS operation. This makes it possible to increase the accuracy of OTS modeling for subsequent management decisions;

– in the ability to carry out initial adjustment of OTS knowledge bases using an improved genetic algorithm. This allows to reduce the computational complexity during the further formation of the OTS knowledge base by reducing the metric of rule formation in the OTS knowledge base;

– in the ability to model the nature of the development of atypical events in the OTS due to the use of time series, which achieves the possibility of developing preventive measures to minimize the impact of the specified events on the process of OTS operation;

– in the gradual reduction of the metric of the formation of the knowledge base about the states of OTS, due to the training of agents of the improved genetic algorithm. This allows to reduce the number of computing resources of the subsystem for assessing the state of OTS operation;

The proposed method provides an increase in efficiency by an average of 23%, while ensuring high convergence of the obtained results at the level of 93.17%, which is confirmed by the results of a numerical experiment

Devising a method for managing computing resources in a fog layer of the mobile high-density internet of things

Heorhii Kuchuk — 2025-12-17

This study considers a process that manages the distribution of computing resources in the fog layer of the mobile high-density Internet of Things. The task addressed is to reduce the load imbalance of fog servers by devising a method for controlling computing resources in the fog layer when processing information flows.

Information flows are formed by intelligent gateways of the mobile high-density Internet of Things, which receive data from the boundary layer. In the process of research, a mathematical model for the process of controlling computing resources in the fog layer was built. Its main difference from existing ones is a module hierarchical structure according to the basic levels of decision-making when managing computing resources.

When constructing the model, the principle of process decomposition into adjacent time intervals was used. Its application made it possible to carry out local optimization of the process of managing computing resources in short time intervals. The mathematical model has made it possible to devise a method for controlling computing resources in the fog layer.

The main difference of this method from existing ones is that the process optimization is carried out according to the area of the relative deviation from the balanced load in the time interval under study. In addition, a two-stage algorithm for distributing tasks of free fog devices across fog layer servers is also used. That made it possible to reduce the time for finding an approximate solution for distributing computing resources of fog servers by up to 50%.

The research results can be attributed to the combined use of the simulated annealing algorithm and the genetic algorithm. The method is effective when the load on the fog layer is from 20% to 70% of the maximum possible load

Development of a forecasting model for optimizing energy consumption at coal enterprises

Shynar Telbayeva — 2025-12-17

The study object is daily data on electricity consumption of one of the coal mines in the Karaganda basin for 2024. This article solves the problem of the lack of accurate tools that can predict complex and variable modes of energy consumption in a coal mine and thereby ensure more efficient management of energy-intensive installations.

This article presents a comparative analysis of three electricity demand forecasting models using data from a coal mine in the Karaganda basin for 2024. The study explores the effectiveness of both classical approaches (seasonal ARIMA model and simple exponential smoothing) and an LSTM neural network model. To handle non-stationary data, the first difference method was applied, allowing the time series to be stationary. The forecast was generated for 7 days in advance. A comparative analysis of the models’ accuracy was conducted using the MAPE metric on both the training and test sets. The study found that the LSTM model demonstrated the best results with a MAPE of 5.37% on the test set demonstrating its superior ability to capture complex data dynamics compared to ARIMA and simple exponential smoothing.

The developed predictive LSTM model can be effectively used in automated energy monitoring and management systems, providing accurate short-term load forecasts for coal mines and other mining and metallurgical enterprises with complex and volatile energy structures, provided the initial data is highly reliable and complete

Development hybrid OA-RG with multi-row time-aggregated cover cuts for solving MINLP in coffee plantation maintenance

Eko Hariyanto — 2025-12-17

The object of this research is the NP-hard combinatorial optimization problem in the allocation of limited resources for the maintenance of smallholder coffee plantations. In this study, a hybrid method of outer Approximation (OA) and reduced gradient (RG), enhanced by multi-row time-aggregated cover cuts (MTACC) is proposed to address the computational time efficiency problem in mixed-integer nonlinear programming (MINLP)-based combinatorial optimization problems. The testing was conducted using plantation land data from the Rahmat Kinara Coffee Farmers Association, which includes 538 land blocks with a total area of 825.5 hectares. Based on the numerical results obtained, it shows a reduction in the number of iterations by up to 38.83% and an increase in the speed of convergence time by up to 12.84%. The n_w feature in MTACC specifically controls the length of the time window to form multi-row covering slices that are suitable for the characteristics of the constraints, which affects the master and RG subproblems in overcoming the computational load. The evaluation results for testing parameters n_w = 7 and n_w = 14 show an increased contribution to convergence time of up to 10.1% by reducing the average master MILP time by 6.16%. Evaluation of the area under curve (AUC) metric confirms that MTACC is more stable in controlling optimality gaps across global iterations based on AUC (abs) assessment, which decreased by 21.6%; AUC per iteration decreased by 19.9%, and normalized AUC also decreased by 18.6%.

The results obtained can be effectively applied in small to large-scale coffee plantations, especially in decision support systems on low-power computing devices for production sustainability