2 papers
eess.SY2026
Smoothing the Ramp, Not the Peak: Scheduling-Induced Power Dynamics of LLM Inference and Their Grid-Scale Consequences
Pan Li, Yize Chen, Xia Miao +1
Large language model (LLM) inference serving is a fast-growing electricity load whose power dynamics remain uncharacterized from a grid-planning perspective. Using real, measured G…
eess.SP2025
Short-Term Load Forecasting for AI-Data Center
Mariam Mughees, Yuzhuo Li, Yize Chen +1
Recent research shows large-scale AI-centric data centers could experience rapid fluctuations in power demand due to varying computation loads, such as sudden spikes from inference…