DEVELOPMENT OF AN INTELLIGENT CONTROL SOFTWARE PACKAGE FOR ELECTRICAL ENERGY PRODUCTION USING MACHINE LEARNING ALGORITHMS
Abstract
This research is dedicated to the theoretical and practical issues of intelligent management of electricity generation processes within the framework of digital transformation in energy systems. The relevance of the article is justified by the sharp increase in demand for energy resources and the low adaptability of traditional management systems. Within the scope of the study, the architecture of a software complex based on machine learning algorithms and Big Data analysis was developed. Models for high-precision electricity consumption forecasting and real-time generation process optimization are proposed using regression analysis, decision trees, and artificial neural networks. The article analyzes the state policy for ensuring the energy security of the Republic of Uzbekistan and modern trends in the industry.
Keywords
machine learning, intelligent management, electricity, software complex, energy system, forecasting, algorithms, optimization, digital economy, energy efficiency, artificial intelligence, neural networks, data analytics, automation, resource saving.
References
- 1. Decree of the President of the Republic of Uzbekistan. "On the Action Strategy for Further Development of the Republic of Uzbekistan." Collection of Legislative Acts of the Republic of Uzbekistan. – Tashkent, 2017.
- 2. Resolution of the President of the Republic of Uzbekistan. "On Measures for Digitalization of the Energy Sector in 2022–2026." – Tashkent, 2022.
- 3. Gulyamov, S. S., et al. (2019). Blockchain Technologies in the Digital Economy. – Tashkent: TMI Publishing. – 386 p.
- 4. Muhammadiyev, M. M. (2018). Fundamentals of Intelligent Control in Energy Systems. – Tashkent: “Fan va texnologiya” Publishing House. – 210 p.
- 5. Yusupbekov, N. R., et al. (2020). Automated Management Systems for Technological Processes. – Tashkent: “Innovatsiya-Ziyo”. – 520 p.
- 6. Bengio, Y., LeCun, Y., & Hinton, G. (2015). Deep learning for the energy sector: A comprehensive review. Nature, 521(7553), pp. 436–444.
- 7. Chollet, F. (2018). Deep Learning with Python. – Manning Publications. – 384 p.
- 8. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning series). – MIT Press. – 800 p.
- 9. Hippert, H. S. (2017). Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE Transactions on Power Systems, 32(1), pp. 124–135.