Scholarlink

<p>With the rapid development of artificial intelligence and IoT technologies, smart city operations have advanced significantly. At the same time, urban energy systems, particularly power systems, are facing increasing challenges such as load growth, complex energy scheduling, and low-carbon transformation. Therefore, reducing energy consumption while improving the coordination efficiency between communication and power resources has become an important research direction in smart cities. However, conventional IoT-based smart city models mainly focus on technical efficiency and fail to reflect unstructured data such as citizens’ subjective experiences and daily needs. To address these limitations, this study proposes an optimization model for smart city IoT applications by integrating artificial intelligence technologies with the Living Lab methodology. The proposed model was validated through NS-3 simulations to evaluate its performance and technical feasibility. By combining IoT technical infrastructure with citizen participation mechanisms, the model aims to improve both the practicality and sustainability of smart cities. Simulation results show that the proposed model reduced network energy consumption by 29.1% compared with existing models, while achieving a transmission delay of 18.2 ± 0.89 ms, data reliability of 0.83 ± 0.02, and packet loss rate of 2.0 ± 0.18%. These improvements are mainly attributed to the LEACH algorithm and Bayesian correction techniques. In addition, the citizen demand response time improved by 26.6%, while the citizen satisfaction index increased by 54.9%, benefiting from the Living Lab feedback layer and the LSTM-BERT sentiment analysis module. The proposed model also achieved a network lifetime of 126 ± 4.25&#xa0;h and an adaptability index of 0.84 ± 0.04, demonstrating enhanced energy efficiency and adaptability. Overall, the simulation results confirm the effectiveness of the proposed framework. This study provides a scientific and practical solution for the collaborative optimization of communication networks and power energy systems in smart cities, while also supporting the development of low-energy, highly responsive, and citizen-oriented smart city environments.</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

An AI-driven IoT optimization framework for smart cities considering power energy efficiency and citizen participation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月13日

查看全文
  • Hyunjin Chun

摘要

With the rapid development of artificial intelligence and IoT technologies, smart city operations have advanced significantly. At the same time, urban energy systems, particularly power systems, are facing increasing challenges such as load growth, complex energy scheduling, and low-carbon transformation. Therefore, reducing energy consumption while improving the coordination efficiency between communication and power resources has become an important research direction in smart cities. However, conventional IoT-based smart city models mainly focus on technical efficiency and fail to reflect unstructured data such as citizens’ subjective experiences and daily needs. To address these limitations, this study proposes an optimization model for smart city IoT applications by integrating artificial intelligence technologies with the Living Lab methodology. The proposed model was validated through NS-3 simulations to evaluate its performance and technical feasibility. By combining IoT technical infrastructure with citizen participation mechanisms, the model aims to improve both the practicality and sustainability of smart cities. Simulation results show that the proposed model reduced network energy consumption by 29.1% compared with existing models, while achieving a transmission delay of 18.2 ± 0.89 ms, data reliability of 0.83 ± 0.02, and packet loss rate of 2.0 ± 0.18%. These improvements are mainly attributed to the LEACH algorithm and Bayesian correction techniques. In addition, the citizen demand response time improved by 26.6%, while the citizen satisfaction index increased by 54.9%, benefiting from the Living Lab feedback layer and the LSTM-BERT sentiment analysis module. The proposed model also achieved a network lifetime of 126 ± 4.25 h and an adaptability index of 0.84 ± 0.04, demonstrating enhanced energy efficiency and adaptability. Overall, the simulation results confirm the effectiveness of the proposed framework. This study provides a scientific and practical solution for the collaborative optimization of communication networks and power energy systems in smart cities, while also supporting the development of low-energy, highly responsive, and citizen-oriented smart city environments.