Abstract: Data caching is an important technique in metropolitan vehicle networks. It can increase data availability and significantly improve the efficiency of information access by reducing the access latency and bandwidth usage. However, designing efficient caching algorithms is nontrivial when network nodes have limited memory. This paper analyzed how to cache with the help of benefit function, and proposed a way of using local access frequency and neighboring node access frequency to construct the benefit function. The authors simulated the algorithm using a network simulator (NS2), and its advantage was demonstrated in city scenarios.

Key words: metropolitan vehicle network, data caching algorithm, data access frequency

摘要： 数据缓存在城市车辆网络中有着重要的应用。移动车辆通过缓存数据不仅可以减少自身访问数据的延迟，同时可以为整个网络节省带宽。所以，如何更有效地利用节点有限的存储是目前数据缓存研究的主要内容。重点分析了节点利用收益函数决定如何缓存数据，提出了利用本地访问频率和邻居节点访问频率构建收益函数的方法。最后，通过建立城市车辆网络场景并模拟验证了该收益函数下的数据缓存的优越性。

关键词: 城市车辆网络, 数据缓存算法, 数据访问频率