BUILDING AN ADAPTIVE HYBRID MODEL FOR SHORT-TERM PREDICTION OF POWER CONSUMPTION USING A NEURAL NETWORK

This paper proposes a step-by-step technique for combining basic models that forecast electricity consumption in an artificial neural network by the method of preliminary selection and further hybridization. The reported experiments were conducted using data on hourly electricity consumption at the metallurgical plant AO ArcelorMittal Temirtau in the period from January 1, 2019, to November 30, 2021. The current research is related to the planned introduction of a balancing electricity market. 96 combinations of basic models were compiled, differing in the type of neural network, the set of initial data, the order of lag, the learning algorithm, and the number of neurons in the hidden layer. It has been determined that the NARX-type network is the most optimal architecture to forecast electricity consumption. Based on experimental studies, the number of hidden neurons needed to form a planned daily profile should equal 3 or 4; it is recommended to use the conjugate gradient method as a learning algorithm. When selecting models from three groups, it was revealed that the conjugate gradient method produces better results compared to the Levenberg-Marquardt algorithm. It is determined that the values of the selected RMSE error indicator take values of 23.17, 22.54, and 22.56, respectively, for the first, second, and third data groups. The adaptive hybridization method has been shown to reduce the RMSE error rate to 21.73. However, the weights of the best models with values of 0.327 for the first group of data, and 0.336 for the second and third ones, show that the indi-vidual use of a separate combination of models is also applicable. The devised forecasting electricity consumption model can be integrated into an automated electricity metering system. A quantitative comparative analysis of available energy resources and technologies based on them was carried out. It is proposed to use the acceptability index and the environmental conservation index as a criterion for the preference of a resource. Index values equal to or greater than 1 indicate resource preference. It is shown that for the base region under consideration, such resources are nuclear, solar, wind, and hydropower. The method of expert assessments makes it possible to get an ob-jective idea of the acceptability of using a certain energy resource to ensure energy security, taking into consideration its environmental impact in a particular region of the country. A quantitative comparative analysis of the state of the existing structure of energy resources in the region and their availability has been carried out. To conduct a comparative analysis of acceptability by indicators and types of resources, a graphical and analytical methodology was used. The reliability of the results obtained was assessed using a concordance coefficient. The results could be useful for devising projects for the development and ensuring the energy security of the regions in the context of reforms. reached when used heterogeneous core configuration case three with percentage of U-233 in F1=2 %, F2=4 % and F3=6 % with the addition of Pa-231 0.5 % and fuel fraction 53 %. It has a maximum excess reactivity value 7.67 % % ∆ k / k . The comparison of optimum design of UN and ThN fuel shows that the ThN fuel has the k - eff value closer to critical than UN fuel. Therefore, in this study, ThN fuel is more suitable for use in PWR reactors because it has a small excess value and can operate for 10 years without refueling. the first design with gas turbine engines. A schematic diagram of the general design of the proposed hybrid power system and the principle of its operation is proposed. The difficulties encountered in the design and operation of such hybrid power systems are noted. This paper considers partitioning parameters and the mutual arrangement of magnets in the rotor of the traction synchronous-jet engine with permanent partitioned magnets. The synthesis of geo-metrical parameters for the rotor of a synchronous reluctance motor with partitioned permanent magnets was proposed on the basis of solving the problem of conditional optimization. To solve the synthesis problem, a mathematical model has been built to determine the electromagnetic momentum of a synchronous reluctance motor with partitioned permanent magnets. It is based on the calculation of the electromagnetic momentum of the engine employing the results of a finite-element analysis of the magnetic field in the flat-parallel state-ment of the problem. The model is implemented in the finite-element analysis FEMM environment and makes it possible to determine the electromagnetic momentum of the engine with a variety of partitioning of permanent magnets. As an analysis problem, it is proposed to use a mathematical model of the magnetic field of the engine. The problem of conditional optimization of the rotor of a synchronous reluctance motor was stated according to the geometric criteria of the rotor. Restrictions are set on geometric, strength indicators, as