This paper is devoted to designing, modeling, and analyzing a solar-powered street lighting system using artificial intelligence technologies to predict energy consumption. The system involves the integration of solar panels, batteries, and sensors to efficiently control the brightness of LED lamps depending on the illumination level and the presence of motion in the lighting area. The use of artificial neural networks (LSTM, GRU, Random Forest) provided accurate prediction of solar energy generation and the need to connect to the city power grid during periods of low solar activity. The developed model was implemented in MATLAB Simulink, considering actual weather data. The results showed that the system can operate autonomously for up to three days under unfavorable weather conditions, reducing power by 30%. The need for connection to the external network is no more than 10% in summer and up to 30% in winter. The prototype will be implemented in Kazakhstan to validate the model and further optimize its operation.

This paper presents a digital model of an intelligent solar-powered street lighting system with integrated energy consumption forecasting, developed in MATLAB/Simulink. The simulation uses real hourly weather data from the Almaty region, where solar irradiance ranged from 0 to 980 W/m² and temperatures varied from –25°C to +35°C. The modeled system includes a 200 W photovoltaic panel, a 120 Ah battery, and LED luminaires up to 60 W. Predictive analysis of the battery’s state of charge (SOC) and need for external power was conducted using AI algorithms ANN, LSTM, GRU, and Random Forest trained on synthetic data from the simulation. Results show the system can operate autonomously for up to 72 hours under adverse weather. The probability of switching to backup power is 27–32% in winter and under 8% in summer. The LSTM and GRU models achieved a mean SOC prediction error of less than 5% versus actual values. The proposed architecture offers a practical and adaptable approach for designing, testing, and optimizing solar-powered lighting in both urban and rural settings across Kazakhstan and similar regions. It demonstrates the potential of combining simulation with AI to support sustainable and resilient outdoor lighting infrastructure.

Бұл мақалада электр энергиясы нарығындағы Виртуалды электр станциясы (ВЭС) үшін операциялық стратегияның түрлі нұсқаларын үйлестіру мүмкіндігі сипатталған. ВЭС моделі - электр энергиясы нарығында электр энергиясын сатудан түсетін жалпы пайданы барынша көбейту мақсатында, жел және күн электр станциясынан алынатын энергияны сақтау жүйесімен қамтылған энергетикалық жүйе болып табылады. Бұл модель ВЭС иелеріне баға төмен болған кезде энергияны нарықтан сатып алуға және оны нарықтық баға жоғары деп саналатын кезеңдерде қайта сатуға мүмкіндік береді. Сонымен қатар, энергияны сақтау жүйесінің көмегімен желідегі ауытқуыды азайтуға болады.

This paper introduces the design and implementation of an intelligent, modular Light Emitting Diode (LED) lighting system for industrial and municipal applications, leveraging modern computer science methods and the Internet of Things (IoT). The system features power redundancy, decentralized control, and native support for Power Line Communication (PLC) and the Digital Addressable Lighting Interface (DALI) to ensure high reliability, low latency, and energy efficiency. We detail a robust communication and data transmission architecture together with sensor-driven control algorithms that enable context-aware dimming, occupancy-based scheduling, and continuous self-tuning to reduce consumption while maintaining lighting quality. Simulation studies and laboratory prototypes demonstrate marked performance gains: Mean Time Between Failures (MTBF) increases by more than 60%, reaching up to 65,000 hours, and energy savings reach approximately 30% relative to conventional deployments. The modular design facilitates phased rollouts and retrofits, while built-in monitoring, diagnostics, and predictive maintenance analytics improve lifecycle management and reduce downtime. The proposed approach aligns with smart-city initiatives and Industry 4.0 automation, providing interoperable management, centralized orchestration, and fine-grained control across heterogeneous facilities.

В статьи рассматриваются ключевые факторы, влияющие на эффективность солнечных панелей, включая ветер, влажность, температуру и освещенность. Анализируется, как эти климатические условия и окружающая среда воздействуют на производительность солнечных установок. Исследования показывают, что ветер может как способствовать снижению температуры панелей, улучшая их работу, так и вызывать загрязнение, негативно сказываясь на выходной мощности. Температура является критическим фактором, так как высокие температуры снижают напряжение и, соответственно, производительность. Влажность также играет значительную роль: слишком высокая влажность может вызывать коррозию, в то время как оптимальные условия могут помочь в равномерном распределении тепла. Освещенность, зависящая от местоположения и погодных условий, напрямую влияет на выход энергии солнечных панелей [1]. Таким образом, для оптимизации производительности солнечных установок необходимо учитывать все перечисленные факторы и проводить регулярный мониторинг условий эксплуатации. Данное исследование подчеркивает важность комплексного подхода к проектированию и эксплуатации солнечных систем с целью повышения их эффективности и долговечности в различных климатических условиях.

The increasing penetration of variable renewable energy sources creates new challenges for regional power systems characterized by structural electricity deficits and dependence on external power transfers. This paper develops an intelligent forecasting framework for wind and solar power generation aimed at supporting power balance assessment and grid stability analysis in the Almaty region of Kazakhstan. The proposed approach combines historical meteorological data, renewable generation profiles, and machine-learning algorithms to forecast variable renewable energy output under different operating conditions. Forecasting models based on time-series analysis and machine-learning techniques are evaluated using standard accuracy indicators, including RMSE, MAE, and MAPE. The forecasted renewable generation is further integrated into a regional power balance assessment to estimate its potential contribution to reducing electricity deficit and supporting operational planning. The results demonstrate that intelligent forecasting can improve the predictability of renewable generation, reduce uncertainty in dispatch decisions, and provide a data-driven basis for renewable energy integration in deficit prone power systems. The study contributes to the development of practical forecasting tools for emerging power systems with growing shares of renewable energy. Keywords: intelligent forecasting, Renewable energy forecasting, variable renewable energy, wind power forecasting, machine learning, artificial intelligence.