Exemplary Model of AI-Supported Adaptive Optimization Energy Flow Control in Smart City Microgrids: A Simulation-Based Scenarios

Abstract : The paper focuses on the possibilities for developing a model for adaptive control of electricity flows in urban microgrids using AI support into the Internet of Things networks. The goal is the requirement for smarter, more adaptive and sustainable methods in controlling local energy systems. This is critical for distributed generation and the growing incorporation of renewable energy resources. The study is conceptual in nature and aims to develop an integrated model that combines physical energy infrastructure, IoT-based data acquisition, the analytical capabilities of artificial intelligence, and a logic for adaptive real-time decision-making. It is analyzed the theoretical foundations of adaptive management in microgrids, the design of model development of multilayered architecture, and the interaction between physical and information flows. Particular attention is given to the role of intelligent monitoring devices, forecasting and optimization algorithms, as well as the coordination between local generation, storage, consumption, and exchange with the main grid. The proposed model is analyzed through comparison with traditional, optimization-based, and AI-driven models discussed in the scientific literature, and it is argued that the integration of AI and IoT enables higher adaptability, improved load balancing, more efficient use of local energy resources, and better integration of renewable energy sources in the urban energy environment. The proposed model provides a conceptual framework for the intelligent management of electricity flows in urban microgrids, emphasizing its potential for further development and application in sustainable energy systems.