Short-Term Load Forecasting for Smart HomeAppliances with Sequence to Sequence Learning

TL;DR

This paper introduces an LSTM-based sequence-to-sequence model for short-term appliance load forecasting in smart homes, demonstrating superior accuracy over traditional and other neural network methods using real residential data.

Contribution

The paper presents a novel LSTM-based seq2seq approach for appliance load forecasting, outperforming existing methods on real-world residential datasets.

Findings

The proposed model achieves lower prediction errors than VARMA, CNN, and standard LSTM models.

Seq2seq LSTM effectively captures appliance load profiles.

Model outperforms others in most tested scenarios.

Abstract

Appliance-level load forecasting plays a critical role in residential energy management, besides having significant importance for ancillary services performed by the utilities. In this paper, we propose to use an LSTM-based sequence-to-sequence (seq2seq) learning model that can capture the load profiles of appliances. We use a real dataset collected fromfour residential buildings and compare our proposed schemewith three other techniques, namely VARMA, Dilated One Dimensional Convolutional Neural Network, and an LSTM model.The results show that the proposed LSTM-based seq2seq model outperforms other techniques in terms of prediction error in most cases.