Optimizing energy consumption in automated systems by using cloud technologies
Students Name: Slichnyi Sviatoslav Ihorovych
Qualification Level: magister
Speciality: Computerized Control Systems and Automatics
Institute: Institute of Computer Technologies, Automation and Metrology
Mode of Study: full
Academic Year: 2024-2025 н.р.
Language of Defence: ukrainian
Abstract: The master’s qualification thesis is dedicated to researching and implementing cloud technologies for optimizing energy consumption in automated systems of industrial facilities. Under the current challenges of the energy sector, such as rising energy costs, the need to improve energy efficiency, and the introduction of environmentally oriented solutions, the proposed approaches gain particular relevance. The research aims to develop an integrated energy management system based on cloud computing for collecting, processing, and analyzing large volumes of data. The theoretical part of the thesis analyzes modern energy management methods and existing software and hardware solutions for automating energy processes. Special attention is given to the review of cloud platforms used in industrial environments, such as Amazon Web Services, Microsoft Azure, and Google Cloud, and their functional capabilities for integration with energy management systems. Studies [2, 3] emphasize the effectiveness of using cloud technologies to address energy efficiency challenges. Based on the analysis, the system architecture was selected, consisting of several modules, including a data collection module, a cloud processing module, a decisionmaking module, and a user interface for result visualization. The methodology is based on the use of machine learning algorithms for energy consumption forecasting, anomaly detection, and developing recommendations for optimizing energy resource usage. The practical part of the thesis focuses on the implementation of software that ensures efficient energy consumption management based on data analysis from industrial facilities. Modern cloud services were utilized in the development to ensure scalability and flexibility of the solution. The system was tested on real production data, and the results confirmed its ability to reduce energy costs by up to 15% compared to traditional approaches [4]. In addition to economic efficiency, the thesis addresses issues of environmental safety and compliance with modern occupational safety standards. The proposed system 7 provides automatic detection of potential energy consumption risks and generates reports to minimize such risks. Keywords: automation, machine learning, energy optimization, cloud technologies. 1. Energy Efficiency 2023. Analysis and Forecasts to 2030. International Energy Agency: веб-сайт. URL: https://www.iea.org/reports/energy-efficiency-2023 (дата звернення: 15.10.2024). 2. Zhuk, O. V., Myronenko, S. V., Ivanova, N. A. Machine Learning Techniques for Energy Optimization: A Review. Journal of Energy Research. 2023. Vol. 28. P. 45–56. 3. Implementation of IoT-based Energy Management Systems in Smart Factories. IEEE Transactions on Industrial Informatics. 2022. Vol. 18, No. 5. P. 2550– 2561. 4. Vykorystannia khmarnykh platform u enerhetytsi: AWS ta Microsoft Azure. IT Pro Portal: veb-sait. URL: https://www.itproportal.com (data zvernennia: 11.11.2024). 5. AI in Energy Management Systems: Role of Machine Learning in Energy Optimization. Forbes Technology Council: веб-сайт. URL: https://www.forbes.com (дата звернення: 13.10.2024). 6. Smart Grid: tekhnolohii dlia suchasnoho upravlinnia enerhospozhyvanniam. IEEE Xplore: veb-sait. URL: https://ieeexplore.ieee.org (data zvernennia: 12.11.2024).