A Q-learning based Method for Energy-Efficient Computation Offloading in Mobile Edge Computing

Keyphrases

• Learning-based 100%
• Q-learning 100%
• Mobile Edge Computing 100%
• Energy-efficient Computing 100%
• Computation Offloading 100%
• User Equipment 80%
• Computational Resources 60%
• Resource Allocation 40%
• Energy Consumption 40%
• Optimal Policy 20%
• Resource Assignment 20%
• System Environment 20%
• Heterogeneous Computing 20%
• Computing Paradigm 20%
• Delay Constraint 20%
• Energy Resources 20%
• Multi-user 20%
• Resource Requirements 20%
• System Dynamics 20%
• Optimization Objectives 20%
• Task Execution 20%
• Dynamic Resource Requirement 20%
• Quasi-static 20%
• 5G Networks 20%
• System Status 20%
• Computing Servers 20%
• Mixed Integer Nonlinear Programming 20%
• Offloading Decision 20%
• Reinforcement Learning Approach 20%
• Computational Tasks 20%
• Static System 20%
• Value Iteration 20%
• Joint Optimization 20%
• Time-varying Systems 20%

Computer Science

• Energy Efficient 100%
• Multi-Access Edge Computing 100%
• Computation Offloading 100%
• Efficient Computation 100%
• Energy Consumption 40%
• Resource Requirement 40%
• Resource Allocation 40%
• Reinforcement Learning 20%
• Heterogeneous Computation 20%
• computing paradigm 20%
• Nonlinear Programming 20%
• System Dynamics 20%
• Optimisation Objective 20%
• System Condition 20%
• Delay Constraint 20%
• Baseline Method 20%
• Learning Approach 20%
• Task Execution 20%
• Linear Programming Problem 20%
• 5G Mobile Communication 20%