REVIEW 4 major objections 4 minor 15 references
Integrating Explainable AI for Energy Efficient Open Radio Access Networks
T0 review · 4 major / 4 minor · reviewed 2026-08-16 · deepseek-v4-flash
Pith's one-line read The paper claims XAI reveals airtime, BSR, goodput, and selected airtime as the dominant drivers of RAN energy consumption.
desk verdict A straightforward XAI application to O-RAN energy data with a plausible parameter shortlist, but the paper's top-4 claim is contradicted by its own single-instance figures. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
SHAP (Shapley additive explanations) and LIME (local interpretable model-agnostic explanations), applied to three tree-based energy predictors: gradient boosting, random forest, and XGBoost. SHAP attributes each prediction to features by averaging over feature-order permutations; LIME perturbs input instances locally to approximate the model and reads off contributions. The work uses these attributions, displayed per test instance, to rank which measured RAN parameters (airtime, BSR, goodput, throughput, subframe decoding time, number of resource blocks, and others) push predicted power up or down.
What would settle it
Take the full test set, compute mean absolute SHAP and LIME values for every feature per model and dataset, and sort them; the claim stands only if airtime, buffer status report, goodput, and selected airtime remain in the top four of the aggregated ranking.
Extended reading notes
Core claim
On the paper's own terms, the central discovery is that SHAP and LIME explanations, applied to gradient boosting, random forest, and XGBoost energy predictors, converge on a small set of RAN parameters — airtime, buffer status report, goodput, selected airtime, and number of resource blocks — as the dominant drivers of RAN energy consumption for both uplink-only and combined uplink/downlink data. The analysis concludes that variations in these parameters could impact RAN energy consumption, and that the identified ranking provides a benchmark for designing energy-efficient protocols.
Load-bearing premise
The paper assumes that the single example explanation shown for each model fairly represents which features matter across the whole dataset, without averaging the explanation scores over all test cases.
Editorial extensions
If this is right
- Energy-saving rApps and xApps in the O-RAN intelligent controllers can be steered by the ranked parameters, for example by triggering power-reduction actions when airtime or buffer status rises.
- Operators can prioritize protocol changes that minimize unnecessary airtime, since it appears as the strongest positive driver of predicted power.
- The convergence of SHAP and LIME rankings across three different tree models suggests the identified parameters are not an artifact of one ML algorithm.
- The same XAI pipeline can be rerun on live O-RAN data to track when the energy drivers change with traffic conditions.
Reading between the lines
- The displayed explanations cover one instance per model; a defensible global ranking would aggregate SHAP and LIME values over the full test set, so the paper's top-4 claim is stronger than its current evidence.
- The parameters named as top drivers, such as airtime and selected airtime, are likely correlated with each other, so the individual importance values may split a shared causal effect.
- A direct test of the paper's claim would use the top-ranked parameters as control inputs in an O-RAN testbed and measure whether constraining them cuts measured power.
- If the ranking generalizes, XAI-based energy monitoring could move from post-hoc analysis to closed-loop control within the Near-RT RIC's feedback loop.
Signed reviews
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper applies two model-agnostic explainability methods, SHAP and LIME, to energy-consumption prediction models (Gradient Boosting, Random Forest, and XGBoost) trained on a public O-RAN experimental dataset. It proposes integrating XAI into the O-RAN RIC architecture, reports train/test MSE for the three models on two datasets (DL/UL and UL-only), and, based on individual explanation plots, claims that a small set of RAN parameters—airtime, buffer status report, goodput, and selected airtime—are the top-4 key drivers of RAN energy consumption. The paper then suggests these parameters as targets for energy-efficient RAN design.
Significance. The topic is timely: providing interpretable explanations for energy predictions in Open RAN could support operators and future rApps/xApps. The paper uses a public real-world dataset and applies two standard explainability techniques, which is a sensible and reproducible starting point. If the headline parameter ranking were supported by rigorous aggregation over the test set and by model diagnostics, the work would be a useful empirical benchmark for energy-oriented RAN optimization. As it stands, however, the central ranking claim is not supported by the evidence in the figures, so the scientific contribution is conditional on a substantial re-analysis.
major comments (4)
- [Section IV-B, Figs. 2 and 3] The assertion that "Both LIME and SHAP in all the considered AI/ML models report that (i) airtime; (ii) Average Buffer Status Report (bsr); (iii) Average Goodput (gput) uplink; and (iv) selected airtime are top-4 key parameters" is contradicted by the displayed instances. For LIME with Gradient Boosting in Fig. 2a, the top-4 features are airtime_ul, airtime_dl, thr_ul, and gput_ul, with bsr_ul fifth and selected_airtime absent from the top-10. For LIME with XGBoost in Fig. 2e, gput_ul does not appear in the top-10 and bsr_dl ranks seventh. The SHAP panels described in the text also name different leading features, including dec_time, thr, gput, and turbodec_it. Thus the claimed cross-model and cross-method consistency does not hold even on the single displayed instances, and the central ranking claim is unsupported.
