A node deployment and resource optimization method for CPDS based on cloud‐fog‐edge collaboration

• Published in: IET generation, transmission & distribution Vol. 18; no. 21; pp. 3524 - 3537
• Main Authors: Xiong, Xiaoping, Yang, Geng
• Format: Journal Article
• Language: English
• Published: Wiley 01.11.2024
• Subjects: cloud computing; cyber‐physical systems; data communication; delays; distribution networks; energy consumption
• ISSN: 1751-8687; 1751-8695
• DOI: 10.1049/gtd2.13286

With the development of the Internet of Things (IoT) in power distribution and the advancement of energy information integration technologies, the explosive growth in network data volume caused by massive terminal devices connecting to the power distribution network has become a significant challenge. Multi‐terminal collaborative computing is a key approach to addressing issues such as high latency and high energy consumption. In this article, fog computing is introduced into the computing network of the power distribution system, and a cloud‐fog‐edge collaborative computing architecture for intelligent power distribution networks is proposed. Within this framework, an improved weighted K‐means method based on information entropy theory is presented for node partitioning. Subsequently, an improved multi‐objective particle swarm optimization algorithm (MWM‐MOPSO) is employed to solve the task resource allocation problem. Finally, the effectiveness of the proposed architecture and allocation strategy is validated through simulations on the OPNET and PureEdgeSim platforms. The results demonstrate that, compared to traditional cloud‐edge service architectures, the proposed architecture and task offloading scheme achieve better performance in terms of processing latency and energy consumption. Our study presents a novel approach to enhance the efficiency of Cyber‐Physical Distribution Systems (CPDS) through Cloud‐Fog‐Edge collaboration. We introduce a three‐layer distribution information physical system architecture and propose a dual‐layer resource optimization model for cloud‐fog terminal deployment strategy and task allocation, leveraging advanced techniques such as weighted K‐means node partitioning and multi‐objective particle swarm optimization. Experimental validation demonstrates significant reductions in processing latency and energy consumption compared to traditional architectures