Faster and Cheaper Energy Demand Forecasting at ScaleDownload PDF

04 Oct 2022, 08:28 (modified: 08 Nov 2022, 10:33)HITY Workshop NeurIPS 2022Readers: Everyone
Keywords: machine learning lightness, power consumption, forecasting, transformer
TL;DR: We propose an approach to forecast seasonal time series much faster; industrial case with power consumption.
Abstract: Energy demand forecasting is one of the most challenging tasks for grids operators. Many approaches have been suggested over the years to tackle it. Yet, those still remain too expensive to train in terms of both time and computational resources, hindering their adoption as customers behaviors are continuously evolving. We introduce Transplit, a new lightweight transformer-based model, which significantly decreases this cost by exploiting the seasonality property and learning typical days of power demand. We show that Transplit can be run efficiently on CPU and is several hundred times faster than state-of-the-art predictive models, while performing as well.
Supplementary Material: zip
3 Replies