Genetic Algorithm-Driven Feature Selection for Total Harmonic Distortion Prediction Using Hybrid Machine Learning
Bibliographic record
Abstract
Due to the high penetration of renewable energies and the implementation of electronic switches alongside the load non-linearity, Total Harmonic Distortion (THD) has raised concern among engineers due to its direct impact on grid stability. Machine learning has been used to gain the capability of prediction to the system. However, dealing with a high number of features could introduce a significant computational burden and potential model overfitting. This paper introduces a novel Genetic Algorithm (GA) – driven feature selection framework for the THD prediction that effectively can mitigate the mentioned challenges. The approach is to combine evolutionary optimization for feature selection with focusing on a hybrid Autoregressive Integrated Moving Average (ARIMA) and Extreme Gradient Boosting (XGBoost) model, that leverages ARIMA’s capability for capturing the temporal trends and linear dependencies alongside XGBoost’s advantageous feature for modelling complex non-linear interactions and residual patterns. For the model performance validation, a comparative analysis against Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE) has been done, over real-time power system data, to demonstrate the privilege of the proposed approach, Mean Absolute Error (MAE) of 0.1179 and a Root Mean Squared Error (RMSE) of 0.1489. In comparison, PCA alone resulted in an MAE of 0.1852 and an RMSE of 0.2103, while RFE yielded an MAE of 0.1958 and an RMSE of 0.2241., alongside reducing computational time by approximately 20%. The results confirm an effective solution for accurate THD prediction, enabling proactive power quality management in increasingly complex grid environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".