A Multiple QOS Constraints Based Trustworthy Resource Sharing In Cloud Computing Using Fuzzy Neural Network Harmony Platform

Cloud computing has become a popular computing paradigm, in which cloud providers offer scalable resources over the Internet to customers. Advancements in cloud computing are inevitably leading to a promising future for collaborative cloud computing (CCC), where globally - scattered distributed cloud resources belonging to different organizations or individuals (i. e. , entities) are collectively pooled and used in a cooperative manner to provide services. In the existing work, harmony platform is introduced to handle both reputation management and resource management in the CCC. The harmony platform makes use of neural network to learn and derive the meaning from complicated or imprecise data and extract patterns and detect trends. It uses adaptive learning to learn how to do tasks based on the data given for training, and then functions as an expert on the data it has been given to analyze. However the existing works more time to build the harmony which reduced the accuracy of QoS prediction. This problem can be overcome by considering the time period for the neural network model training and the load factor calculation. This is achieved in our work by introducing the fuzzy neural network arises from the need to overcome the lengthy learning process and poor convergence of traditional neural network. The experimental results prove that our proposed algorithm is better than the existing method.