• Version
• Download 4
• File Size 303.54 KB
• File Count 1
• Create Date 24 March 2026
• Last Updated 24 March 2026

Optimisation of Resource Utilisation in Cloud Computing Environments using Machine Learning

Dr. K. Satyam1, V Harish2
1Associate Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati,
Andhra Pradesh, India.
2 Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra
Pradesh, India.

Abstract:This study demonstrates the significance of time in cloud computing scheduling, allocation, and intelligent resource utilisation. In order to estimate the runtime based on CPU utilisation, memory usage, disc speed, and network delay using MATLAB, this study compares two machine learning models: Support vector machine (SVM) and Decision tree (DT). While the DT (Decision tree) divides execution time into groups or bins (0-10 sec, 10-20 sec, etc.) and uses them to predicttime, SVM attempts to anticipate the smallest feasible error between actual life and expected outcome. There are two common tests to compare which model is superior. The first is the MEAN SQUARED ERROR (MSE), which indicates how accurate your forecasts are. Second, the r-squared approach indicates how well the model captures the variation in the data. The SVM outperforms DT by an astounding 81%, according to the results. As a result, SVM produced significantly superior predictions that were quite accurate, but DT produced predictions that were probably more inaccurate than SVM's. Additionally, it is thought that in the years to come, SVM may be combined with other cloud models to produce
Keywords- Cloud computing; Machine learning; Support Vector Machine; Decision Tree; Prediction; Runtime; Networkdelay; Mean squared error.