In this paper we prove criteria for a nonnormal toric variety to be flexible, to be rigid and to be almost rigid. For rigid and almost rigid toric varieties we describe the automorphism group explicitly.

The paper describes a control system for renewable energy complexes with optimization of operating modes based on digital twins of equipment. The application of digital twins allowed us to develop a simulator that simulates the main processes occurring in the ground heat pump system. The simulator allows: to perform computer experiments to study different modes of Polygon operation; to demonstrate the physical essence of the ongoing processes to form the qualifications and skills of students in the field of non-traditional and renewable sources of electric and thermal energy. The use of digital twins also allows the implementation of a renewable energy combination management system to improve the energy efficiency of hybrid power complexes. The algorithm developed by the authors for selecting combinations of renewable energy sources to increase the energy efficiency of the complexes takes into account the current values of the operating parameters of the equipment, the forecast of energy consumption, as well as the forecast of power generation by each of the components of the complex.

This paper addresses the problem of thermal power plant generating unit efficiency evaluation accuracy increase. The comparison of classic regression analysis and artificial neural network regression approaches is described. The feasibility and reasonability of application of the machine learning techniques for generating unit performance prediction and selecting most influential parameters on its efficiency evaluation accuracy are considered.

This paper deals with the development of an algorithm for predicting thermal power plant process variables. The input data are described, and the data cleaning algorithm is presented along with the Python frameworks used. The employed machine learning model is discussed, and the results are presented.

The paper is on the technical and economic performance optimization technique for thermal and power generating system using machine learning methods. The possibility of using regression analysis for parameter influence evaluation when calculating technical and economic performance in order to reach better generating unit efficiency is described. The approach to evaluate the parameter influence of a large distributed control system is presented.