Abstract
Dynamic traffic variations in Open Radio Access Networks (O-RAN) lead to drift, degrading the performance of Artificial Intelligence/Machine Learning (AI/ML) models. Traditional retraining approaches maintain forecasting accuracy but incur high computational costs 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.
Blogger's Review: The ADORN method proposed in this paper optimizes the retraining process for O-RAN using Q-learning, significantly reducing computational overhead while ensuring stable system performance. This research offers new insights for the intelligent evolution of future wireless networks, particularly in enhancing adaptive capabilities in high-dynamic environments.