WDWWO Combined NN and Its Application to Handover in Heterogeneous Networks

Abstract

In heterogeneous networks, vertical handover (VH) has a significant impact on networking performance including delay, throughput, and call block probability. VH management involves technique complexity, network modelling challenges, and inaccurate handover despite several prior efforts. This chapter discusses hybrid methodology that aims to provide accurate VH maintaining less complexity. Deep residual neural (DRN) and wind-driven water wave optimisation (WDWWO) are combined to perform VH. To address this situation, the use of DRN is combined with WDWWO for weight optimisation, resulting in optimised DRN (ODRN). ODRN modelling encompasses a wide range of networking parameters, viz., bandwidth, delay, throughput, velocity, BER, SNR, energy consumption, monetary cost, and data traffic. Performance analysis is carried out based on various parameters such as energy consumption, RSS, throughput, packet delivery ratio, packet loss, handover failure rate, algorithm convergence, and latency are compared with D-TOPSIS, FIS-ENN, and F-AHP.