A Machine Learning Based Forwarding Algorithm Over Cognitive Radios in Wireless Mesh Networks

Mesh routers and client devices are self-organized and self-configured to form wireless mesh networks(WMNs) meshsurvey (). A device is called a node in WMNs. Each node is equipped with multiple radios to improve the whole capacities in WMNs yang0 (). The radios in WMNs are cognitive radios, by which the radio devices are capable of learning from their environment and adapting to the environmentCognitive (). Cognitive radio is also called programmable radio because such radio has the ability of self-programmingself (), learning and reasoning Cognitive ().

Machine learning has been studied for about 60 years. It evolved from simple artificial intelligence to a wide variety of applications in image processing, vision, networking, and pattern recognition. In this paper, we propose a learning algorithm for a forwarding node to find one of its links with possibly maximal bandwidth, and then choose next forwarding node and then forward the message to that node. Each node only saves the last three changed bandwidth status of its links . Then the forwarding node learns the three status and predict the potential bandwidth of its links. So the forwarding node is able to find the neighbor with highest link bandwidth as its next hop. We further devise an algorithm to let the source node figure out the forwarding region in order to avoid flooding.

The rest of the paper is organized as follows. Section II discusses the related research on this topic. Section III proposes our novel forwarding method that selects the best next hop. We evaluate the proposed schemes via simulations and describe the performance results in Section IV. Section V concludes the paper.

Some approaches on machine learning, wireless forwarding and related work have been studied yang1 ()MTA ()yang2 ()yang3 ()shen1 ()shen2 ()shen3 (). Wang Y. et al. wang1 ()proposed a machine learning mechanism to improve data transmission in sensor network. The predication of link quality was used to implement the approach. Additionally, they developed a protocol called MetricMap to maintain efficient routing in case the regular routing is not working.

Sawhney A. et al. Sawhney1 () presented a machine learning algorithm to handle congestion controlling in wireless networks. Their approach learns many factors that have impact to congestion controlling, and then uses the parameters in a fuzzy logic to generate better result when congestion takes place. The efficiency is assessed with machine learning tools.

We evaluated our mechanism in a simulated noiseless radio network environment by MATLAB. We create a topology that consists of a number of randomly distributed nodes. We compare our approach(“ML Forwarding”) with two other algorithms. One is congestion control and fuzzy logic with machine learning for wireless communications, say Fuzzy Logic. The other one is supervised learning approach for routing optimization in wireless networks, say Supervised Learning. The compared metrics are transmission delay(Milliseconds) and transmission speed(MBs/Millisecond). We performed a sequence of experiments in which the number of nodes varies from 100 to 300 in increments of 25 over an area of 100x100 meters in the reference network. For each number of mobile users, we conduct our experiments 10 times and present the average value.

Figure 3 shows that our approach results in the least delay. It is because our approach selects the link with potential maximum bandwidth of each hop. Figure 4 shows that with the same reason, our approach generates the maximal transmission speed among the three approaches.

A machine learning based forwarding algorithm in wireless mesh networks with cognitive radios is presented in this paper. In this algorithm, each mobile device keeps the last three times of bandwidth changes of its links that connect its neighbors. Then when a node intends to forward data, the node learns the historical changes of bandwidth and then predicts the possible future bandwidths of the links with neighbor nodes. Hence the forwarding node is able to select the next hop with highest bandwidth. We also designed a geometrical algorithm to let the source node figure out the forwarding region in order to avoid unnecessary flooding. Simulation results demonstrate that our approach outperforms peer approaches.
   
   
ACKNOWLEDGMENT

This work is supported in part by the Spanish government, Dirección General de Investigación Científica y Técnica, a unit of the Ministerio de Economía y Competitividad, TIN2015-69542-C2-1-R (MINECO/FEDER), in collaboration with Universidad Rey Juan Carlos, Spain, under the project “Inteligencia Artificial y Métodos Matemáticos Avanzados para el Reconocimiento Automático de Actividades.”