Context-aware multi-objective resource allocation in mobile cloud

• A resource allocation method to minimize time and energy of tasks in mobile cloud is proposed.
• A two-stage approach using NSGA-II, entropy and TOPSIS methods is employed.
• A context-aware Offloading Middleware for Mobile Cloud is developed to manage offloading.
• A virtual credit based incentive mechanism is used to motivate users to cooperate in offloading.
• The proposed method appropriately manages the trade-off between time and energy.

Mobile Cloud Computing (MCC) augments capabilities of mobile devices by offloading applications to cloud. Resource allocation is one of the most challenging issues in MCC which is investigated in this paper considering neighboring mobile devices as service providers. The objective of the resource allocation is to select service providers minimizing the completion time of the offloading along maximizing lifetime of mobile devices satisfying deadline constraint. The paper proposes a two-stage approach to solve the problem: first, Non-dominated Sorting Genetic Algorithm II (NSGA-II) is applied to obtain the Pareto solution set; second, entropy weight and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method are employed to specify the best compromise solution. Furthermore, a context-aware offloading middleware is developed to collect contextual information and handle offloading process. Moreover, to stimulate selfish users, a virtual credit based incentive mechanism is exploited in offloading decision. The experimental results demonstrate the ability of the proposed resource allocation approach to manage the trade-off between time and energy comparing to traditional algorithms.

Figure optionsDownload as PowerPoint slide