Fault-Aware Machine Learning and Deep Learning-Based Algorithm for Cloud Architecture

Abstract

The service-oriented computing paradigm is the mutual pool of varied computing, storage and network resources across the globe. The hardware, platform resources are assigned to cloud users using service availability measurement. The resources are accessed by the end-users based on pricing models. The resources are managed using data center network topologies which connect the host machines inside the data center. The identification of faults is a challenging issue in a modular cloud environment. Researchers have developed various methods for the fault-aware scheduling of cloud resources. Fault-aware resource allocation includes static, dynamic, meta-heuristic and learning-based approaches. In this chapter, we primarily focused on existing fault-aware resource allocation techniques and then we proposed a model that will primarily focus on fault forecast in tasks allocation. The projected model is based on a nature-inspired heuristic approach and intelligent artificial neural network. The fault-tolerant aware ANN-based proposed model focuses on performance improvement and reliability testing proactively. The proposed model surpasses the existing state-of-the-art methods for proactive and reactive fault-aware scheduling techniques in a large-scale data center. The results and discussions section supports the reliability assertion of the fault-tolerant aware human brain and nature-inspired model.