Intelligent mobile ad hoc network management system

This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London.Currently wireless networks have grown significantly and contributed to several fields of technology especially communication. One of the imperative features of wireless networks is providing access to information without considering the geographical and the topological attributes of a user. One of the most popular wireless network technologies is mobile Ad Hoc network. In order to find an appropriate route between two connected nodes, several routing protocols have been suggested and created. Each routing protocol performs best under specific network conditions, such as under relatively low mobility level and highly dense network size. The main attribute to routing protocol performance degradation is connected to changes of the network context and conditions. Up to date, there is no routing protocol that can maintain its performance at high level under all possible context conditions. In this thesis, the introduction of a management system utilizing artificial intelligence and optimisation techniques to be responsible for predicting MANET routing protocol performance behaviour and selecting the best suited one to adapted to the changes in the network conditions to solve the network performance degradation problem. MANET is modelled with the support of Artificial Intelligent (AI) techniques to help in a better understanding of the network performance under different context scenarios, the use of various packet types, and operating with different routing protocols. Thus the main addition made by this research is the use of different techniques to model our mobile Ad Hoc networks in terms of their behaviour that can be utilised for prediction purposes. An additional contribution is utilisation and comparison of different optimisation techniques based on MANET performance models that can be part of the system for choosing the best of the selected five routing protocols based on the network. The determined parameters for the context that affect the network were average mobility, number of nodes, and packet types. I_MMS manages the selection of a routing mechanism to maintain a stable performance by the network. The selected routing mechanism resulted by a minimum value in delay rate, RA, load, and higher throughpu