Enhanced spatio-temporal electric load forecasts using less data with active deep learning
This work provides a solution for electric utilities to reduce data collection costs and accelerate grid decarbonization by improving the efficiency of smart meter deployment and data acquisition for load forecasting.
This paper addresses the challenge of high data demand and associated costs for training deep learning models in spatio-temporal electric load forecasting. The authors demonstrate that by using active learning to strategically collect data, electric utilities can achieve more accurate load predictions with approximately half the data compared to passive learning.
An effective way to oppose global warming and mitigate climate change is to electrify our energy sectors and supply their electric power from renewable wind and solar. Spatio-temporal predictions of electric load become increasingly important for planning this transition, while deep learning prediction models provide increasingly accurate predictions for it. The data used for training deep learning models, however, is usually collected at random using a passive learning approach. This naturally results in a large demand for data and associated costs for sensors like smart meters, posing a large barrier for electric utilities in decarbonizing their grids. Here, we test active learning where we leverage additional computation for collecting a more informative subset of data. We show how electric utilities can apply active learning to better distribute smart meters and collect their data for more accurate predictions of load with about half the data compared to when applying passive learning.