Application of Deep Learning Long Short-Term Memory in Energy Demand Forecasting

TL;DR

This paper demonstrates that LSTM neural networks can accurately forecast 3-day ahead energy demand using smart meter data, with a novel approach to incorporate time as a feature to improve performance.

Contribution

It introduces a method to quantify time as a feature in LSTM models for energy demand forecasting, enhancing prediction accuracy.

Findings

3-day ahead demand forecast with 3.15% MAPE

Time quantification improves model performance

LSTM effectively models energy demand patterns

Abstract

The smart metering infrastructure has changed how electricity is measured in both residential and industrial application. The large amount of data collected by smart meter per day provides a huge potential for analytics to support the operation of a smart grid, an example of which is energy demand forecasting. Short term energy forecasting can be used by utilities to assess if any forecasted peak energy demand would have an adverse effect on the power system transmission and distribution infrastructure. It can also help in load scheduling and demand side management. Many techniques have been proposed to forecast time series including Support Vector Machine, Artificial Neural Network and Deep Learning. In this work we use Long Short Term Memory architecture to forecast 3-day ahead energy demand across each month in the year. The results show that 3-day ahead demand can be accurately forecasted with a Mean Absolute Percentage Error of 3.15%. In addition to that, the paper proposes way to quantify the time as a feature to be used in the training phase which is shown to affect the network performance.