Abstract
A semi-supervised classifier is used in this paper is to investigate a model for forecasting unpredictable load on the IT systems and to predict extreme CPU utilization in a complex enterprise environment with large number of applications running concurrently. This proposed model forecasts the likelihood of a scenario where extreme load of web traffic impacts the IT systems and this model predicts the CPU utilization under extreme stress conditions. The enterprise IT environment consists of a large number of applications running in a real time system. Load features are extracted while analysing an envelope of the patterns of work-load traffic which are hidden in the transactional data of these applications. This method simulates and generates synthetic workload demand patterns, run use-case high priority scenarios in a test environment and use our model to predict the excessive CPU utilization under peak load conditions for validation. Expectation Maximization classifier with forced-learning, attempts to extract and analyse the parameters that can maximize the chances of the model after subsiding the unknown labels. As a result of this model, likelihood of an excessive CPU utilization can be predicted in short duration as compared to few days in a complex enterprise environment. Workload demand prediction and profiling has enormous potential in optimizing usages of IT resources with minimal risk.
Highlights
The current cloud based environment is very dynamic in which the web traffic or number of hits to some applications increases exponentially in a short span of time and it drastically slows down the enterprise application system
We have developed and implemented a novel practical approach to predict burst in traffic behaviour in a complex and highly integrated environment where more than 130 IT applications were live and thousands virtual users generate user-load under stress conditions
The proposed practical approach helped the IT architects to mitigate the risk of an unexpected failure of the IT systems, due to burst of traffic patterns, within a very short duration of time (3 to 4 hours) compared to 1 - 2 weeks as in the current practice
Summary
The current cloud based environment is very dynamic in which the web traffic or number of hits to some applications increases exponentially in a short span of time (burst in traffic) and it drastically slows down the enterprise application system. It is observed that at many occasions the systems crash randomly due to unpredictable load because of excessive web traffic for short period This results in loss of efficiency and productivity of service providers. Our reliance on cloud internet computing is increasing every day and it has become unavoidable It has become very important for big enterprises to keep the key applications running 24/7 to an acceptable efficiency during the whole year. The main aim of this research paper is to develop and implement a practical approach to forecast unpredictable burst in traffic by using semi-supervised neural nets classifier To perform this we have analysed the work-load patterns hidden in of the key transactions over a year and observed CPU utilization under stress conditions (high volume of web traffic) using data mining techniques
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
