Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mean Age of Information in Partial Offloading Mobile Edge Computing Networks

Ying Dong, Hang Xiao, Haonan Hu, Jiliang Zhang, Qianbin Chen, Jie Zhang

TL;DR

By jointly optimising the COR and TGR, the partial offloading scheme outperforms the local and remote computing schemes in terms of the MAoI, which can be improved by up to 51% and 61%, respectively, which encourages the MEC networks to adopt the partial offloading scheme to improve the MAoI performance.

Abstract

The age of information (AoI) performance analysis is essential for evaluating the information freshness in the large-scale mobile edge computing (MEC) networks. This work proposes the earliest analysis of the mean AoI (MAoI) performance of large-scale partial offloading MEC networks. Firstly, we derive and validate the closed-form expressions of MAoI by using queueing theory and stochastic geometry. Based on these expressions, we analyse the effects of computing offloading ratio (COR) and task generation rate (TGR) on the MAoI performance and compare the MAoI performance under the local computing, remote computing, and partial offloading schemes. The results show that by jointly optimising the COR and TGR, the partial offloading scheme outperforms the local and remote computing schemes in terms of the MAoI, which can be improved by up to 51% and 61%, respectively. This encourages the MEC networks to adopt the partial offloading scheme to improve the MAoI performance.

Mean Age of Information in Partial Offloading Mobile Edge Computing Networks

TL;DR

By jointly optimising the COR and TGR, the partial offloading scheme outperforms the local and remote computing schemes in terms of the MAoI, which can be improved by up to 51% and 61%, respectively, which encourages the MEC networks to adopt the partial offloading scheme to improve the MAoI performance.

Abstract

The age of information (AoI) performance analysis is essential for evaluating the information freshness in the large-scale mobile edge computing (MEC) networks. This work proposes the earliest analysis of the mean AoI (MAoI) performance of large-scale partial offloading MEC networks. Firstly, we derive and validate the closed-form expressions of MAoI by using queueing theory and stochastic geometry. Based on these expressions, we analyse the effects of computing offloading ratio (COR) and task generation rate (TGR) on the MAoI performance and compare the MAoI performance under the local computing, remote computing, and partial offloading schemes. The results show that by jointly optimising the COR and TGR, the partial offloading scheme outperforms the local and remote computing schemes in terms of the MAoI, which can be improved by up to 51% and 61%, respectively. This encourages the MEC networks to adopt the partial offloading scheme to improve the MAoI performance.
Paper Structure (17 sections, 5 theorems, 51 equations, 7 figures, 1 table)

This paper contains 17 sections, 5 theorems, 51 equations, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Model
  3. Network Model
  4. Computing Offloading Model
  5. Local Computing Scheme
  6. Remote Computing Scheme
  7. Partial Offloading Scheme
  8. Investigated Performance Metrics
  9. Performance Analysis
  10. Successful Transmission Probability
  11. Age of Information Analysis
  12. Numerical results and analysis
  13. Validation
  14. Analysis
  15. Conclusion
  16. ...and 2 more sections

Key Result

Lemma 1

In the large-scale partial offloading MEC networks with the spatial distributions of UEs and BSs following the MCP, the STP $\Theta_{i,j}$ can be expressed by where $\varsigma=\frac{2\pi\tau^{\frac{2}{\alpha}}}{\alpha(1+\epsilon)\sin\left(\frac{2\pi}{\alpha}\right)}$ and ${\bf{E}}_{\frac{\epsilon}{\epsilon-1}}\left( \varsigma \right)=\int_1^\infty \frac{e^{ - \varsigma t}}{t^{\frac{\epsilon}{\ep

Figures (7)

  • Figure 1: The computing offloading model in the large-scale partial offloading MEC network.
  • Figure 2: An example of AoI demonstration under the partial offloading scheme with the FCFS queueing discipline.
  • Figure 3: The simulation and theoretical results of MAoI versus the SIR threshold for the local computing, remote computing, and partial offloading schemes.
  • Figure 5: The relationship between the optimal COR and the number of UEs with the TGR being 0.2 and 0.5 and the SIR threshold being 0 dB and 5 dB.
  • Figure 6: The relationship between the MAoI and the TGR with the COR being 0, 0.3, 0.7, 1 and optimal.
  • ...and 2 more figures

Theorems & Definitions (6)

  • Lemma 1
  • proof
  • Lemma 2
  • Theorem 1
  • Corollary 1
  • Corollary 2