INTELLIGENT MACHINE LEARNING APPROACH FOR ELECTRICITY LOSS ANALYSIS AND FORECASTING IN POWER TRANSMISSION NETWORKS
Keywords:
electricity loss; power transmission networks; machine learning; random forest; cascade model; regression and classification; IQR; adaptive algorithms; energy systems; interpretable artificial intelligenceAbstract
This study presents an intelligent machine learning framework for electricity loss analysis in power transmission networks. The proposed approach combines a two-stage cascade prediction algorithm with an adaptive post-processing mechanism based on interquartile range (IQR) statistics. The regression model estimates electricity losses, while the classification model identifies their causes using the predicted loss value as an additional feature. An adaptive post-processing algorithm ensures consistency with physical constraints and generates interpretable explanations for each prediction. The proposed framework improves prediction accuracy, provides reliability estimation, and enhances model transparency, making it suitable for practical applications in energy systems
References
1. Leo Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
2. Jerome H. Friedman, Trevor Hastie, Robert Tibshirani, The Elements of Statistical Learning, Springer, 2009.
3. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O’Reilly Media, 2019.
4. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
5. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016.
6. Scott Lundberg, Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” NeurIPS, 2017.
7. Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin, “Why Should I Trust You? Explaining the Predictions of Any Classifier,” KDD, 2016.
8. International Energy Agency, World Energy Outlook, 2022.
9. World Bank, “Reducing Technical and Non-Technical Losses in Power Systems,” 2020.
10. IEEE, “IEEE Guide for Electric Power Distribution Reliability Indices,” IEEE Std 1366, 2012.
11. Zhang, Y., Wang, J., and Li, X., “Electricity Loss Analysis Using Machine Learning Techniques,” Energy Reports, vol. 8, pp. 1023–1035, 2022.
12. Wang, H., Chen, Z., and Liu, Y., “Data-Driven Methods for Power Loss Prediction in Smart Grids,” IEEE Access, vol. 8, pp. 124567–124578, 2020.
13. Gholami, A., Shekari, T., and Aminifar, F., “Energy Loss Reduction in Power Systems Using Data Analytics,” Electric Power Systems Research, vol. 189, 2020.
14. Chicco, G., Napoli, R., and Piglione, F., “Distribution System Loss Analysis: A Review,” Electric Power Systems Research, vol. 81, no. 12, pp. 2298–2310, 2011.
15. Mutanen, A., Ruska, M., and Repo, S., “Customer Classification and Load Profiling,” IEEE Transactions on Power Systems, vol. 26, no. 3, pp. 1755–1763, 2011.
16. Ahmad, T., Chen, H., “Short-Term Load Forecasting Using Machine Learning Methods,” Energy, vol. 102, pp. 42–52, 2016.
17. Fan, S., Hyndman, R. J., “Short-Term Load Forecasting Based on Temperature Effects,” Journal of Business & Economic Statistics, vol. 30, no. 3, pp. 456–464, 2012.
18. Box, G. E. P., Cox, D. R., “An Analysis of Transformations,” Journal of the Royal Statistical Society, 1964.
19. Tukey, J. W., Exploratory Data Analysis, Addison-Wesley, 1977.
20. Montgomery, D. C., Introduction to Statistical Quality Control, Wiley, 2019.
