부산대학교 도서관

To solve low-resource utilization, complex storage, and busy traffic in space–air–ground integrated networks (SAGINs), a new multilayered decentralized coded caching (ML-DCC) scheme is proposed in hierarchical networks with nonuniform file popularity and multilevel cache capacity. First, a file popularity prediction is performed by a random forest model with grid search. Second, a multipopularity coded caching (MPCC) strategy by grouping files is executed in a two-hop network with fixed cache size. Finally, a new ML-DCC scheme is proposed to adopt nonuniform file popularity and multilevel cache capacity with both block-coded caching and zero-bit padding to obtain high-resource utilization and efficient file exchange in file transmissions. The innovations are random forest classifier with bagging integration and grid search to improve network traffic and link load, decentralized coded caching to reduce average transferred files, and coded caching and grouping files by popularity to improve network load. Simulation results show that the data payload of the proposed scheme is significantly improved by about 1.88, 1.18, 1.38, 3.53, and 4.39 times, when compared with those of the shared cache, multilevel popularity, hierarchical coded caching, MPCC, and uncoded caching schemes, respectively. Under the expected load of $R=211.57F$ bits of the shared link, the cache size used by the proposed ML-DCC is only 1/42.85 and 1/24.39 of those of the highest popularity first (HPF) and nonuniform cache schemes, respectively.