Summary Resource management is one of the major issue in cloud computing for IaaS. Among several resource management problems allocation, provisioning, and requirement mapping directly affects the performance of cloud. Resource allocation signifies assignment of available resources to different workloads in an economically optimal manner. Precise and accurate allocation is required to maximize the usage of resources. Current method of task allocation do not take previously acquired knowledge, type of the tasks, and the QoS parameters altogether into account in the allocation phase, and it has not been trained for different set of tasks. Furthermore, the self‐optimization of the autonomous system fails to address the task type and identify the relationship between tasks and the resource demands along with its requirements. Important aspects like task management and resource utilization are the primary factors to consider for such a characteristic. This paper will present a novel autonomic resource management framework named task‐aware autonomic resource allocation strategy using neural networks (TARNN), which aims to use knowledge about the behavior of the task over an extended period of time and use this knowledge to allocate resources when a similar task is submitted in future by the user. To effectively do the allocation, a neural network–based approach is adopted to classify the tasks appropriately based on the task parameters, task type, and QoS parameters and allocate the resource optimally for a new task autonomously, without the intervention of the cloud provider. Moreover, to identify and improve the relationship of the tasks with the resources in the context of scheduling, we have proposed a novel modified Particle Swarm Optimization (m‐PSO) algorithm to schedule the tasks to resources based on resource demands. In TARNN, we have separated the collected synthetic dataset into 60‐40 ratio for training and testing purposes. We found that the neural network–based approach provides almost 80% accurate classification w.r.t. task type and QoS parameters. We have also compared our results with support vector machine (SVM) and got 69% accuracy. Since the tasks are classified appropriately, the occurrence of resource reconfiguration and VM migration is drastically reduced. Hence, our system provides better allocation of resources and schedules the tasks appropriately to the resources, thereby improving the performance of the cloud.

Cloud computing is basically an internet based computing, whereby shared configurable resources are provided to cloud service consumers as services on demand. As an increasing growth of cloud computing, many enterprises provide different cloud services to cloud service consumers. From cloud service consumer's perspective, it is difficult to choose an appropriate cloud service that satisfies their QoS requirements. As requirements of one cloud service consumer will vary from another, dynamic ranking has to be used to satisfy the requirements of different cloud service consumers. A simple model is needed to address the dynamic ranking of cloud services. The dynamic ranking and selection of cloud services is solved using Linear Programming(LP) model. This project considers quantifiable attributes such as processor speed, cost, etc. and some non-quantifiable attributes to rank various cloud services according to the requirements of cloud service consumer using Linear Programming(LP) technique.