As smart grid integration and the Internet of Things (IoT) advance, there is an increasing demand for sophisticated algorithms that may boost productivity, improve sustainability, and improve energy management. The primary objective of the research is to develop and use energyaware artificial intelligence (AI) algorithms for Internet of Things (IoT)-enabled smart grids. The recommended algorithms utilise machine-learning techniques to assess real-time data from a scope of IoT devices, including smart meters, sensors, and actuators, to optimise energy distribution, consumption, and overall grid efficiency. The research’s objective is to find solutions for issues caused by smart grids’ dynamic energy demand and variable supply of renewable energy sources. The algorithms can anticipate patterns in energy usage, modify changes in the grid environment, and dynamically distribute resources to reduce energy waste by employing predictive analytics. In addition, this research examines that edge computing capabilities can be included to enhance the responsiveness of AI algorithms, leading to reduced latency and faster decision-making. The suggested energy-aware AI algorithms additionally consider demand-responsive programs, variable energy prices, and energy-saving incentives as factors when examining the economic aspects of energy consumption. The goal of this comprehensive strategy is to achieve a balance between environmental sustainability, cost-effectiveness, and grid efficiency. Testbeds for IoT-enabled smart grids can be used for real-world applications and simulations to validate the suggested methodologies. The results of this research are anticipated to have a major impact on current attempts to create smart grids that are adaptable, durable, and energy-efficient. These grids are essential to the shift towards a more intelligent and sustainable energy infrastructure. The proposed approach has several benefits, including improved smart grid optimisation using cutting-edge energy-aware AI algorithms, sustainability, grid resilience, and cost considerations. © 2024 Elsevier B.V., All rights reserved.