Machine learning has emerged as a transformative force, innovating diverse industries through its capacity to infuse meaningful insights from large datasets. It plays a pivotal role in powering data analysis, discover pattern matching, identifying hidden or evolving risks in securing systems. The ability of categorizing and behavior analysis is central to its efficacy in cybersecurity. This paper highlights the importance of machine learning in landscape of cyber threats. In this paper, we have identified few machine learning algorithms to categorize huge dataset. The complexities of identifying hidden risks increases by many folds, when the input data is voluminous. Evaluating and contemplating the underlying meaning of data is time-consuming and can be missed easily. We compared different types of machine learning algorithms. Each machine learning algorithm has its strength and weakness. It is found that, the TressJ48 algorithm is proficient in classifying the large dataset, better than Naive Bayes and Decision Stump algorithms. The efficient classifier helps to generate insight, which can be further used to make decisions in terms of cybersecurity.

Paradigm need to shifts from cloud computing to intercloud for disaster recoveries, which can outbreak anytime and anywhere. Natural disaster treatment includes radically high voluminous impatient job request demanding immediate attention. Under the disequilibrium circumstance, intercloud is more practical and functional option. There are need of protocols like quality of services, service level agreement and disaster recovery pacts to be discussed and clarified during the initial setup to fast track the distress scenario. Orchestration of resources in large scale distributed system having muli-objective optimization of resources, minimum energy consumption, maximum throughput, load balancing, minimum carbon footprint altogether is quite challenging. Intercloud where resources of different clouds are in align, plays crucial role in resource mapping. The objective of this paper is to improvise and fast track the mapping procedures in cloud platform and addressing impatient job requests in balanced and efficient manner. Genetic algorithm based resource allocation is proposed using pareto optimal mapping of resources to keep high utilization rate of processors, high througput and low carbon footprint. Decision variables include utilization of processors, throughput, locality cost and real time deadline. Simulation results of load balancer using first in first out and genetic algorithm are compared under similar circumstances.