Reviewing AI-Powered Solutions for Energy Efficiency in 6G Communication Systems

The advent of 6G networks promises ultra-high speeds, low latency, and ubiquitous connectivity, but achieving energy efficiency in such data-intensive systems remains a key challenge. This study reviews the vital role of advanced AI sensing approaches in optimizing energy use while maintaining high network performance. Techniques involving machine learning, deep learning, and hybrid AI enable real-time adaptation to network conditions, ensuring efficient resource allocation and reduced energy waste. Key applications include spectrum management, beamforming optimization, massive MIMO systems, and device-todevice communication. The review highlights AI’s role in enabling dynamic resource management, fault detection in self-healing networks, and energy-aware spectrum allocation. It also explores challenges like processing overhead, scalability, and data privacy. Emerging solutions such as federated learning and edge computing offer promising ways to balance computational demands with energy efficiency. Additionally, future directions include integrating renewable energy sources and developing lightweight AI algorithms to reduce carbon footprints and operational costs. By classifying and comparing various AI sensing strategies, this paper provides valuable insights into their capabilities and limitations. The findings support researchers and practitioners in designing sustainable 6G infrastructures and underscore AI’s transformative potential in advancing green telecommunications.