Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AdapShare: An RL-Based Dynamic Spectrum Sharing Solution for O-RAN

Sneihil Gopal, David Griffith, Richard A. Rouil, Chunmei Liu

TL;DR

This work introduces AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs.

Abstract

The Open Radio Access Network (O-RAN) initiative, characterized by open interfaces and AI/ML-capable RAN Intelligent Controller (RIC), facilitates effective spectrum sharing among RANs. In this context, we introduce AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs. By employing RL agents, AdapShare intelligently learns network demand patterns and uses them to allocate resources. We demonstrate the efficacy of AdapShare in the spectrum sharing scenario between LTE and NR networks, incorporating real-world LTE resource usage data and synthetic NR usage data to demonstrate its practical use. We use the average surplus or deficit and fairness index to measure the system's performance in various scenarios. AdapShare outperforms a quasi-static resource allocation scheme based on long-term network demand statistics, particularly when available resources are scarce or exceed the aggregate demand from the networks. Lastly, we present a high-level O-RAN compatible architecture using RL agents, which demonstrates the seamless integration of AdapShare into real-world deployment scenarios.

AdapShare: An RL-Based Dynamic Spectrum Sharing Solution for O-RAN

TL;DR

This work introduces AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs.

Abstract

The Open Radio Access Network (O-RAN) initiative, characterized by open interfaces and AI/ML-capable RAN Intelligent Controller (RIC), facilitates effective spectrum sharing among RANs. In this context, we introduce AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs. By employing RL agents, AdapShare intelligently learns network demand patterns and uses them to allocate resources. We demonstrate the efficacy of AdapShare in the spectrum sharing scenario between LTE and NR networks, incorporating real-world LTE resource usage data and synthetic NR usage data to demonstrate its practical use. We use the average surplus or deficit and fairness index to measure the system's performance in various scenarios. AdapShare outperforms a quasi-static resource allocation scheme based on long-term network demand statistics, particularly when available resources are scarce or exceed the aggregate demand from the networks. Lastly, we present a high-level O-RAN compatible architecture using RL agents, which demonstrates the seamless integration of AdapShare into real-world deployment scenarios.
Paper Structure (12 sections, 4 equations, 4 figures)

This paper contains 12 sections, 4 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. AdapShare: The Proposed Solution
  4. Optimal Resource Allocation
  5. Reinforcement Learning Approach
  6. Methodology
  7. RL Agent Design
  8. Data Collection
  9. Training and Evaluation
  10. Results
  11. Integration with Architecture
  12. Conclusions

Figures (4)

  • Figure 1: (a) Average PRB usage vs. time for , and +, i.e., aggregate, and (b) CDF of average PRB demand for and synthetically generated dataset. Both plots correspond to 1-hour time granularity.
  • Figure 2: Resource demand and allocation, surplus/deficit, and Jain's Fairness Index for $N_r = \{20,100\}$.
  • Figure 3: Performance Comparison between and .
  • Figure 4: High-level structure illustrating the deployment of AdapShare as a rApp within the architecture ref:oran_tr_wg1.