Integrating Explainable AI for Energy Efficient Open Radio Access Networks
L. Malakalapalli, V. Gudepu, B. Chirumamilla, S. J. Yadhunandan, K. Kondepu
TL;DR
This paper addresses energy efficiency in Open RAN by integrating eXplainable AI to interpret AI/ML energy-prediction models and reveal how RAN parameters drive power consumption. It employs SHAP and LIME to provide global and local explanations of feature contributions, linking parameters such as airtime, buffer status, and throughput to energy use. Using a real-time O-RAN dataset, it compares Gradient Boosting, Random Forest, and XGBoost, reporting specific MSE results and showing that XAI can uncover actionable energy drivers across UL and DL contexts. The work demonstrates the practical value of XAI in guiding energy-aware RAN designs and sets a path for future integration into O-RAN testbeds and XR-enabled use cases.
Abstract
The Open Radio Access Network (Open RAN) is an emerging idea -- transforming the traditional Radio Access Networks (RAN) that are monolithic and inflexible into more flexible and innovative. By leveraging open standard interfaces, data collection across all RAN layers becomes feasible, paving the way for the development of energy-efficient Open RAN architectures through Artificial Intelligence / Machine Learning (AI/ML). However, the inherent complexity and black-box nature of AI/ML models used for energy consumption prediction pose challenges in interpreting their underlying factors and relationships. This work presents an integration of eXplainable AI (XAI) to understand the key RAN parameters that contribute to energy consumption. Furthermore, the paper delves into the analysis of RAN parameters -- \emph{airtime}, \emph{goodput}, \emph{throughput}, \emph{buffer status report}, \emph{number of resource blocks}, and many others -- identified by XAI techniques, highlighting their significance in energy consumption.