Deep Learning for Forecasting the Energy Consumption in Public Buildings

TL;DR

This paper introduces an LSTM-based approach to accurately forecast energy consumption in public buildings using historical data, demonstrating its effectiveness on real-world measurements from the UK National Archives.

Contribution

The paper presents a novel LSTM-based method specifically designed for energy consumption forecasting in public buildings, including a comprehensive data processing and validation framework.

Findings

The method achieved low MAE and MAPE on the dataset.

LSTM effectively captures temporal patterns in energy data.

The approach outperforms traditional forecasting methods.

Abstract

In this paper we propose a Long Short-Term Memory Network based method to forecast the energy consumption in public buildings, based on past measurements. Our approach consists of three main steps: data processing step, training and validation step, and finally the forecasting step. We tested our method on a data set consisting of measurements taken every half an hour from the main building of the National Archives of the United Kingdom, in Kew and as evaluation metrics we have used Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE).