MODELING OF ENERGY INDICATORS OF LIGHTING DEVICES USING ARTIFICIAL NEURAL NETWORKS Rakhmonov I.U.1, Toirov M.T.2, Umarov B.S.3
1Rakhmonov Ikromjon Usmonovich —DSc, Professor, 2Toirov Muhammadkhon Toir ugli - PhD student, TASHKENT STATE TECHNICAL UNIVERSITY, TASHKENT, REPUBLIC OF UZBEKISTAN 3Umarov Baigazi Sadvakas uli - Assistant, KARAKALPAK STATE UNIVERSITY, NUKUS, REPUBLIC OF KARAKALPAKSTAN
Abstract: this article shows what results can be achieved by modeling the energy performance of lighting devices through artificial neural networks. At the same time, basic information about energy performance of lighting devices and artificial neural networks is explained.
Keywords: electrical power, thermal power, efficiency, luminous efficasy, power factor, correlated color temperature, artificial neural networks, model, voltage.
UDC 621.311.12
We now know that the demand for lighting devices is increasing in proportion to the increase in the amount of electricity consumers. As long as this is the case, the place among electricity consumers is also considered significant. Also, now the field of programming is developing very rapidly. Examples of this include Python, Java, Mathlab Simulink and Artificial Neural Networks programming languages. Among the above, modeling processes through artificial neural networks also have their place. That is, nowadays it is quite important to perform modeling through artificial neural networks. [1, 2].
The energy indicators of lighting devices are as follows:
Electrical power represents the rate at which electrical energy is transferred in an electric circuit, indicating the amount of energy a device consumes or generates per unit of time. It is typically measured in watts (W), with one watt equaling one joule of energy per second.
Thermal power is the rate at which heat energy is generated, transferred, or utilized in a system, indicating the amount of thermal energy produced or consumed per unit time. It is typically measured in watts (W), equivalent to one joule of energy per second, though larger units such as kilowatts (kW) or megawatts (MW) are commonly used for large-scale applications.
Efficiency measures how effectively a system or device converts input energy, resources, or effort into useful output. Expressed as a percentage, it represents the ratio of useful output to total input. High efficiency indicates minimal waste and optimal performance, whereas low efficiency suggests greater waste or energy loss [3, 4, 5].
Luminous efficacy measures how efficiently a light source converts electrical power into visible light. It is defined as the amount of visible light (in lumens) produced per watt of electrical power consumed, typically expressed in lumens per watt (lm/W). A higher luminous efficacy indicates that the lighting device generates more light output for each watt of power consumed, making it more energy-efficient.
Power Factor (PF) measures how efficiently electrical power is being utilized in an alternating current (AC) system. It is the ratio of real power (active power), which performs useful work, to apparent power, the total power supplied to the circuit. The power factor reflects how much of the supplied power is being effectively converted into useful work, and how much is lost as reactive power, which doesn't contribute to useful work but is required for maintaining voltage levels in the system [4, 5, 6].
CRI (Colour Rendering Index).
Fig. 1. Colour Rendering Index.
The color rendering index (CRI) of a light source is a quantitative measure of its ability to reproduce the colors of various objects faithfully in comparison with an ideal or natural light. CCT (Correlated Color Temperature).
no 01 0 2 0.1 II4 0.3 Oft №7 OH
Fig. 2. Correlated Color Temperature.
Color temperature has been described most simply as a method of describing the color characteristics of light, usually either warm (yellowish) or cool (bluish), and measuring it in degrees of Kelvin (K) [4,5].
Before making it possible to model the energy parameters of the above-mentioned lighting devices through artificial neural networks, it is necessary to know the basic concepts of artificial neural networks. Artificial neural networks are one of the main tools used in machine learning. They are designed to replicate what people need and do to learn. SNT consists of input, hidden and output layers. It helps to solve problems that are very difficult for programmers. Another name for neural networks is Perceptron, which has been around since 1940. In the last few decades, they have been considered the main part of artificial intelligence.
input layer
hidden layer 1 hidden layer 2
Fig. 3. Basic structure of Artificial Neural Network.
Above is a diagram explaining the basis of artificial neural networks in Figure 3. In this case, the image consists of 4 parts: input, 2 hidden and output layers. In this case, the hidden layer performs a large amount of work [7, 8].
Using artificial neural networks (ANNs) to model energy indicators of lighting devices can enhance energy efficiency optimization and predict key performance metrics, including energy consumption, luminous efficacy, and lifespan. ANNs can evaluate complex relationships between multiple variables (like power input, temperature, and light output), enabling the modeling or prediction of lighting device performance under various conditions.
References
1. A.I. Zhmakin Enhancement of light extraction from light emitting diodes, Phys. Rep. 498 (4-5) (2011) 189241.
2. I.U. Rakhmonov, M.T. Toirov. Analysis of factors affecting the life of lighting devices. Republican scientific and technical conference 2024 on the topic "Prospects of mining and processing of mineral raw materials in the eyes of young people" (dedicated to the 75th anniversary of JSC "Almaliq kmk"). page: 236-237
3. S. Takamatsu, T. Yamashita, and T. Itoh Meter-scale large area LED-embedded Light Fabric for the Application of Fabric Ceilings in Rooms, Microsyst. Technol., 2014.
4. Sermin Onaygil, Onder Guler, andM. Berker Yurtseven Evaluation of led luminaire utilization in road lighting installations in terms of electrical energy quality, Light & Engineering, Vol. 31, No. 6, pp. 13-21, 2023.
5. I.U. Rakhmonov, M.T. Toirov. Effect of voltage value change on the lifespan of lighting devices. IV international scientific and technical conference "current problems of the power supply system" 2024, pp: 98100.
6. Рахмонов И.У., Холихматов Б.Б., Гуломов Ф.Ф., Нажматдинов Р.К. Снижения расхода энергии и улучшение производственных показателей промышленных предприятий с непрерывным характером производства // «Вестник науки и образования» научно-методический журнал. 2024. № 5 (148) Часть 2. С. 13-19.
7. Рахмонов И.У., Коржобова М.Ф., Абдухалилов М.К., Отепбергенов Ш.Т. Анализ существующих подходов при выборе методов оценки эффективности управления энергопотреблением промышленных предприятий // «Проблемы современной науки и образования» научно-методический журнал. 2024. № 5 (192). С. 5-9.
8. Рахмонов И.У., Абдухалилов М.К., Курбонов Н.Н., Узаков Б.А. Исследование экономических показателей для оценки энергоэффективности промышленных предприятий с непрерывным характером производства // «Проблемы современной науки и образования» научно-методический журнал. 2024. № 5 (192). С. 10-14.
9. Рахмонов И.У., Ережепов М.Т., Курбонов Н.Н., Ниматуллаев И.А. Разработка мероприятий, напрвленных на снижение расхода электроэнергии с учетом особенностей технологичеких процессов // «Вопросы науки и образования» научно-теоретический журнал. 2024. № 4 (176). С. 12-19.