Хорижий лингвистика ва лингводидактика 1-jild 1-son (2023) · 129-138-betlar
ARTIFICIAL INTELLIGENCE FOR POWER QUALITY OPTIMIZATION IN RENEWABLE ENERGY CIRCULATION RELATIONS
Akbarova, Gulkhayo, Акбарова, Гулхаё, Akbarova, Gulxayo
Annotatsiya
Background: The rising adoption of renewable power systems throughout present-day distribution systems has produced various obstacles which affect the delivery of stable power with high quality. The irregular operation of solar and wind power systems creates multiple problems which include voltage changes and harmonic interference and unstable power grid frequency. Methods: The study used a quantitative cross-sectional survey framework to assess AI systems optimize power quality for renewable energy networks which serve American power distribution systems. A total of 185 respondents, including engineers, utility operators, and energy researchers, participated in a structured questionnaire. Pearson correlation along with descriptive statistics based on percentage analysis to study the connection between AI adoption rates and power system performance indicators. Results: AI technology produces a 26% rise in fault detection precision and creates a 20% improvement in load distribution performance and voltage network stability. Machine Learning stands as the most popular AI method which receives 28% of usage while Neural Networks follow with 22% usage. AI adoption creates strong positive connections with power quality and system reliability and fault detection efficiency according to correlation analysis results r = 0.78, 0.74, and 0.81 respectively. The deployment of this technology faces three main obstacles which include expensive installation costs that affect 25% of users and 22% of users struggle to find qualified personnel and 15% of users need to handle security threats. Conclusion: Artificial Intelligence plays a crucial role in enhancing power quality and reliability in renewable energy distribution networks.
Distribution NetworkPower QualityRenewable EnergyArtificial Intelligence
Metadata manbasi: jurnal OAI-PMH arxivi · Sindex toʻliq matnni saqlamaydi, manbaga havola beradi.