INNOVATIVE APPROACHES TO BUILDING THE ENERGY NETWORK OF THE FUTURE USING ARTIFICIAL INTELLIGENCE
Abstract
Dziubanovska N.V. INNOVATIVE APPROACHES TO BUILDING THE ENERGY NETWORK OF THE FUTURE USING ARTIFICIAL INTELLIGENCE
Purpose. The aim of the article is to form the concept of “energy network of the future”, identify the main challenges faced by the current energy system that require new innovative approaches and solutions, and analyse the possibilities of applying artificial intelligence algorithms to increase its efficiency.
Methodology of research. The theoretical and methodological basis of the research is scientific works of scientists on the application of artificial intelligence algorithms in the energy sector. During the research, general scientific and special methods were used, including analysis and synthesis (for analysing the dynamics of greenhouse gas emissions, final energy consumption, and energy consumption based on renewable sources in Ukraine), graphical – for visualizing the obtained results, grouping renewable energy sources by type (for analysing dynamic shifts in the structure of overall energy consumption based on renewable sources), abstract and logical (for outlining the main directions of applying artificial intelligence in the energy network).
Findings. The concept of “energy network of the future” has been defined, which will be understood as an integrated and automated system that uses renewable energy sources and ensures stable and uninterrupted electricity supply to consumers. The main task of such an energy network is to transition to low-carbon technologies, increase the role of renewable energy, and use energy-efficient technologies and innovations. The main challenges faced by the modern energy system requiring new innovative approaches and solutions include reducing greenhouse gas emissions, increasing the efficiency and safety of energy systems, developing renewable energy sources, and more. An analysis of the possibilities of using artificial intelligence to increase the efficiency of the energy network’s work has been carried out, resulting in the generalization of the main principles of machine learning algorithms and other methods for optimizing various processes in the energy industry, namely: data collection and processing, model training, implementation of decisions, monitoring, and support.
Originality. The technological content of “energy network of the future” has been further developed, which involves a transition to low-carbon technologies, increasing the role of renewable energy and the use of energy-efficient technologies and innovations. The main directions of applying artificial intelligence have been justified and their effectiveness for solving important energy issues has been determined.
Practical value. The research results can be used to develop new innovative products and services that allow energy sector companies to reduce costs and improve the quality of their services. The research can become an important source of information for government and non-governmental organizations involved in developing energy development strategies in the country.
Key words: energy network, innovation, machine learning, technology, artificial intelligence.Keywords
Full Text:
References
Hryb, O., Senderovich, G., Diachenko, O., Karpaliuk, I. and Shvets, S. (2020), “Analysis of the prospects for the development of digital energy in Ukraine”, Visnyk Natsionalnoho tekhnichnoho universytetu KhPI. Seriia: Hidravlichni mashyny ta hidroahrehaty, no. 1, pp. 85-90.
Timchenko, O.M., Nebrat, V.V. et al. (2019), “Organizational and economic determinants of the development of digital energy in Ukraine”, Ekonomika i prohnozuvannia, no. 3, pp. 78-100.
Karpa, D.M., Tsmots, I.H. and Opotiak, Y.V. (2018), “Neural network tools for predicting energy resource consumption”, Naukovyi visnyk NLTU Ukrainy, Issue 28(5), pp. 140-146, available at: https://doi.org/10.15421/40280529 (access date January 12, 2023).
Hariachevska, I.V. and Movenko, S.Yu. (2018), “Development of artificial neural networks for electricity consumption forecasting”, Visnyk Khersonskoho natsionalnoho tekhnichnoho universytetu, no. 3(1), pp. 250-259, available at: http://nbuv.gov.ua/UJRN/Vkhdtu_2018_3%281%29__37 (access date January 12, 2023).
Chernenko, P.O. and Miroshnyk, V.O. (2018), “Short-term forecasting of electric load of a power supply company using a deep learning artificial neural network”, Pratsi Instytutu elektrodynamiky NAN Ukrainy, no. 50, pp. 5-11, available at: http://nbuv.gov.ua/UJRN/PIED_2018_50_3 (access date January 12, 2023).
Zhyvoglyad, O. (2019), “Forecasting of electricity consumption based on neural network”, Elektronna ta Akustychna Inzheneriia, no. 2(1), pp. 39-42.
“State Statistics Service of Ukraine”, available at: https://ukrstat.gov.ua/ (access date January 12, 2023).
“National Report on the State of the Environment in Ukraine in 2021”, available at: https://mepr.gov.ua/diyalnist/napryamky/ekologichnyj-monitoryng/natsionalni-dopovidi-pro-stan-navkolyshnogo-pryrodnogo-seredovyshha-v-ukrayini/ (access date January 12, 2023).
Bukharina, L.M. and Tytarchuk, D.I. (2016), “Forming an effective energy-saving policy for an industrial enterprise”, Akademichnyi ohliad, no. 2, pp. 72-76, available at: http://nbuv.gov.ua/UJRN/ao_2016_2_10 (access date January 12, 2023).
DOI: https://doi.org/10.37332/2309-1533.2023.1.21
Refbacks
- There are currently no refbacks.
INNOVATIVE ECONOMY 2006 - 2024