Machine Learning Failure-Aware Scheme for Profit Maximization in the Cloud Market

A successful cloud trading system requires suitable financial incentives for all parties involved. Cloud providers in the market provide computing services to clients order perform their tasks and earn extra money. Unfortunately, applications are prone failure several reasons. service responsible managing availability of scheduled high-level quality customers. However, is extremely heterogeneous distributed, making resource management a challenging problem. Protecting against non-trivial mission due dynamic, heterogeneous, largely distributed structure environment. The existing works literature focus on task prediction neglect remedial (post) actions. To address these challenges, this paper suggests fault-tolerant scheme which optimal amount resources extracted at each epoch replace failed machines. When provider detects malfunctioning machine, they transfer associated work new machinery.