面向边缘计算的物联网网络流量测量方法

在物联网中,边缘计算能够提供物联网计算的实时性,减少网络中数据的传输量.为了适应物联网技术的发展,研究了采用软件定义网络(SDN,software defined networking)架构的物联网网络,并利用SDN提供的方法对网络中的流量进行测量.细粒度流量测量可以更准确地描述网络中的流量,但同时也需要消耗大量的测量开销.为了减少测量过程中产生的开销并获得近似的细粒度测量,提出了一种面向边缘计算的物联网网络流量测量方案.新测量架构采用粗粒度测量和插值优化等方法进行测量.首先,在文中采用随机抽样方法通过OpenFlow协议快速获得粗粒度的网络流量测量.接着,对粗粒度的网络流量进行插值恢复,并利用多约束的优化方法对插值结果进行优化,直到找到满足条件约束的最优细粒度流量测量结果.最后,文中通过实验验证了所提出的测量方法的可行性和有效性.

An edge computing-based network traffic measurement of the Internet of Things

In the Internet of Things, edge computing can provide real-time performance of IoT computing and reduce the amount of data transmitted in the network. In order to satisfy the development of the IoT technology, the IoT network with software defined network (SDN) architecture was studied in this paper, and the method provided by SDN was used to measure the traffic in the network. Fine-grained traffic measurement can accurately describe traffic in the network, but it also consumes a lot of measurement overhead generated in the measurement process. To reduce the overhead and obtain approximate fine-grained measurements, an IoT network traffic measurement scheme based on edge computing was proposed. The new measurement architecture involved coarse-grained measurements and interpolation optimization. The random sampling method was used to measure coarse-grained network traffic through Open Flow protocol. Then, the coarse-grained network traffic was interpolated and restored, and the interpolation result was optimized by the multi-constraint optimization method to obtain the optimal fine-grained flow measurement result that satisfied the condition constraint. Finally, the feasibility and effectiveness of the proposed measurement method were verified by experiments.