5G Network Deployment Scheme and Communication Efficiency Optimization Method for Intelligent Manufacturing

This article addresses the deployment of 5G networks in intelligent manufacturing factories, focusing on issues such as high energy consumption, signal coverage efficiency, and minimizing deployment costs. Initially, models for the workshop, macro base stations, and micro base stations are simplified and quantified. This leads to the construction of models for minimizing base station energy consumption, minimizing base station deployment costs, and optimizing 5G network coverage. Simultaneously, full network coverage in these models serves as the cut-off condition. To find the optimal solution, this article employs an integrated algorithm that combines an improved K-means clustering algorithm with the NSGA-III algorithm. Additionally, the algorithm incorporates the Adam gradient descent method for iteration, enabling the clustering of network nodes from terminal devices in the factory. This approach not only reduces computational complexity but also enhances the algorithm’s global search and convergence capabilities. Through simulation experiments, our method effectively identifies the optimal solution for 5G deployment schemes. Furthermore, the improved algorithm demonstrates superior convergence performance compared to its predecessor, thereby validating the feasibility of our approach.