No abstract

Load balancing routing and quality of transmission (QoT) aware routing have been increasingly studied in mesh wireless networks (WMN) to improve their performance. For the load balancing routing, the traffic bottleneck in the network can be resolved. However, it can decrease QoT because the routes may pass through multiple hops. On the other hand, the QoT aware routing often improves the QoT of the routes, but it can increase the traffic bottleneck due to the unbalanced traffic load in the network. Therefore, the investigation of load balancing routing taking into account QoT is very essential, especially in the case of a wide and ultra-high speed WMN. In this paper, we propose a load balancing routing algorithm under the constraints of QoT for WMN. Our method uses the principle of the software defined networking (SDN) to choose the load balancing routes satisfying the constraints of QoT. Our performance evaluations using OMNeT++ have shown the effectiveness of the proposed algorithm in improving QoT of the data transmission routes, increasing the packet delivery ratio and the network throughput, decreasing the end-to-end delay.

No abstract

In software-defined wireless networking (SDWN), the optimal routing technique is one of the effective solutions to improve its performance. This routing technique is done by many different methods, with the most common using integer linear programming problem (ILP), building optimal routing metrics.These methods often only focus on one routing objective, such as minimizing the packet blocking probability, minimizing end-to-end delay (EED), and maximizing network throughput. It is difficult to consider multiple objectives concurrently in a routing algorithm. In this paper, we investigate the application of machine learning to control routing in the SDWN. An intelligent routing algorithm is then proposed based on the machine learning to improve the network performance. The proposed algorithm can optimize multiple routing objectives. Our idea is to combine supervised learning (SL) and reinforcement learning (RL) methods to discover new routes. The SL is used to predict the performance metrics of the links, including EED quality of transmission (QoT), and packet blocking probability (PBP). The routing is done by the RL method. We use the Q-value in the fundamental equation of the RL to store the PBP, which is used for the aim of route selection. Concurrently, the learning rate coefficient is flexibly changed to determine the constraints of routing during learning. These constraints include QoT and EED. Our performance evaluations based on OMNeT++ have shown that the proposed algorithm has significantly improved the network performance in terms of the QoT, EED, packet delivery ratio, and network throughput compared with other wellknown routing algorithms.

No abstract