• N. Sunayana
• Mrs. M.Swathi

Machine learning and artificial intelligence techniques have been proven helpful when pragmatic to a wide range of complex problems and areas such as energy optimization, workflow scheduling, video gaming, and cloud computing Algorithms for cloud computing and machine learning when coupled provide superior results by enhancing the efficiency of cloud data centres over existing methods used by different academics. Objective of the proposed work is to optimize allocation of resource requests within minimum no of servers. However, we need to ensure individual server specific load distribution is kept well under the server capacity so that there is no performance bottleneck. In order to implement the above we will derive slot wise day long predicted load capacity into the distributedly managed cloud system of servers. Day wise requirement will be partitioned into small time quantum each 1 hr. Based on the particular time quantum, requisite no of servers will be kept active. However, on a particular day, actual requirement might be higher than the predicted count. In that case a comparative analysis between predicted trend and actual ongoing requirement will guide us to check the difference and accordingly based on a mathematical model some additional servers will be made active to cater the excess need

Hypervisor vulnerability, Network-cascading, Risk analysis, Side-channel, Unauthorized data access

"AI-Driven VM Threat Prediction Model for Multi-Risks Analysis-Based Cloud Cybersecurity", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.250-253, June-2024, Available :http://www.jetir.org/papers/JETIRGL06042.pdf

"AI-Driven VM Threat Prediction Model for Multi-Risks Analysis-Based Cloud Cybersecurity", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp250-253, June-2024, Available at : http://www.jetir.org/papers/JETIRGL06042.pdf