改进遗传算法在站址与小区工参联合优化中的应用

Joint Optimization of Station Location and Cell Parameters Using Improved Genetic Algorithm:An Application

相比于LTE,5G/6G需要更大规模建站来满足信号覆盖的需求,而一个优秀的站址规划与小区工参配置方案能够大大降低运营商建站成本。基于遗传算法,结合最大期望思想通过对由不同物理量组成的染色体分步完成基因突变,能够很好地给出准最优的站址规划与小区工参联合优化方案。同时,给出了一个简单的小区容量评估方案用以评估站址个数、站址规划以及小区工参配置是否合适。仿真结果表明,相比于传统遗传算法,目标函数值提升9.8%,相比于在站址规划中应用频繁的模拟退火算法,目标函数值提升4.7%,所提方法能够很好地求解由不同物理量构成的高维向量组合解问题,为求解在高维空间中组合解问题提供了一种新的通用框架。

Aim to reduce the construction cost of the operator in large-scale station deployment,this paper proposes an improved genetic algorithm to solve the joint optimization problem of station location planning and cell parameter configuration,while meeting the signal coverage requirements.The genetic algorithm is used to achieve quasi-optimal solutions by iteratively mutating the chromosomes composed of different physical quantities based on the weighted sum of the reference signal received power level and the signal-to-interference-plus-noise ratio as the objective function.Meanwhile,a simple and feasible cell capacity evaluation scheme is presented to evaluate the feasibility of the optimization results.Simulation results show that compared with the traditional genetic algorithm,the proposed method achieves a 9.8% increase in the objective function value,and a 4.7% increase compared to the frequent use of simulated annealing algorithm in station location planning.The proposed method can effectively solve the high-dimensional vector combination problem composed of different physical quantities and provide a new general framework for solving combinatorial optimization problems in highdimensional space.