Citation :

Surajit Bhattacherjee, Dipankar Pal, "A Methodical Comparison of Random Forest and Neural Network Models to Forecast Digital Design Behaviour," International Journal of Electronics and Communication Engineering, vol. 13, no. 9, pp. 181-194, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I9P111

Abstract

Predicting design behaviour in digital systems is vital to optimize electronic design automation workflows and help reduce time-to-market for integrated circuits. Traditional System Verilog and UVM-based methods demonstrate functional correctness while lacking predictive insights to performance metrics prior to synthesis, resulting in expensive design iterations when the timing or power constraints are violated. In this paper, we compare Random Forest (RF) and Neural Network (NN) models for predicting digital design behaviour at the pre-synthesis stage by timing, power consumption and resource utilization. The main novelty is in predictive analytics for proactive design optimization with RTL features. The 2 models were trained and tested in 1,000 synthesis runs on various RTL designs. The RF used 200 decision trees with optimized hyperparameters, whereas the NN was based on five layers with dropout regularization. Performance metrics such as Mean Absolute Error, Root Mean Square Error and R² scores were obtained. RF shows accuracy for timing prediction and robustness over noisy inputs, while NN is excellent when modeling intricate non-linear relationships. However, its training time is much longer. Analysis of feature importance demonstrated clock frequency, technology node, etc. with the most influential predictors. The comparisons guide the choice of suitable machine learning methods by analyzing trade-offs between interpretability, computational cost and predictive performance.

Keywords

AI-Driven design verification, Hardware performance prediction, ML-based behavioral analysis, Predictive design analytics, RTL synthesis forecasting.

References

1. Anindita Chattopadhyay and Vijay Kumar Sutrakar, “Machine Learning Framework for Early Power, Performance, and Area Estimation of RTL,” 2025 6^th International Conference on Control, Communication and Computing (ICCC), Thiruvanathapuram, India, pp. 1-6, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
2. “1800-2017 - IEEE Standard for SystemVerilog--Unified Hardware Design, Specification, and Verification Language,” IEEE Std 1800-2017 (Revision of IEEE Std 1800-2012), pp. 1-1315, 2018.
   [CrossRef] [Google Scholar] [Publisher Link]
3. “1800.2-2020 - IEEE Standard for Universal Verification Methodology Language Reference Manual,” IEEE Std 1800.2-2020 (Revision of IEEE Std 1800.2-2017), pp. 1-458, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Guyue Huang et al., “Machine Learning for Electronic Design Automation: A Survey,” ACM Transactions on Design Automation of Electronic Systems, vol. 26, no. 5, pp. 1-46, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Wenji Fang et al., “MasterRTL: A Pre-Synthesis PPA Estimation Framework for Any RTL Design,” 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), San Francisco, CA, USA, 2023. pp. 1-9, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Pagolu Meghana et al., “Analysis of Neural Network Algorithm in Comparison to Multiple Linear Regression and Random Forest Algorithm,” 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), Manama, Bahrain, pp. 437-443, 2024. [CrossRef] [Google Scholar] [Publisher Link]
7. Ignatious K. Pious et al., “Enhancing Prediction Accuracy Through Random Forest in Classification and Regression,” 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG), Chennai - 600077, Tamil Nadu, India, pp. 1-6, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Fahad Shamshad et al., “Transformers in Medical Imaging: A Survey,” Medical Image Analysis, vol. 88, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. João Manoel Herrera Pinheiro et al., “The Impact of Feature Scaling in Machine Learning: Effects on Regression and Classification Tasks,” IEEE Access, vol. 13, pp. 199903-199931, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Martin Rapp et al., “MLCAD: A Survey of Research in Machine Learning for CAD Keynote Paper,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no. 10, pp. 3162-3181, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Leo Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Thomas Rincy N, and Roopam Gupta, “A Survey on Machine Learning Approaches and Its Techniques,” 2020 IEEE International Students' Conference on Electrical,Electronics and Computer Science (SCEECS), Bhopal, India, pp. 1-6, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Tetiana Reznychenko, Evženie Uglickich, and Ivan Nagy, “Accuracy Comparison of Logistic Regression, Random Forest, and Neural Networks Applied to Real MaaS Data,” 2024 Smart City Symposium Prague (SCSP), Prague, Czech Republic, pp. 1-5, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Nikolaos I. Deligiannis et al., “A Reliability Evaluation Flow for Assessing the Impact of Permanent Hardware Faults on Integer Arithmetic Circuits,” IEEE Access, vol. 13, pp. 32177-32196, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, “Deep Learning,” Nature, vol. 521, pp. 436-444, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Kurt Hornik, Maxwell Stinchcombe, and Halbert White, “Multilayer Feedforward Networks are Universal Approximators,” Neural Networks, vol. 2, no. 5, pp. 359-366, 1989.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Sohrab Mirsaeidi et al., “Applications of Machine Learning in Modern Power Systems: A Comprehensive Review,” 2023 3^rd International Conference on New Energy and Power Engineering (ICNEPE), Huzhou, China, pp. 1074-1080, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, Cambridge, MA: MIT Press, 2016.
    [Google Scholar] [Publisher Link]
19. Wenji Fang et al., “A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design and EDA,” ACM Transactions on Design Automation of Electronic Systems, pp. 1-73, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Bernhard Schölkopf and Alexander J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, Cambridge, MA: MIT Press, 2002.
    [Google Scholar] [Publisher Link]
21. Christopher J.C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Tianqi Chen and Carlos Ernesto Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22^nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Jerome H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” The Annals of Statistics, vol. 29, no. 5, pp. 1189-1232, 2001.
    [Google Scholar] [Publisher Link]
24. Ceyu Xu, Chris Kjellqvist, and Lisa Wu Wills, “SNS is not a Synthesizer: A Deep-Learning-based Synthesis Predictor,” Proceedings of the 49^th Annual International Symposium on Computer Architecture, New York, NY, USA, pp. 847-859, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Prianka Sengupta et al., “How Good is Your Verilog RTL Code? A Quick Answer from Machine Learning,” Proceedings of the 41^st IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, USA, no. 89, pp. 1-9, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Wenji Fang et al., “Annotating Slack Directly on Your Verilog: Fine-Grained RTL Timing Evaluation for Early Optimization,” Proceedings of the 61^st ACM/IEEE Design Automation Conference, San Francisco, CA, USA, pp. 1-6, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Daniela Sánchez Lopera et al., “Early RTL Delay Prediction Using Neural Networks,” Microprocessors and Microsystems, vol. 94, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
28. R. Gowrishankar et al., “Intelligent Power Estimation of Digital Circuits using Random Forest and Neural Network Models,” International Journal of Computational Intelligence Systems, vol. 18, pp. 1-33, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Recep Emir et al., “Deep Learning Approach for Modeling the Power Consumption and Delay of Logic Circuits Employing GNRFET Technology,” Electronics, vol. 13, no. 15, pp. 1-14, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Morris J. Dworkin et al., “Advanced Encryption Standard (AES),” National Institute of Standards and Technology, Federal Information Processing Standards, vol. 197, 2001.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Design Compiler User Guide, Synopsys Inc, Mountain View, CA, USA, 2023.
    [Google Scholar] [Publisher Link]
32. Adam Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” Proceeding 33^rd Conference Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada, pp. 8024-8035, 2019.
    [Google Scholar] [Publisher Link]
33. Spyros Makridakis, “Accuracy Measures: Theoretical and Practical Concerns,” International Journal of Forecasting, vol. 9, no. 4, pp. 527-529, 1993.
    [CrossRef] [Google Scholar] [Publisher Link]