- [Section IV-B, Figs. 2 and 3] The analysis generalizes from one local explanation per model-dataset pair to a global statement about "key parameters" without any aggregation. SHAP and LIME values are computed for a single instance; the feature ranking can vary substantially across instances, especially for tree ensembles. The paper should report aggregated importance, for example mean absolute SHAP values or LIME weights over the full test set, together with a measure of variance (e.g., standard deviation or quantiles across instances), before drawing conclusions about which RAN parameters are globally important.
- [Section IV-A, Tables I and II] The model-performance metrics indicate overfitting, and the lack of model diagnostics weakens the credibility of the subsequent explainability analysis. On the DL/UL dataset, Random Forest has train MSE 0.00897 W versus test MSE 0.06806 W, and XGBoost has 0.01672 W versus 0.07021 W; on the UL dataset Random Forest has 0.0020 W versus 0.0143 W. No hyperparameter values, cross-validation, repeated runs, or error bars are reported, so it is unclear whether the fitted models generalize. Because SHAP and LIME explain these particular fitted models, the explanations inherit any overfitting. The authors should provide tuned models and demonstrate stability (e.g., through cross-validated performance and repeated training runs).
- [Section IV and Section V] The conclusion that "variations in RAN parameters ... could impact the RAN energy consumption" is too weak and generic to be a substantive scientific finding, and the paper does not test the XAI-identified parameters against any baseline or ground truth. The claimed influence of airtime, BSR, goodput, and selected airtime should be validated, for example by retraining the models without those features and measuring the drop in prediction accuracy, or by comparing the XAI rankings with domain-known physical drivers of RAN energy consumption. Without such a step, the reported feature rankings are purely internal descriptions of fitted models and are not established as meaningful RAN energy drivers.
minor comments (4)
- [Throughout] There are several typos and inconsistent terms: "transmission Gain (tx again)" should likely be "transmission gain (txgain)"; the dataset reference [12] contains "Evaluatuin" instead of "Evaluation"; and capitalization of "Goodput" and "BSR" is inconsistent across the text and figures.
- [Figures 2 and 3] The LIME and SHAP plots are difficult to read at publication size; higher-resolution figures, a consistent color legend, and a note explaining which values are shown (e.g., a single instance vs. aggregated) would greatly improve clarity.
- [Section IV-A] The paper does not state the dataset size, number of features, feature normalization, or how the 80/20 train-test split was performed. Adding these details is essential for reproducibility, especially since the analysis relies on feature-level explanations.
- [Section IV-B] The text sometimes claims a feature has a "positive impact" based on a SHAP summary plot without clarifying whether this refers to the global mean absolute SHAP value or to a selected instance; this should be stated explicitly in the figure captions and in the text.
Circularity Check
No significant circularity: the XAI feature-importance analysis is descriptive of fitted models on an external dataset, with no fitted input renamed as a prediction.
full rationale
The paper's derivation chain is an empirical XAI analysis: real-time RAN energy datasets from an external source are used to train Gradient Boosting, Random Forest, and XGBoost models, and SHAP/LIME are then applied to those fitted models to rank feature contributions. There is no equation in which a predicted quantity is defined in terms of the quantity it is claimed to explain, and no parameter is fitted to a subset of data and then reported as an independent prediction. The central claim that RAN parameters 'could impact' energy consumption is an interpretation of model explanations, not a derivation forced by construction. Several prior works cited in the introduction and related-work sections are authored by members of the present group, but those references concern testbed infrastructure, drift handling, and energy measurement tools; they do not supply the SHAP/LIME ranking result, which comes from the external O-RAN dataset and the fitted models. Even if the claimed 'top-4' consistency across models is questionable given the displayed single-instance plots, that is an evidentiary or generalization concern, not a circularity concern. The analysis is therefore self-contained against external benchmarks and warrants a score of 0.
Assumptions & free parameters
free parameters (1)
- ML model hyperparameters (tree count, depth, learning rate) for Gradient Boosting, Random Forest, XGBoost
assumptions (3)
- standard math Shapley value and LIME definitions as implemented by the cited libraries produce faithful model explanations
- domain assumption The public O-RAN dataset [12] is representative of real RAN energy consumption
- ad hoc to paper Local explanations on selected instances generalize to global parameter importance
Cite this review
Pith. "Pith review of Integrating Explainable AI for Energy Efficient Open Radio Access Networks." pith.science (2026). https://pith.science/paper/WBQ6FRB4
@misc{pith2026250418029,
author = {Pith},
title = {Pith review of: Integrating Explainable AI for Energy Efficient Open Radio Access Networks},
year = {2026},
howpublished = {\url{https://pith.science/paper/WBQ6FRB4}},
note = {Machine review of arXiv:2504.18029}
}
read the original 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.
