Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Transformer-Based Wireless Traffic Prediction and Network Optimization in O-RAN

Md Arafat Habib, Pedro Enrique Iturria-Rivera, Yigit Ozcan, Medhat Elsayed, Majid Bavand, Raimundus Gaigalas, Melike Erol-Kantarci

Abstract

This paper introduces an innovative method for predicting wireless network traffic in concise temporal intervals for Open Radio Access Networks (O-RAN) using a transformer architecture, which is the machine learning model behind generative AI tools. Depending on the anticipated traffic, the system either launches a reinforcement learning-based traffic steering xApp or a cell sleeping rApp to enhance performance metrics like throughput or energy efficiency. Our simulation results demonstrate that the proposed traffic prediction-based network optimization mechanism matches the performance of standalone RAN applications (rApps/ xApps) that are always on during the whole simulation time while offering on-demand activation. This feature is particularly advantageous during instances of abrupt fluctuations in traffic volume. Rather than persistently operating specific applications irrespective of the actual incoming traffic conditions, the proposed prediction-based method increases the average energy efficiency by 39.7% compared to the "Always on Traffic Steering xApp" and achieves 10.1% increase in throughput compared to the "Always on Cell Sleeping rApp". The simulation has been conducted over 24 hours, emulating a whole day traffic pattern for a dense urban area.

Transformer-Based Wireless Traffic Prediction and Network Optimization in O-RAN

Abstract

This paper introduces an innovative method for predicting wireless network traffic in concise temporal intervals for Open Radio Access Networks (O-RAN) using a transformer architecture, which is the machine learning model behind generative AI tools. Depending on the anticipated traffic, the system either launches a reinforcement learning-based traffic steering xApp or a cell sleeping rApp to enhance performance metrics like throughput or energy efficiency. Our simulation results demonstrate that the proposed traffic prediction-based network optimization mechanism matches the performance of standalone RAN applications (rApps/ xApps) that are always on during the whole simulation time while offering on-demand activation. This feature is particularly advantageous during instances of abrupt fluctuations in traffic volume. Rather than persistently operating specific applications irrespective of the actual incoming traffic conditions, the proposed prediction-based method increases the average energy efficiency by 39.7% compared to the "Always on Traffic Steering xApp" and achieves 10.1% increase in throughput compared to the "Always on Cell Sleeping rApp". The simulation has been conducted over 24 hours, emulating a whole day traffic pattern for a dense urban area.
Paper Structure (15 sections, 5 equations, 6 figures, 1 table)

This paper contains 15 sections, 5 equations, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. System Model
  4. System Model
  5. Problem formulation
  6. Proposed Transformer-based Traffic Prediction and Performance Optimization Scheme
  7. Data Aggregation and Pre-processing
  8. Traffic Prediction xApp
  9. Traffic Steering and Cell Sleeping Apps
  10. Network Optimization Using Autoformer and RL-based RIC applications
  11. Baseline Algorithms
  12. Performance Evaluation
  13. Simulation setup
  14. Simulation results
  15. Conclusions

Figures (6)

  • Figure 1: O-RAN based network stack with macro cell and small cells based deployment.
  • Figure 2: Traffic prediction and network optimization based on the proposed method.
  • Figure 3: Residual plots of the proposed method and the baselines.
  • Figure 4: Threshold value selection for initiating cell sleeping rApp.
  • Figure 5: Performance comparison in terms of throughput.
  • ...and 1 more figures