Self-supervised contrastive learning is effective for time-series representation learning, but its deployment in industrial environments remains challenging because of spatiotemporal heterogeneity, domain-specific noise, and label scarcity. We study these challenges in the smart-grid domain, a representative cyber-physical system characterized by non-stationary events, missing data, and policy-driven distribution shifts.
We introduce the West China AMI Benchmark (WCA-Bench), a real-world dataset containing 713,700 user-day electricity profiles from 1,950 users and 506 expert-verified structural evolution events, including electric-vehicle access and photovoltaic installation. We further propose Domain-Aware Self-Supervised Contrastive Learning (DA-SSCL), which combines a lightweight PatchMLP encoder, physically grounded augmentations, and a hierarchical instance- and patch-level InfoNCE objective.
DA-SSCL achieves an unsupervised clustering ARI of 0.699, reaches 88.4% classification accuracy with only 10% labeled data, and maintains transferability across the evaluated heterogeneous city districts.
These results provide a practical methodology and a verified benchmark for robust, label-efficient, and transferable time-series representation learning in cyber-physical systems.
Linghao Zhang, Bo-Wei Yang, Xing-Si Ke et al.· Frontiers in Artificial Inte...· 0 citations
Accurate air conditioning (AC) load prediction under extreme weather conditions is critical for power grid stability and energy management. While tree-based ensemble methods such as XGBoost, LightGBM, and Gradient Boosting have become the dominant paradigm in short-term load forecasting, their effectiveness for weather-sensitive AC load prediction—particularly during extreme weather events—remains insufficiently examined. This study presents a systematic comparison of four machine learning models—Support Vector Regression with RBF kernel (SVR-RBF), LightGBM, XGBoost, and Gradient Boosting—for daily AC load estimation conditioned on measured same-day meteorological and calendar features. Based on five years of processed load and weather data from a major city in Southwest China, we construct 31 features and evaluate model performance across four scenarios: normal days, weather-extreme days, high-load P85, and high-load P90. Hyperparameters are selected within the first four years by expanding-window validation, and the fifth year is held out for testing. Our results reveal that SVR-RBF achieves an overall R2 of 0.9772, substantially outperforming LightGBM (0.9091), XGBoost (0.8972), and Gradient Boosting (0.9094); paired moving-block bootstrap intervals for the tree-minus-SVR MAE differences exclude zero. The advantage of SVR-RBF is most pronounced under extreme conditions: on weather-extreme days, SVR-RBF attains R2=0.8316 versus R2=0.39 for the best tree model. This pattern is consistent with the smooth U-shaped temperature–load relationship captured by the RBF kernel. Additional trend-sensitivity analysis shows that annual load growth and target-level extrapolation also explain a substantial part of the tree-model degradation. Furthermore, we quantify the performance limitation of the restricted feature set: while normal-day estimation achieves R2=0.984, high-load P90 days reach R2=0.843. These findings support SVR-RBF as a strong baseline for measured-weather conditional AC load estimation while emphasizing that temporal shift and training-domain coverage must be considered when interpreting model differences. For energy-system applications, the lower errors under high-load and weather-extreme conditions are relevant to peak-demand assessment, reserve planning, and demand-side management.
Chuan Long, Xinting Yang, Yun-Che Su et al.· Energies· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
