Modelling Mobile-X Architecture for Offloading in Mobile Edge Computing

Mobile Edge Computing (MEC) assists clouds to handle enormous tasks from mobile devices in close proximity. The edge servers are not allocated efficiently according the dynamic nature of network. It leads processing delay, and dropped due time limitations. researchers find it difficult complex determine offloading decision because uncertain load condition over nodes. challenge relies on selection nodes for a centralized manner. This study focuses minimizing task-processing while simultaneously increasing success rate service provided by servers. Initially, task-offloading problem needs be formulated based communication processing. Then is solved deep analysis task flow network feedback services. significance model improved with modelling Deep Mobile-X architecture bi-directional Long Short Term Memory (b-LSTM). simulation done Edgecloudsim environment, outcomes show proposed idea. anticipated 6.6 s. following performance metrics, server utilization, ratio task, number evaluated compared existing learning approaches. shows better trade-off