Quality of Service Estimation Enabled With Trust-Based Resource Allocation in Collaborative Cloud Using Improved Grey Wolf Optimization

Abstract

Collaborative cloud computing utilizes information technology to successfully provide service over the network and serve the end users with tremendously stronger computational capability and enormous memory space at lower costs. Moreover, providing highly trustworthy service is the most fundamental task even on this platform. So far, only some contributions are there that meet the requirements of trust computing in this scenario. This proposal estimates the Quality of Service and trust by analyzing the system behavior using a new trust computing model. This is handled using Neural Network model. Further, a parallel resource matching framework is introduced using the concept of MapReduce concept, thereby the resource allocation is performed without any conflicts. Particularly, the resource allocation is performed precisely by optimization logic, where an Improved Grey Wolf Optimizer is introduced to do the same. In fact, the proposed algorithm is the enhanced version of traditional Grey Wolf Optimizer. Finally, the performance of the projected model is compared over other state-of-the-art models concerning different performance measures.