AnIO: anchored input-output learning for time-series forecasting

Ourania Stentoumi, Paraskevi Nousi, Maria Tzelepi, Anastasios Tefas

Abstract: In this work, the short-term electric load demand forecasting problem is addressed, proposing a method inspired by the use of anchors in object detection methods. Specifically, a method named Anchored Input–Output Learning (AnIO) is proposed. AnIO proposes to define and use an anchor, reformulating the problem into offset prediction instead of actual load value prediction. Additionally, the use of anchor-encoded input features to match the encoded output is proposed. Extensive experiments were conducted, considering different anchors and model architectures on different datasets. Considering the Greek energy market, AnIO improves the performance from 2.914 to 2.251% in terms of MAPE. In conclusion, AnIO method achieves to improve the performance, considering time-series forecasting tasks.