1 citations · 1 across the 1 of their papers we have counts for
4 papers
Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
Xudong Wang, Guoming Tang, Junyu Xue +3
Non-Intrusive Load Monitoring (NILM) offers a cost-effective method to obtain fine-grained appliance-level energy consumption in smart homes and building applications. However, the…
BandPilot: Toward Performance- and Contention-Aware GPU Dispatching in AI Clusters
Kunming Zhang, Hanlong Liao, Junyu Xue +2
Modern multi-tenant AI clusters are increasingly communication-bound, driven by high-volume and multi-round GPU-to-GPU collective communication. Consequently, the GPU dispatcher's…
CaberNet: Causal Representation Learning for Cross-Domain HVAC Energy Prediction
Kaiyuan Zhai, Jiacheng Cui, Zhehao Zhang +4
Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both cost…
Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
Junyu Xue, Xudong Wang, Xiaoling He +3
Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage, thus enabling more effective energy management. While deep…