Integrating AI into Mobile Cloud Computing Task Offloading

Abstract

This thesis explores the application of Artificial Intelligence (AI) to task offloading in Mobile Cloud Computing (MCC) environments. The study addresses the challenge of efficiently allocating computational tasks among local devices, edge servers, and cloud resources while minimizing execution delay and energy consumption. To achieve this objective, the offloading problem is formulated as a Reinforcement Learning (RL) task, and two Deep Reinforcement Learning (DRL) algorithms, Deep Q-Network (DQN) and Double Deep Q-Network (DDQN), are employed to learn adaptive offloading policies based on real-time system conditions. A closed-loop intelligent framework is proposed, implemented in Python, and evaluated through simulation experiments. The results demonstrate that the proposed DRL-based approach effectively improves task allocation decisions, reduces latency and energy consumption, and achieves stable convergence during training. These findings highlight the potential of AI-driven, context-aware offloading strategies for enhancing the performance and efficiency of next-generation MCC systems.