Software‐defined networking (SDN) has a vital role in network resource utilization. However, it does not provide a comprehensive view of middleboxes (MBs). In this article, we proposed an intelligent dynamic routing framework for performance optimization based on a SDN architecture with a comprehensive view of all network properties. This routing framework also uses the genetic algorithm (GA) for performance improvement. It extracts the CPU, memory, and bandwidth utilization of MBs as dynamic routing parameters. The implemented GA calculates the impact factor (IF) of these parameters to declare the impact of each parameter in network performance. The obtained results show that considering MBs status in flow forwarding improves the tested network's resource utilization by 13, 10, and 7 times compared with hop‐based shortest path first, random path selection, and Round Robin methods, respectively. The results also showed that considering IFs (IF_CPU, IF_RAM, and IF_BW) in routing procedure would improve the network's performance. Therefore, we used the GA to calculate optimal IFs for fairness load balancing and performance optimization. The GA calculates 0.4 and 0.6, for IF_CPU and IF_BW, respectively. It calculates these IFs only after five iterations. It also showed that we could ignore the RAM utilization parameter in our dynamic routing as our MBs are not memory‐bounded. The simulation results declared that routing with optimal IFs not only improves the network' throughput but also improves load distribution fairness by about 25% compared with routing without the IFs.

中文翻译：

---

通过软件定义网络中的智能框架优化中间盒选择

软件定义网络（SDN）在网络资源利用中起着至关重要的作用。但是，它没有提供中间箱（MB）的全面视图。在本文中，我们提出了一种基于SDN架构的智能动态路由框架，用于性能优化，并具有所有网络属性的全面视图。此路由框架还使用遗传算法（GA）来提高性能。它提取MB的CPU，内存和带宽利用率作为动态路由参数。实施的GA计算这些参数的影响因子（IF），以声明每个参数对网络性能的影响。获得的结果表明，与基于跳的最短路径优先相比，考虑流转发中的MB状态可以将测试网络的资源利用率提高13倍，10倍和7倍，随机路径选择和循环法。结果还表明，考虑IF（IF路由过程中的_CPU，IF _RAM和IF _BW）将提高网络的性能。因此，我们使用GA来计算最佳IF，以实现公平负载平衡和性能优化。GA分别针对IF _CPU和IF _BW计算出0.4和0.6。仅在五次迭代后才计算这些IF。这也表明我们可以忽略动态路由中的RAM利用率参数，因为我们的MB不受内存限制。仿真结果表明，与没有IF的路由相比，具有最佳IF的路由不仅可以提高网络的吞吐量，而且还可以将负载分配公平性提高25％。