Load-Aware VM Migration Using Hypergraph Based CDB-LSTM

Live Virtual Machine (VM) migration is one of the foremost techniques for progressing Cloud Data Centers’ (CDC) proficiency as it leads to better resource usage. The workload CDC often dynamic in nature, envisage upcoming early detection overload status, underload status and trigger at an appropriate point wherein enough number resources are available. Though various statistical machine learning approaches widely applied usage prediction, they failed handle increase non-linear data. To overcome this issue, a novel Hypergrah based Convolutional Deep Bi-Directional-Long Short Term Memory (CDB-LSTM) model proposed. CDB-LSTM adopts Helly property Hypergraph Savitzky–Golay (SG) filter select informative samples exclude noisy inference & outliers. proposed approach optimizes prediction reduces migrations with minimal computational complexity during live VM migration. Further, implements correlation co-efficient measure destination server A was validated using Google cluster dataset compared state-of-the-art terms evaluation metrics.