Year: 2025
Type: article
Abstract: Physical cell identification (PCI) collision, confusion and interference are key problems in modern LTE network optimization, which significantly affect network performance and user experience. Traditional optimization methods that rely on manual adjustment and empirical rules are inefficient and difficult to adapt to complex network environments. This paper presents an optimization method based on simulated annealing to minimize PCI conflict, confusion and interference. Through the collection and pre-processing of user device MR Data and network topology data, combined with feature engineering to extract key features, a hybrid integer programming model with the goal of minimizing the total MR Value is constructed, and the constraint conditions of node unique PCI allocation and adjacent PCI differentiation are designed, and the improved simulated annealing algorithm is used to solve the problem. Experimental results show that the proposed method reduces the total MR Value from 50492016 to 32602231, effectively reduces PCI conflict and interference, significantly improves network stability and performance, and provides a new method with theoretical significance and practical value for LTE network optimization.
DOI: 10.54097/nv1gfk68
Authors: Yifan Lai, Haoran Gao
Institution: Northwestern Polytechnical University
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409621519