Figures
Reference graph
Works this paper leans on
-
[1]
Edge Computing in Micro Data Centers for Firefighting in Residential Areas of Future Smart Cities,
V . Gudepu, B. Pappu, T. Javvadi, R. Bassoli, F. H. Fitzek, L. Valcarenghi, D. Devi, and K. Kondepu, “Edge Computing in Micro Data Centers for Firefighting in Residential Areas of Future Smart Cities,” in IEEE ICECCME. IEEE, 2022, pp. 1–6
work page 2022
-
[2]
The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations,
C. Freitag, M. Berners-Lee, K. Widdicks, B. Knowles, G. S. Blair, and A. Friday, “The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations,” Patterns, vol. 2, no. 9, 2021
work page 2021
-
[3]
Toward Greener 5G and Beyond Radio Access Networks—A Survey,
L. M. Larsen, H. L. Christiansen, S. Ruepp, and M. S. Berger, “Toward Greener 5G and Beyond Radio Access Networks—A Survey,” IEEE Open Journal of the Communications Society, vol. 4, pp. 768–797, 2023
work page 2023
-
[4]
The Drift Handling Framework for Open Radio Access Networks: An Experimental Evaluation,
V . Gudepu, V . R. Chintapalli, P. Castoldi, L. Valcarenghi, B. R. Tamma, and K. Kondepu, “The Drift Handling Framework for Open Radio Access Networks: An Experimental Evaluation,” Computer Networks , vol. 243, p. 110290, 2024
work page 2024
-
[5]
Demonstrating the Energy Consumption of Radio Access Networks in Container Clouds,
V . Gudepu, R. R. Tella, C. Centofanti, J. Santos, A. Marotta, and K. Kondepu, “Demonstrating the Energy Consumption of Radio Access Networks in Container Clouds,” in NOMS2024, the IEEE/IFIP Network Operations and Management Symposium , 2024
work page 2024
-
[6]
Joint Time and Energy-Optimal Approach to Allocate Task to Actors in Wireless Sensor Actor Networks,
M. Okhovvat, M. T. Kheirabadi, M. R. Okhovvat, and A. Nodehi, “Joint Time and Energy-Optimal Approach to Allocate Task to Actors in Wireless Sensor Actor Networks,” Computer Networks , p. 110018, 2023
work page 2023
-
[7]
EARNEST: Experimental Analysis of RAN Energy with Open-Source Software Tools,
V . Gudepu, B. Chirumamilla, R. R. Tella, A. Bhattacharyya, S. Agarwal, L. Malakalapalli, C. Centofanti, J. Santos, and K. Kondepu, “EARNEST: Experimental Analysis of RAN Energy with Open-Source Software Tools,” in 16th IEEE/ACM COMSNETS . IEEE, 2024, pp. 1148–1153
work page 2024
-
[8]
M. Ilbeigi, M. Ghomeishi, and A. Dehghanbanadaki, “Prediction and Optimization of Energy Consumption in an Office Building Using Artificial Neural Network and a Genetic Algorithm,” Sustainable Cities and Society, vol. 61, p. 102325, 2020
work page 2020
Show all 15 references
-
[9]
Method for evaluation on energy consumption of cloud computing data center based on deep reinforcement learning,
H. Ma and A. Ding, “Method for evaluation on energy consumption of cloud computing data center based on deep reinforcement learning,” Electric Power Systems Research , vol. 208, p. 107899, 2022
2022
-
[10]
Energy consumption prediction by using machine learning for smart building: Case study in Malaysia,
M. K. M. Shapi, N. A. Ramli, and L. J. Awalin, “Energy consumption prediction by using machine learning for smart building: Case study in Malaysia,” Developments in the Built Environment , vol. 5, p. 100037, 2021
2021
-
[11]
Why model why? Assessing the strengths and limitations of LIME,
J. Dieber and S. Kirrane, “Why model why? Assessing the strengths and limitations of LIME,” arXiv preprint arXiv:2012.00093 , 2020
2012 arXiv
-
[12]
O- RAN Experimental Evaluatuin Datasets,
J. X. Salvat Lozano, J. A. Ayala-Romero, L. Zanzi et al. , “O- RAN Experimental Evaluatuin Datasets,” 2022. [Online]. Available: https://dx.doi.org/10.21227/64s5-q431
2022 doi
-
[13]
Stochastic Gradient Boosting,
J. H. Friedman, “Stochastic Gradient Boosting,” Computational statistics & data analysis , vol. 38, no. 4, pp. 367–378, 2002
2002
-
[14]
Random Forests,
L. Breiman, “Random Forests,” Machine learning , vol. 45, pp. 5–32, 2001
2001
-
[15]
XGBoost: A Scalable Tree Boosting System,
T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining , 2016, pp. 785–794
2016
Reviewed August 16, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.