ADORN: Adaptive Drift handling for Open RAN using Reinforcement Learning

Source

Source name: arXiv
Source kind: paper
Authors / organization: Ashit Kumar Subudhi, Bhargav Chirumamilla, Shubham Vaishnav, Mduduzi C. Hlophe, Praveen Kumar Donta, Andrea Fumagalli, Venkateswarlu Gudepu, Koteswararao Kondepu
Venue: arXiv: cs.NI
Published: 2026-07-09
Collected: 2026-07-10
URL: http://arxiv.org/abs/2607.08443v1
PDF: https://arxiv.org/pdf/2607.08443v1
DOI: UNKNOWN

Plain-Language Brief

The paper proposes a Q-learning based adaptive retraining approach for Open Radio Access Networks (O-RAN) using Reinforcement Learning (RL). The goal is to balance forecasting accuracy and retraining cost, which can help reduce computational cost and prevent violations of Service Level Agreements (SLAs). The method uses a multi-expert Long Short-Term Memory (LSTM) ensemble to mitigate catastrophic forgetting and improve robustness.

What the Document Says

There's a problem of drift in Open Radio Access Networks (O-RAN) that degrades the performance of AI/ML models.
Traditional retraining approaches maintain forecasting accuracy but can incur high computational cost and potentially violate Service Level Agreements (SLAs).
The paper proposes a Q-learning-based adaptive retraining approach to balance forecasting accuracy and retraining cost.
The approach formulates the retraining decision as a Markov Decision Process (MDP) using an RL agent that learns a policy.
A multi-expert Long Short-Term Memory (LSTM) ensemble is used to mitigate catastrophic forgetting and improve robustness across diverse traffic conditions.
Experimental results show the proposed approach reduces retraining overhead compared to greedy and random baselines, while maintaining system performance within predefined limits.

Key Concepts Mentioned

Open Radio Access Networks (O-RAN)
Artificial Intelligence/Machine Learning (AI/ML)
Drift
Retraining
Service Level Agreements (SLAs)
Q-learning
Markov Decision Process (MDP)
Reinforcement Learning (RL)
Long Short-Term Memory (LSTM) ensemble
catastrophic forgetting
robustness

Claims Made by the Document

The proposed Q-learning based adaptive retraining approach can reduce retraining overhead and maintain system performance within predefined limits.

Evidence Used

Experimental results show the proposed approach reduces retraining overhead compared to greedy and random baselines, while maintaining system performance within predefined limits.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Dynamic traffic variations in Open Radio Access Networks (O-RAN) lead to drift, which degrades the performance of Artificial Intelligence/Machine Learning (AI/ML) models. Traditional retraining approaches maintain forecasting accuracy but incur high computational cost and may lead to violations of Service Level Agreements (SLAs). This work proposes a Q-learning-based adaptive retraining approach that formulates the retraining decision as a Markov Decision Process (MDP), where a Reinforcement Learning (RL) agent learns a policy that balances forecasting accuracy and retraining cost. The proposed approach incorporates a multi-expert Long Short-Term Memory (LSTM) ensemble to mitigate catastrophic forgetting and improve robustness across diverse traffic conditions. Experimental results show that the proposed approach effectively reduces retraining overhead compared to greedy and random baselines, while maintaining system performance within predefined limits.