well as on the level of electromagnetic momentum. The chosen optimization method is the Nelder-Mead method. Based on the results of solving the problem of synthesizing parameters for the partitioned rotor of the traction motor of trolleybus wheels, it was established that the volume of permanent magnets was reduced by 2.27 times compared to the base structure; their optimal geometric dimensions were determined (5 mm, 5.2 mm, and 5 mm), as well as the distance between them, 17.8 mm and 15.3 mm, and the engine load angle, which is 121.12 electrical degrees. Based on the results of solving the problem of synthesizing parameters for the partitioned rotor of a trolleybus traction synchronous reluctance motor, its optimal geometric parameters have been determined. The surface of the Earth is a source of radiation of thermal energy, which, passing through the atmosphere, is partially absorbed while the bulk of the energy is released into the surrounding outer space. A cooling technique based on this physical phenomenon is known as radiative cooling (RC). It is possible to reduce the consumption of electricity for cooling, as well as to reduce capital costs, by integrating the unit with radiative cooling directly into the circulation circuit of the refrigerant of the refrigeration machine. An experimental refrigeration system has been designed, in which in the cold periods of the year the removal of heat from the cooled object is carried out due to the mode of natural circulation of the refrigerant from the evaporator to the heat exchanger, cooled by radiative cooling. A refrigeration system with natural circulation and radiative cooling of the refrigerant R134a was experimentally studied during the autumn period in Almaty. The experimental study established that the chamber is cooled with the help of the examined system while the temperature in the cooled volume is maintained by 5...7 K above ambient air temperature at night. The dependence of the air temperature in the refrigerating chamber on the temperature of the atmospheric air has been determined. A procedure for assessing the cooling capacity of the system has been devised. The study reported here demonstrated the possibility of using radiative cooling to remove heat under the mode of natural circulation of the refrigerant. The refrigeration system reduces energy consumption in the cold seasons by diverting heat to the environment without the compres-sor operating. %. It is expected that the designed structure could be a solution for small farmers in the post-harvest drying process.

A quantitative comparative analysis of available energy resources and technologies based on them was carried out. It is proposed to use the acceptability index and the environmental conservation index as a criterion for the preference of a resource. Index values equal to or greater than 1 indicate resource preference. It is shown that for the base region under consideration, such resources are nuclear, solar, wind, and hydropower.
The method of expert assessments makes it possible to get an objective idea of the acceptability of using a certain energy resource to ensure energy security, taking into consideration its environmental impact in a particular region of the country.
A quantitative comparative analysis of the state of the existing structure of energy resources in the region and their availability has been carried out.
To conduct a comparative analysis of acceptability by indicators and types of resources, a graphical and analytical methodology was used. The reliability of the results obtained was assessed using a concordance coefficient.
The results could be useful for devising projects for the development and ensuring the energy security of the regions in the context of reforms.
Keywords: expert assessments, applicability, energy resources, energy security, environmental friendliness, acceptability, environmental conservation index.

Yuriy Elkin
Odessa State Academy of Civil Engineering and Architecture, Odessa, Ukraine ORCID: https://orcid.org/0000-0001-7677-377X This paper considers the task of ensuring the energy and environmental security of regions under the conditions of shortage of traditional energy resources. The method of expert assessments has been applied to justify the choice of types of acceptable energy resources that provide an increase in the relative energy supply of the territories of the regions.
A list of factors from 6 groups has been devised and compiled that includes 27 indicators characterizing the technological, environmental, and other consumer characteristics of energy resources available for use.
The maximum and minimum values of the indicator scores, the permissible intervals for their change, and the weighting coefficients that assess the importance of the indicator in the list have been determined.
The method of expert assessments is supplemented by a random number generator for the formation of an information field on the values of the characteristics of energy resources and statistical processing of data on acceptable energy resources under the conditions of the considered regions.
