37. саветовање CIGRE Србија (2025) СИГУРНОСТ, СТАБИЛНОСТ, ПОУЗДАНОСТ И RESILIENCE ЕЛЕКТРОЕНЕРГЕТСКОГ СИСТЕМА МУЛТИСЕКТОРСКО ПОВЕЗИВАЊЕ У ЕНЕРГЕТИЦИ И ПРИВРЕДИ – D2-03
АУТОР(И) / AUTHOR(S): Немања Војновић, Милета Жарковић
DOI: 10.46793/CIGRE37.D2.03
САЖЕТАК / ABSTRACT:
Forecasting electricity consumption and production is a key challenge in power systems, especially with the increasing reliance on renewable energy sources. Traditional forecasting methods are often not sufficiently accurate due to the complexity and variability of energy flows, necessitating the application of advanced artificial intelligence (AI) techniques. This paper explores the potential use of AI, particularly artificial neural networks, to improve the accuracy of electricity consumption and production forecasts. Through the analysis of different models and neural network architectures, parameter optimization was performed to determine the most efficient configuration for forecasting based on temporal and energy data. The proposed approach was implemented in the Python programming language using libraries such as TensorFlow and Scikit-learn. Model evaluation demonstrated significant improvements in forecast accuracy compared to classical methods such as linear regression and support vector machines. In addition to theoretical analysis, the paper includes an experimental evaluation of the developed models through data processing from real power systems. The research results contribute to better production planning, network operation optimization, and increased integration of renewable energy sources into the power system.
КЉУЧНЕ РЕЧИ / KEYWORDS:
neural networks, consumption forecasting, power system, Python, artificial intelligence
ПРОЈЕКАТ / ACKNOWLEDGEMENT:
ЛИТЕРАТУРА / REFERENCES:
- Guillermo Escrivá-Escrivá, Carlos Álvarez-Bel, Carlos Roldán-Blay, Manuel Alcázar-Ortega, New artificial neural network prediction method for electrical consumption forecasting based on building end-uses, Energy and Buildings (43) (2011) 3112–3119.
- L. Ekonomou, Greek long-term energy consumption prediction using artificial neural networks, Energy (35) (2010) 512–517.
- Lei Tang, Xifan Wang, Xiuli Wang, Chengcheng Shao, Shiyu Liu, Shijun Tian, Long-term electricity consumption forecasting based on expert prediction and fuzzy Bayesian theory, Energy (167) (2019) 1144e1154.
- Sasan Barak, S. Saeedeh Sadegh, Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm, Electrical Power and Energy Systems, (82) (2016) 92–104.
- Mahdi Sharifzadeha, Alexandra Sikinioti-Locka, Nilay Shaha, Machine-learning methods for integrated renewable power generation: A T comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression, Renewable and Sustainable Energy Reviews, (108) (2019) 513–538.