Recurrent Transform Learning

TL;DR

This paper introduces recurrent transform learning (RTL), a novel approach for building demand forecasting that outperforms existing methods by using unsupervised feature extraction and integrated regression models.

Contribution

The paper proposes a new recurrent transform learning framework with two versions, enhancing demand forecasting accuracy over state-of-the-art methods.

Findings

RTL outperforms LSTM, echo state network, and sparse coding regression.

Both RTL and R2TL achieve superior forecasting accuracy.

Experiments on three datasets validate the effectiveness of the proposed methods.

Abstract

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL). Two versions are proposed. The first one (RTL) is unsupervised; this is used as a feature extraction tool that is further fed into a regression model. The second formulation embeds regression into the RTL framework leading to regressing recurrent transform learning (R2TL). Forecasting experiments have been carried out on three popular publicly available datasets. Both of our proposed techniques yield results superior to the state-of-the-art like long short term memory network, echo state network and sparse coding regression.