Comparison of thorium nitride (ThN) and uranium nitride (UN) fuel on small modular PWR in neutronic analysis has been carried out. PWR in module is one type of reactor that can be utilized because of its small size so that it can be placed on demand. Neutronic calculations were performed using SRAC version 2006, the data library using JENDL 4.0. The first calculation was fuel pin (PIJ) calculation with hexagonal fuel pin cell type. And the second calculation was reactor core (CITATION) calculation using homogeneous and heterogeneous core configurations. ThN and UN fuels use heterogeneous configurations with 3 fuel variations. The reactor geometry was used in two fuels are the same, with diameter and height active core was 300 cm and 100 cm. In this research, Np-237 was added as a minor actinide in the UN fuel to reduce the amount of Np-237 in the world and also reduce the k-eff value. For ThN fuel, Pa-231 also added in the fuel to reduce the k-eff value. The optimum configuration of UN fuel reached when used heterogeneous core configuration case four with percentage of U-235 in F1=5.5 %, F2=7 % and F3=8.5 % also with the addi5tion of Np-237 0.2 % and fuel fraction 56 %. It has a maximum excess reactivity value 12.56 % %∆k/k. And then, the optimum configuration of ThN fuel reached when used heterogeneous core configuration case three with percentage of U-233 in F1=2 %, F2=4 % and F3=6 % with the addition of Pa-231 0.5 % and fuel fraction 53 %. It has a maximum excess reactivity value 7.67 % %∆k/k. The comparison of optimum design of UN and ThN fuel shows that the ThN fuel has the k-eff value closer to critical than UN fuel. Therefore, in this study, ThN fuel is more suitable for use in PWR reactors because it has a small excess value and can operate for 10 years without refueling.
Keywords: PWR, SRAC, thorium nitride, uranium nitride, modular reactor, excess reactivity. This paper considers the issue related to the use of jet gas turbine engines for the generation of thermal and electrical energy, defined as a hybrid energy system powered by biogas. Revealing the main vulnerable points of the use and operation of these systems, it is proposed to use biogas obtained from agricultural, crop and livestock waste as fuel for gas turbine engines.

Аdylkhan Kibishov
Analyzing the work of gas turbine engines, it reveals not only the technological advantages of using biogas instead of fuel, but also reducing the cost of heat and electric energy obtained by obtaining a productive land biohumus. This will result, firstly, it is especially emphasized, the usefulness of the resulting ground humus as a waste material, when producing biogas as fuel, for the operation of a hybrid energy system operating on the basis of gas turbine engines. Secondly, during the operation of a hybrid power system, it is possible to simultaneously obtain thermal and electrical energy. Thirdly, the low cost of the heat and electric energy received.
The following are other useful applications of such a power system. The resulting thermal energy is used for heating the greenhouse, and the electrical energy obtained from the operation of the hybrid power system can be used not only for lighting the premises, but can be used for the needs of the greenhouse. It is shown that the proposed hybrid power system consists of two technological structures. The first design is to obtain fuel in the form of biogas for the operation of gas turbine engines, the second design is the connection of the first design with gas turbine engines. A schematic diagram of the general design of the proposed hybrid power system and the principle of its operation is proposed. The difficulties encountered in the design and operation of such hybrid power systems are noted.
Keywords: hybrid power system, gas turbine engine, greenhouse, thermal energy, electric energy, humus soil. This paper considers partitioning parameters and the mutual arrangement of magnets in the rotor of the traction synchronous-jet engine with permanent partitioned magnets. The synthesis of geometrical parameters for the rotor of a synchronous reluctance motor with partitioned permanent magnets was proposed on the basis of solving the problem of conditional optimization. To solve the synthesis problem, a mathematical model has been built to determine the electromagnetic momentum of a synchronous reluctance motor with partitioned permanent magnets. It is based on the calculation of the electromagnetic momentum of the engine employing the results of a finite-element analysis of the magnetic field in the flat-parallel statement of the problem. The model is implemented in the finite-element analysis FEMM environment and makes it possible to determine the electromagnetic momentum of the engine with a variety of partitioning of permanent magnets. As an analysis problem, it is proposed to use a mathematical model of the magnetic field of the engine. The problem of conditional optimization of the rotor of a synchronous reluctance motor was stated according to the geometric criteria of the rotor. Restrictions are set on geometric, strength indicators, as well as on the level of electromagnetic momentum. The chosen optimization method is the Nelder-Mead method.
