IEEE

Carbon-Aware Multi-Energy Load Forecasting: A Hybrid KAN-Autoformer Approach with Adaptive Feature Extraction and Intelligent Residual Correction

Abstract: The transition towards carbon-neutral integrated energy systems necessitates not only accurate multi-energy load forecasting for operational economics but also precise prediction of ...
GitHub

Multi-Signal Demand Forecasting System (Temporal Fusion Transformer)

2.2.2 signals.py Fetch weather, Google Trends, and FinBERT news sentiment; merge into the sales frame (all with offline fallbacks). 2.2.3 features.py Lag (7/14/28), rolling mean/std, calendar, promo, ...
GitHub

0051-OC-Multithreading-Schematics-load.patch

Optimized mindustry server&client with more API&QoL (v154+, compatible with vanilla) - mlfc666/MindustryX-Arm64 ...
IEEE

Multi-Appliance Adaptive Non-Intrusive Load Monitoring System with Encoder-Decoder Architecture and Self-Adaptive Loss Weighting

Abstract: Non-Intrusive Load Monitoring (NILM) refers to as the technology of identifying the operation status and power consumption of individual electrical devices (typically household appliances) ...