A Hybrid AI-ML Framework for Predictive Maintenance and Load Forecasting in Smart Grid Infrastructures
Bibliographic record
Abstract
The transformation of traditional power systems into intelligent smart grids necessitates advanced data-driven solutions for operational reliability and energy efficiency. This research presents a hybrid artificial intelligence and machine learning framework that integrates Convolutional Neural Networks (CNN) with Random Forest (RF) for predictive maintenance and combines Long Short-Term Memory (LSTM) networks with XGBoost for short- and long-term load forecasting. The proposed architecture utilizes multivariate data from smart meters, sensors, and weather APIs, enabling real-time analysis of equipment health and demand patterns. Experimental results demonstrate that the hybrid CNN-RF model achieves over 94% classification accuracy in fault detection, while the LSTM-XGBoost forecasting model yields a Mean Absolute Percentage Error (MAPE) as low as 2.5%. Comparative evaluations with traditional models such as ARIMA, SVM, and standalone LSTM confirm the superiority of the proposed dual-model strategy. This framework can serve as a modular foundation for intelligent grid automation, maintenance scheduling, and demand-side management in nextgeneration power infrastructures.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".