Based on the results of solving the problem of synthesizing parameters for the partitioned rotor of the traction motor of trolleybus wheels, it was established that the volume of permanent magnets was reduced by 2.27 times compared to the base structure; their optimal geometric dimensions were determined (5 mm, 5.2 mm, and 5 mm), as well as the distance between them, 17.8 mm and 15.3 mm, and the engine load angle, which is 121.12 electrical degrees.
Based on the results of solving the problem of synthesizing parameters for the partitioned rotor of a trolleybus traction synchronous reluctance motor, its optimal geometric parameters have been determined.
Keywords: synchronous reluctance motor, Nelder-Mead method, finite-element method, partitioned permanent magnets. The surface of the Earth is a source of radiation of thermal energy, which, passing through the atmosphere, is partially absorbed while the bulk of the energy is released into the surrounding outer space. A cooling technique based on this physical phenomenon is known as radiative cooling (RC). It is possible to reduce the consumption of electricity for cooling, as well as to reduce capital costs, by integrating the unit with radiative cooling directly into the circulation circuit of the refrigerant of the refrigeration machine. An experimental refrigeration system has been designed, in which in the cold periods of the year the removal of heat from the cooled object is carried out due to the mode of natural circulation of the refrigerant from the evaporator to the heat exchanger, cooled by radiative cooling. A refrigeration system with natural circulation and radiative cooling of the refrigerant R134a was experimentally studied during the autumn period in Almaty. The experimental study established that the chamber is cooled with the help of the examined system while the temperature in the cooled volume is maintained by 5...7 K above ambient air temperature at night. The dependence of the air temperature in the refrigerating chamber on the temperature of the atmospheric air has been determined. A procedure for assessing the cooling capacity of the system has been devised.
The study reported here demonstrated the possibility of using radiative cooling to remove heat under the mode of natural circulation of the refrigerant.
The refrigeration system reduces energy consumption in the cold seasons by diverting heat to the environment without the compressor operating.
Keywords: radiative cooling, effective radiation, natural circulation, refrigeration machine, thermosiphon system, energy saving. pay attention to designing new structures of energy-efficient grain dryers.
A structure of an energy-efficient grain dryer based on thermosiphons has been designed; its energy consumption is 3.5...6.8 MJ/kg depending on surface temperature and air flow rate. The dryer includes a layer heater, a drying chamber, a heat generator, a heater, a noria for loading the product, and fans. The structural features of the dryer allow the drying process to be carried out without direct contact between the combustion gases and the product.
The efficiency of the designed structure was evaluated for such indicators as heat transfer coefficients to the grain flow, specific energy costs, moisture content, the relative humidity of the air leaving the dryer.
The values of coefficients of the heat transfer to the grain flow vary within 36...58 W/m 2 K at speeds 2.5...8 mm/s. An increase in the flow rate by 3.2 times leads to an increase in the heat transfer coefficient by 1.6 times.
The moisture content of the air at the outlet of the dryer reaches 60 g/kg, while the relative humidity is 90 %, which is several times higher than the parameters for convective mine grain dryers.
Energy consumption for drying at the surface temperature of thermosiphons T s =142.9 °C for various grain flow rates is close to a minimum. The energy consumption is lower than in existing convective dryers.
21 % is spent on heating grain in the dryer; 54 % -on moisture evaporation; and 23.6 % are losses. If we consider the energy spent on moisture evaporation usable, the efficiency of convective dryers is only 40 % while that of dryers based on thermosiphons is 54.1 %.
It is expected that the designed structure could be a solution for small farmers in the post-harvest drying process.