Abstract: Limited and heterogeneous cache capacity is one of the key parameters which affect the cache efficiency in Device-to-Device (D2D) caching networks. However, most of existing literatures assume all users have homogeneous cache capability. In this regard, cache placement optimization is necessary for practical scenarios with heterogeneous cache capacities. Considering the mobility and random distribution of terminal users, users with different cache capacities were modeled as mutually independent homogeneous Poisson point processes with stochastic geometry. Moreover, the average cache hit ratio was derived with considering both self-offloading and D2D-offloading cases. Finally, a Joint Cache Placement (JCP) algorithm based on coordinate gradient optimization was proposed to obtain the optimal cache placement scheme which can maximize the cache hit ratio. Simulation results show that the proposed JCP can achieve larger cache hit ratio than the existing cache placement schemes.

Key words: Device-to-Device (D2D) caching network, heterogeneous cache capacity, stochastic geometry, cache hit ratio, cache placement optimization

摘要： 在终端直传（D2D）缓存网络中，用户有限且各异的缓存能力是制约缓存效率的一个关键参数，然而现有文献大多考虑不同用户具有相同的缓存能力，针对这一不足有必要进行用户具有不同缓存容量下的D2D内容缓存布设方案优化。首先，鉴于用户终端的移动性和随机分布特性，利用随机几何理论将网络中不同缓存容量的用户节点建模为相互独立的齐次泊松点过程；其次，考虑本地卸载和邻近D2D链路卸载两种内容卸载方式，推导得到网络缓存命中率；最后，将最大化缓存命中率作为优化目标函数，提出了基于坐标梯度的联合缓存布设（JCP）算法，从而得到多用户多缓存容量场景下的内容缓存布设方案。仿真结果表明，与现有的缓存布设方案相比，由JCP得到的缓存布设方案可以有效提高缓存命中率。

关键词: 终端直传缓存网络, 多缓存容量, 随机几何, 缓存命中率, 缓存布设优化