VHO decision using a fuzzy reverse MLP with Reinforcement Learning

Next generation mobile networks are envisioned to be heterogeneous with an increase in demand towards ubiquitous video applications. As various networks have widely different characteristics, it is difficult to maintain the quality of service (QoS) after executing a handover from one network to another. Moreover, maintaining a good user perception level “quality of experience” (QoE), based on video applications, during the handover needs an intelligent handoff decision mechanism. In this paper, a multi-criteria vertical handover algorithm enhancing the handover performance is proposed. This algorithm is based on a fuzzy neural optimized approach. Fuzzy logic controllers (FLC) takes into account multiple relevant criteria and rules based on prior knowledge of the network. A multi-layer perceptron (MLP) neural network is trained in order to learn the relationship between FLC parameters and QoS/QoE scheme. Then, MLP inversion is performed in order to obtain the optimal parameters of the membership functions starting from QoS/QoE objective values. Performances of proposed algorithm are evaluated and compared to other algorithms without the reverse technique. Results show improvement on network performances.