Accelerated Coverage Optimization With Particle Swarm in the Quotient Space Characterizing Antenna Azimuths of Cellular Networks

Abstract

In order to provide a reliable connection for the ever-increasing devices, cellular networks are facing critical challenges, among which is the issue of network coverage optimization. The costly objective function for network coverage appeals for an efficient approach of optimization, as the canonical particle swarm optimization (PSO) suffers excessive computation caused by population and iteration. The specificity of the antenna azimuths in cellular networks is hereby investigated so as to construct the corresponding metric structures in the naive antenna azimuth space and its quotient space. We introduce two accelerated PSO algorithms induced by the metric structures to maximize the cellular network coverage ratio. The former, named aPSO/S, only considers the shortest arc distance in the naive space, whereas the latter, named aPSO/QS, considers both the shortest arc distance and the equivalence among solutions in the quotient space. The proposed PSO algorithms, mainly the latter as referred to, not only guide the particles to fly toward the shortest arc distance directions but also eliminate lots of unnecessary calculation caused by the equivalence among solutions. The experiments show that the proposed aPSO/QS algorithm edge outs the canonical algorithm and its typical derivatives with various boundary conditions from the perspective of either the convergence speed or the stability with the hyper-parameters. To reach the same performance as that of its best competitor, the proposed aPSO/QS algorithm needs only a fraction of the computation cost so as to be applied in the efficiency-aware live network optimization.

Real‐World Wireless Network Modeling and Optimization: From Model/Data‐Driven Perspective

“…Meta-heuristic methods mainly include genetic algorithm (GA) [74][75][76][77][78] , particle swarm optimization (PSO) algorithm [79][80][81] , simulated annealing (SA) [82] , tabu search [83] , multi-objective evolution algorithm (EA) [84] , and ant colony algorithm (ACA) [85,86] .…”

“…Mai et al . [ 84 ] proposed a BS planning model based on TD‐LTE system and designed a evolutionary algorithm with local search to solve this model. The model aimed at reducing the co‐channel interference, expanding network capacity, and saving the network construction cost at the same time.…”

Hybrid Network–Spatial Clustering for Optimizing 5G Mobile Networks

“…The optimization process of 5G capacity layers [2][3][4][5][6][7]21] involves the identification of optimum values for the adjustable cell/site parameters listed in Figure 1. Each of these parameters contributes in a different way to the network quality and has its own constraints, which will be analyzed in this chapter to detect the most suitable candidate for an automated reconfiguration scheme.…”

“…For this purpose, we used the statistical cumulative distribution functions of these KPIs as well as the 25 th , 50 th , and 75 th percentile to acquire quantitative results on the improvements with respect to the reference scenario. To evaluate the distributions [2,3,6], we are looking for right shifts toward higher RSRP/SINR/normalized per user downlink throughput values, which would indicate network metric improvement. In Figure 7, it is evident that the RSRP distribution shifted to the right from 2-5 dB in various ranges of the distribution for all of the optimization schemes.…”

“…The inclusion of location information in these measurements is of key importance for the identification of coverage deficiencies and optimum network reconfiguration [4][5][6][7][8]. To acquire the location information, various techniques [9][10][11] have been shown to estimate the mobile terminal's location within a specific zone by using only the radio channel quality measurements performed by the mobile terminal devices during handover-related operations.…”