.png){kind=icon}
.png){kind=icon}
Return
Small cell path loss model optimization using genetic algorithm and particle swarm optimization algorithm
.png){kind=icon}
OA
AI
DOI：10.1007/s11276-025-04022-1.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
An essential requirement for the design of a wireless communication system is the determination of the path loss. This study compares and estimates path loss using urban-micro environment path loss models. Path loss model optimization is taken into consideration to represent the real propagation path and to find the optimized path loss model using a genetic algorithm and particle swarm optimization. The analytically measured path loss is contrasted with the optimized path loss values of each model and error statics are used to assess each model's performance. From the simulation results, it can be deduced that the 5GCM open square model generates the mean square error and standard deviation with the lowest values using both genetic algorithm and particle swarm optimization. The error statistics such as MSE, RMSE and SE of 5GCM-OS LOS scenario using GA are 5.43, 2.33 and 2.33 and in NLOS scenario are 8.86, 2.97 and 3.21, using PSO algorithm in LOS scenario are 5.15, 2.67 and 1.56, in NLOS scenario are 7.84, 2.80 and 1.9 respectively. The 3GPP-SC model in LOS scenario using PSO algorithm is the best path loss model which provides minimized error statistics of 3.85, 1.96 and 1.47 respectively. The PSO algorithm works absolutely better than the GA and produces lowest error statistics compared to the GA optimization algorithm. Therefore, the 5G small cell network operators can improve the service quality at millimeter wave frequencies by employing PSO optimization strategy.
Keywords:
5G
Urban micro environment
Path loss model
Error statistics
Optimization
Genetic algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.1
Papers:
308
Citations:
5.4K
Organization
View more organizations