Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Intelligent Task Offloading: Advanced MEC Task Offloading and Resource Management in 5G Networks

Alireza Ebrahimi, Fatemeh Afghah

TL;DR

The paper tackles intelligent task offloading and joint resource management in 5G MEC to support URLLC and mMTC by formulating the problem as an MDP and solving it with Proximal Policy Optimization (PPO). It embeds SLA-aware latency constraints for URLLC and energy minimization for mMTC into two reward functions, guiding the agent to make per-task offloading and resource allocation decisions within an Open RAN (O-RAN) MEC setup. The approach integrates observations of remaining resources, channel conditions, and per-task requirements, training a neural policy that outperforms baselines including DQN and sequential/fair allocations in simulated urban networks. Simulation results show PPO achieving improved QoS, notably lower processing times for URLLC tasks and reduced energy consumption for mMTC devices, validating the method’s slice-aware adaptability and practical viability for 5G deployments.

Abstract

5G technology enhances industries with high-speed, reliable, low-latency communication, revolutionizing mobile broadband and supporting massive IoT connectivity. With the increasing complexity of applications on User Equipment (UE), offloading resource-intensive tasks to robust servers is essential for improving latency and speed. The 3GPP's Multi-access Edge Computing (MEC) framework addresses this challenge by processing tasks closer to the user, highlighting the need for an intelligent controller to optimize task offloading and resource allocation. This paper introduces a novel methodology to efficiently allocate both communication and computational resources among individual UEs. Our approach integrates two critical 5G service imperatives: Ultra-Reliable Low Latency Communication (URLLC) and Massive Machine Type Communication (mMTC), embedding them into the decision-making framework. Central to this approach is the utilization of Proximal Policy Optimization, providing a robust and efficient solution to the challenges posed by the evolving landscape of 5G technology. The proposed model is evaluated in a simulated 5G MEC environment. The model significantly reduces processing time by 4% for URLLC users under strict latency constraints and decreases power consumption by 26% for mMTC users, compared to existing baseline models based on the reported simulation results. These improvements showcase the model's adaptability and superior performance in meeting diverse QoS requirements in 5G networks.

Intelligent Task Offloading: Advanced MEC Task Offloading and Resource Management in 5G Networks

TL;DR

The paper tackles intelligent task offloading and joint resource management in 5G MEC to support URLLC and mMTC by formulating the problem as an MDP and solving it with Proximal Policy Optimization (PPO). It embeds SLA-aware latency constraints for URLLC and energy minimization for mMTC into two reward functions, guiding the agent to make per-task offloading and resource allocation decisions within an Open RAN (O-RAN) MEC setup. The approach integrates observations of remaining resources, channel conditions, and per-task requirements, training a neural policy that outperforms baselines including DQN and sequential/fair allocations in simulated urban networks. Simulation results show PPO achieving improved QoS, notably lower processing times for URLLC tasks and reduced energy consumption for mMTC devices, validating the method’s slice-aware adaptability and practical viability for 5G deployments.

Abstract

5G technology enhances industries with high-speed, reliable, low-latency communication, revolutionizing mobile broadband and supporting massive IoT connectivity. With the increasing complexity of applications on User Equipment (UE), offloading resource-intensive tasks to robust servers is essential for improving latency and speed. The 3GPP's Multi-access Edge Computing (MEC) framework addresses this challenge by processing tasks closer to the user, highlighting the need for an intelligent controller to optimize task offloading and resource allocation. This paper introduces a novel methodology to efficiently allocate both communication and computational resources among individual UEs. Our approach integrates two critical 5G service imperatives: Ultra-Reliable Low Latency Communication (URLLC) and Massive Machine Type Communication (mMTC), embedding them into the decision-making framework. Central to this approach is the utilization of Proximal Policy Optimization, providing a robust and efficient solution to the challenges posed by the evolving landscape of 5G technology. The proposed model is evaluated in a simulated 5G MEC environment. The model significantly reduces processing time by 4% for URLLC users under strict latency constraints and decreases power consumption by 26% for mMTC users, compared to existing baseline models based on the reported simulation results. These improvements showcase the model's adaptability and superior performance in meeting diverse QoS requirements in 5G networks.
Paper Structure (14 sections, 13 equations, 3 figures, 4 tables)

This paper contains 14 sections, 13 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Task Offloading in Edge
  4. Resource Block Allocation in 5G
  5. Edge Computing in 5G
  6. System Model
  7. Wireless Communication
  8. Computational Resources
  9. Energy Consumption
  10. Proposed Method and Optimization
  11. URLLC Reward Function
  12. mMTC Reward Function
  13. Simulation Results
  14. Conclusion

Figures (3)

  • Figure 1: System Model
  • Figure 2: Simulation results illustrating the variation in performance metrics with varying numbers of URLLC UEs, alongside 30 mMTC UEs, for RL agents compared to sequential and fair assignments. (a) Percentage of total processing time as the number of URLLC UEs increases. (b) Percentage of energy consumption by mMTC UEs as the number of URLLC UEs increases. (c) Percentage of total processing time for URLLC UEs.
  • Figure 3: Simulation results depicting the variation in performance metrics with varying numbers of mMTC UEs, alongside 10 URLLC UEs compared to sequential assignment and fair assignment. (a) Percentage of total processing time as the number of mMTC UEs increases. (b) Percentage of energy consumption by mMTC UEs. (c) Percentage of total processing time for URLLC UEs as the number of mMTC UEs increases