Scholarlink

<p>The transition toward carbon-neutral sixth-generation (6G) wireless networks requires a fundamental shift in how communication infrastructures manage energy consumption, computational resources, and environmental impact. This narrative review presents a comprehensive and interdisciplinary synthesis of hybrid artificial intelligence (AI)-driven eco-energy management strategies, green radio-frequency (RF) technologies, sustainability evaluation metrics, and lifecycle-oriented environmental modeling for next-generation wireless systems. Unlike existing surveys that primarily focus on communication efficiency, AI optimization, or green networking independently, this work integrates three interconnected domains: AI-driven resource optimization, carbon-aware network management, and lifecycle sustainability assessment (LCA) within a unified analytical framework. The review first examines the sustainability challenges associated with emerging 6G technologies, including the increasing energy demands of terahertz (THz) communication, ultra-massive multiple-input multiple-output (MIMO) systems, AI-native network architectures, and dense edge-cloud infrastructures. It then analyzes multidimensional sustainability indicators, including energy efficiency, energy-per-bit, carbon footprint, embodied energy, carbon-per-connection, green throughput, and AI computational energy overhead, while highlighting current limitations in benchmarking methodologies and standardized sustainability evaluation frameworks. Furthermore, the review critically investigates green RF technologies, including reconfigurable intelligent surfaces (RIS), simultaneous wireless information and power transfer (SWIPT)-enabled systems, low-power THz hardware, ultra-massive MIMO, and energy-efficient beamforming architectures, emphasizing the trade-offs between operational energy savings and lifecycle environmental impact. In addition, emerging hybrid AI approaches combining deep reinforcement learning (DRL), evolutionary optimization, federated learning (FL), graph neural networks (GNNs), and Green AI methodologies are examined for sustainability-aware resource allocation and carbon-conscious network orchestration. To support integrated sustainability analysis, this review introduces literature-derived conceptual frameworks, including the Green RF Technology Evaluation Matrix (GRTEM), Hybrid AI for Sustainable Power Allocation (HYASPA), and Eco-Digital Twin Architecture (Eco-DTA), which provide structured perspectives for evaluating RF sustainability, AI-driven optimization, and lifecycle environmental impact. These frameworks are presented as analytical synthesis models rather than validated deployment architectures, highlighting future validation requirements through simulations, benchmark datasets, and real-world 6G test environments. Finally, the review identifies key research challenges and future directions, including carbon-aware AI optimization, lifecycle-aware RF design, sustainable digital twins, Green federated learning, recyclable communication hardware, and standardized carbon-aware key performance indicators (KPIs). Overall, this work provides a unified eco-energy management roadmap for developing intelligent, adaptive, and environmentally sustainable 6G wireless networks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid artificial intelligence-driven eco-energy management for carbon-neutral 6G wireless networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月29日

查看全文
  • Ogenyi Fabian Chukwudi,
  • Ugwu Chinyere Nneoma,
  • Ugwu Okechukwu Paul-Chima,
  • Okon Michael Ben,
  • Ugwu Jovita Nnenna,
  • Attah Kenneth Ifeanyi

摘要

The transition toward carbon-neutral sixth-generation (6G) wireless networks requires a fundamental shift in how communication infrastructures manage energy consumption, computational resources, and environmental impact. This narrative review presents a comprehensive and interdisciplinary synthesis of hybrid artificial intelligence (AI)-driven eco-energy management strategies, green radio-frequency (RF) technologies, sustainability evaluation metrics, and lifecycle-oriented environmental modeling for next-generation wireless systems. Unlike existing surveys that primarily focus on communication efficiency, AI optimization, or green networking independently, this work integrates three interconnected domains: AI-driven resource optimization, carbon-aware network management, and lifecycle sustainability assessment (LCA) within a unified analytical framework. The review first examines the sustainability challenges associated with emerging 6G technologies, including the increasing energy demands of terahertz (THz) communication, ultra-massive multiple-input multiple-output (MIMO) systems, AI-native network architectures, and dense edge-cloud infrastructures. It then analyzes multidimensional sustainability indicators, including energy efficiency, energy-per-bit, carbon footprint, embodied energy, carbon-per-connection, green throughput, and AI computational energy overhead, while highlighting current limitations in benchmarking methodologies and standardized sustainability evaluation frameworks. Furthermore, the review critically investigates green RF technologies, including reconfigurable intelligent surfaces (RIS), simultaneous wireless information and power transfer (SWIPT)-enabled systems, low-power THz hardware, ultra-massive MIMO, and energy-efficient beamforming architectures, emphasizing the trade-offs between operational energy savings and lifecycle environmental impact. In addition, emerging hybrid AI approaches combining deep reinforcement learning (DRL), evolutionary optimization, federated learning (FL), graph neural networks (GNNs), and Green AI methodologies are examined for sustainability-aware resource allocation and carbon-conscious network orchestration. To support integrated sustainability analysis, this review introduces literature-derived conceptual frameworks, including the Green RF Technology Evaluation Matrix (GRTEM), Hybrid AI for Sustainable Power Allocation (HYASPA), and Eco-Digital Twin Architecture (Eco-DTA), which provide structured perspectives for evaluating RF sustainability, AI-driven optimization, and lifecycle environmental impact. These frameworks are presented as analytical synthesis models rather than validated deployment architectures, highlighting future validation requirements through simulations, benchmark datasets, and real-world 6G test environments. Finally, the review identifies key research challenges and future directions, including carbon-aware AI optimization, lifecycle-aware RF design, sustainable digital twins, Green federated learning, recyclable communication hardware, and standardized carbon-aware key performance indicators (KPIs). Overall, this work provides a unified eco-energy management roadmap for developing intelligent, adaptive, and environmentally sustainable 6G wireless networks.