Energy Efficient Smart Buildings: LSTM Neural Networks for Time Series Prediction

İdil Sülo, Seref Recep Keskin, Gülüstan Dogan & Theodore Brown

Abstract

Considering the human resources, time and energy expenditures in the modern technology of today, efficient use of resources provides significant advantages in many ways. As a result of this, the role of intelligent building systems, which are part of the campuses and cities, is becoming much more important day by day. The purpose of these building systems is to ensure that the resources and systems are efficiently used in order to provide comfortable living conditions to the people. For this purpose, in this paper, we investigate the ways to improve the efficiency of the energy used by these buildings. In this study, we use the Long Short Term Memory (LSTM) neural network model to analyze the energy expenditures of the buildings that reside in the campuses of the City University of New York (CUNY). With the help of the neural network model that had been developed, we aim to predict the energy consumption values of these buildings in order to obtain energy efficient smart buildings.

International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML), 2019.