Department of Electrical and Electronic Engineering, Imperial College, London SW7 2AZ, UK.
Sensors (Basel). 2018 Oct 8;18(10):3354. doi: 10.3390/s18103354.
In-network caching is one of the key features of information-centric networks (ICN), where forwarding entities in a network are equipped with memory with which they can temporarily store contents and satisfy en route requests. Exploiting in-network caching, therefore, presents the challenge of efficiently coordinating the forwarding of requests with the volatile cache states at the routers. In this paper, we address information-centric networks and consider in-network caching specifically for Named Data Networking (NDN) architectures. Our proposal departs from the forwarding algorithms which primarily use links that have been selected by the routing protocol for probing and forwarding. We propose a novel adaptive forwarding strategy using reinforcement learning with the random neural network (NDNFS-RLRNN), which leverages the routing information and actively seeks new delivery paths in a controlled way. Our simulations show that NDNFS-RLRNN achieves better delivery performance than a strategy that uses fixed paths from the routing layer and a more efficient performance than a strategy that retrieves contents from the nearest caches by flooding requests.
网内缓存是信息中心网络（ICN）的关键特性之一，网络中的转发实体配备有内存，可使用该内存临时存储内容并满足沿途的请求。因此，利用网内缓存带来了与路由器上易变的缓存状态有效协调请求转发的挑战。在本文中，我们研究了信息中心网络，并特别考虑了用于命名数据网络（NDN）体系结构的网内缓存。我们的提议偏离了主要使用路由协议选择用于探测和转发的链路的转发算法。我们提出了一种使用强化学习和随机神经网络（NDNFS-RLRNN）的新颖自适应转发策略，该策略利用路由信息并以受控的方式积极寻找新的传输路径。我们的模拟表明，NDNFS-RLRNN 比使用来自路由层的固定路径的策略具有更好的传输性能，并且比通过洪水请求从最近的缓存中检索内容的策略具有更高的效率。
