Software‐defined networking (SDN) acts as a centralized management unit, especially in a network with devices that operate under the transport layer of the OSI model. However, when a network with layer 7 middleboxes (MBs) is considered, current SDNs exhibit limitations. As such, to achieve a real‐centralized management unit, a new architecture is required that decouples the data and control planes of all network devices. In this report, we propose such a complementary architecture to the current SDN in which SDN‐enabled MBs are included along with contemporary SDN‐enabled switches. The management unit of this architecture improves network performance and reduces routing cost by considering the status of the MBs during flow forwarding. This unit consists of the following two parts: an SDN controller (SDNC) and a middlebox controller (MBC). The latter selects the best MBs for each flow and the former determines the best path according to its routing algorithm and provides information via the MBC. The results show that the proposed architecture improved performance because the utilization of all network devices including MBs is manageable.

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 (IFCPU, IFRAM, and IFBW) 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 IFCPU and IFBW, 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.

No abstract