A Review of Current Trends and Challenges in the Application of Digital Twins and Artificial Intelligence in Energy Systems of the Oil and Gas Industry

This paper presents a review of the current state and development directions of digital twin (DT) and artificial intelligence (AI) technologies, with a focus on their application in energy systems at oil and gas industry facilities. The architectural foundations of DTs are examined, including the six-level model and its classification by levels and application domains. Key AI methods used in conjunction with DTs are discussed, such as machine learning for load and renewable generation forecasting, reinforcement learning for control optimization under uncertainty, and generative AI for decision support and scenario modeling. Applied solutions are considered in detail, including predictive maintenance of equipment, optimization of associated petroleum gas utilization, and the development of intelligent energy management systems. Current challenges and issues are identified, including data processing infrastructure selection, cybersecurity, and economic and legal regulation. Prospects for DT implementation are outlined, taking into account international and Russian environmental requirements, in particular the target of utilizing at least 95% of associated petroleum gas by 2027. Examples of domestic and international developments and studies demonstrate that DT and AI technologies have significant potential for addressing tasks such as equipment monitoring, load forecasting, production process optimization, and automated energy system control in the oil and gas sector.