Failure Prediction for Scientific Workflows Using Nature-Inspired Machine Learning Approach

Scientific workflows have gained the emerging attention in sophisticated large-scale scientific problem-solving environments. The pay-per-use model of cloud, its scalability and dynamic deployment enables it suited for executing workflow applications. Since cloud is not a utopian environment, failures are inevitable that may result experiencing fluctuations delivered performance. Though single task failure occurs based applications, due to dependency nature, reliability overall system will be affected drastically. Hence rather than reactive fault-tolerant approaches, proactive measures vital workflows. This work puts forth an attempt concentrate on exploration issue structuring nature inspired metaheuristics-Intelligent Water Drops Algorithm (IWDA) combined with efficient machine learning approach-Support Vector Regression (SVR) prognostication which facilitates fault-tolerance scheduling prediction models this study been implemented through SVR-based approaches precision accuracy optimized by IWDA several performance metrics were evaluated various benchmark experimental results prove proposed approach performs better compared other existing techniques.