Mean-Field Game Theoretic Edge Caching in Ultra-Dense Networks

This paper investigates a cellular edge caching problem under a very large number of small base stations (SBSs) and users. In this ultra-dense edge caching network (UDCN), conventional caching algorithms may crumble in effectiveness as their complexity increases with the number of SBSs. Furthermore, the performance of a UDCN is highly sensitive to the dynamics of user demand and inter-SBS interference, due to the large number of SBSs. To overcome such difficulties, we propose a distributed caching algorithm under a stochastic geometric network model, as well as a spatio-temporal user demand model that specifies the content popularity changes within long-term and short-term periods. By exploiting mean-field game (MFG) theory, the complexity of the proposed UDCN caching algorithm becomes independent of the number of SBSs. The performance of the proposed caching algorithm can easily be calculated using stochastic geometry (SG). Numerical evaluations validate that the proposed caching algorithm reduces not only the long run average cost of the network but also the replicated caching data amount respectively by 24% and 42%, compared to a baseline caching algorithm. The simulation results also show that the propose caching algorithm is robust to imperfect popularity information, while ensuring the low computational complexity.