Location-aware mobile cloud using artificial intelligence

Abstract

Mobile cloud computing is a rapidly evolving technology these days and it faces major problems of load imbalance due to the high demand for mobile applications. There are many techniques to solve the problem, but the user can improve load by using a more optimized solution. This research deals with the VM allocation and migration by means of location awareness. The research paper also presents a user authentication and server load management system to reduce the overload of the server. A captcha based authentication mechanism is also presented for user verification. The concept of Feedback is also introduced for the mobile servers. This concept makes the selection of mobile server for the job list. ANN (Artificial neural network) is used for location awareness judgment. ANN is a machine learning approach, which is used to minimize the human effort and also minimize the processing time to allocate job to an accurate server with minimum SLA violation. MBFD (Mobile best fit decreasing) algorithm is used for the VM allocation and selection policy. This research has considered SLA (Service level agreement) violation and energy consumption to compute the performance of the work with an aim of reducing energy consumption with maximized resource efficiency. The proposed work model is also compared with the work presented by Xiong in the same area.