On group mobility patterns and their exploitation to logically aggregate terminals in wireless networks

Now days wireless networks have become popular as the mobile applications are increasing day by day and mobility of nodes has become an important feature. The desirable property which separates mobile network from wireless networks is the mobility of communication devices. Therefore, there is a need to design routing mechanism in such a way that they can easily adopt to the frequent changes in the mobility pattern of the network. In this paper, Optimized Link State Routing protocol has been modified by implementing Q-Learning concept, a reinforcement learning algorithm which guides network to select next node to which it should forward packets by first calculating the reward R and then calculation of Q-value with neighbors. Performance of this modified routing protocol has been evaluated for parameters like delay, throughput and delivery ratio. Two mobility models have been used, Random Waypoint and Walk. It is observed that performance in terms of above parameters improve considerably in both mobility patterns when intelligent Q-Learning algorithm is implemented in Optimized Link State Routing.

Download Full-text

Support Vector Machine Based Mobility Prediction Scheme in Heterogeneous Wireless Networks

Mathematical Problems in Engineering ◽

10.1155/2015/373824 ◽

2015 ◽

Vol 2015 ◽

pp. 1-10 ◽

Cited By ~ 3

Author(s):

Jiamei Chen ◽

Lin Ma ◽

Yubin Xu

Keyword(s):

Support Vector Machine ◽

Wireless Networks ◽

Prediction Accuracy ◽

Heterogeneous Wireless Networks ◽

Support Vector ◽

Mobility Prediction ◽

Mobility Patterns ◽

Prediction Scheme ◽

The Cost ◽

Different Characteristics

To improve the intelligence of the mobile-aware applications in the heterogeneous wireless networks (HetNets), it is essential to establish an advanced mechanism to anticipate the change of the user location in every subnet for HetNets. This paper proposes a multiclass support vector machine based mobility prediction (Multi-SVMMP) scheme to estimate the future location of mobile users according to the movement history information of each user in HetNets. In the location prediction process, the regular and random user movement patterns are treated differently, which can reflect the user movements more realistically than the existing movement models in HetNets. And different forms of multiclass support vector machines are embedded in the two mobility patterns according to the different characteristics of the two mobility patterns. Moreover, the introduction of target region (TR) cuts down the energy consumption efficiently without impacting the prediction accuracy. As reported in the simulations, our Multi-SVMMP can overcome the difficulties found in the traditional methods and obtain a higher prediction accuracy and user adaptability while reducing the cost of prediction resources.

Download Full-text