Intelligent control and monitoring in smart metering systems: a systematic review of artificial intelligence, internet of things, and optimization techniques

The rapid growth of smart grid technologies has spurred the use of intelligent metering systems (IMS) for energy monitoring, demand-side management, efficient energy management, and power grid reliability. This paper provides a thorough review of intelligent control and monitoring strategies for smart metering systems with a focus on the latest developments, applications, limitations, and future trends in this domain. The design of IMS is discussed in detail, along with the role of Artificial Intelligence (AI), IoT, Edge Computing, and Cloud Computing in data acquisition, predictive analytics, autonomous decision making, and secure energy management. The comparative evaluation of different machine learning, deep learning, statistical, probabilistic, and optimization methods is presented to provide a solution for energy load forecasting, electricity theft detection, fault detection, demand response management, predictive maintenance, and distributed energy resources management. Special emphasis is placed on advanced technology innovations reported between 2023 and 2026, namely Transformer model, Graph Neural Network (GNN), Federated Learning (FL), Explainable Artificial Intelligence (XAI), Digital Twin, and Edge Intelligence. The major challenges noted in the literature review include lack of real-world data sets, limitations in terms of interoperability, cyber security threats, reliability of communication, scalability, and industrial deployment issues. The results show that integration of AI–IoT–Edge–Cloud systems could greatly increase the capabilities of the system in terms of its intelligence, adaptability, security, and efficiency. Further research should focus on hybrid approaches, which involve the usage of Edge Intelligence, FL, XAI, Digital Twins, security based on the technology of blockchains, and multi-objective optimization.