Data-driven building simulation for thermal and electrical energy demand prediction by using deep machine learning algorithms, RNN and LSTM for energy management

Building energy consumption prediction is becoming increasingly vital for energy management, equipment efficiency improvement, cooperation between building energy and power grid, and so on. However, it is still hard work to obtain accurate prediction results because of the complexity of the building energy behavior and the frequent undulations in the energy demand. In the building energy consumption prediction, the existing historical data are usually used to construct the traditional machine learning models and the deep learning models. This project, will mainly focus on developing a deep learning algorithm using recurrent neural networks and LSTM to have a more efficient and accurate prediction of electrical and thermal demand based on the energy consumption data from buildings. I have been selected to do my thesis in Canada for developing my project by starting a collaboration between DataOptima.it and CIISE in Concordia University.

Faculty Supervisor:

Jia Yuan Yu

Student:

Partner:

Politecnico di Milano

Discipline:

Engineering

Sector:

Education

University:

Concordia University

Program: