Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

Martha Arbayani Zaidan,Alireza Aslani,Naser Hossein Motlagh,Seyed Azad Nabavi,Behnam Zakeri

doi:10.1109/access.2021.3110960

Abstract

Buildings are responsible for 33% of final energy consumption, and 40% of direct and indirect CO2 emissions globally. While energy consumption is steadily rising globally, managing building energy utilization by on-site renewable energy generation can help responding to this demand. This paper proposes a deep learning method based on a discrete wavelet transformation and long short-term memory method (DWT-LSTM) and a scheduling framework for the integrated modelling and management of energy demand and supply for buildings. This method analyzes several factors including electricity price, uncertainty in climatic factors, availability of renewable energy sources (wind and solar), energy consumption patterns in buildings, and the non-linear relationships between these parameters on hourly, daily, weekly and monthly intervals. The method enables monitoring and controlling renewable energy generation, the share of energy imports from the grid, employment of saving strategy based on the user priority list, and energy storage management to minimize the reliance on the grid and electricity cost, especially during the peak hours. The results demonstrate that the proposed method can forecast building energy demand and energy supply with a high level of accuracy, showing a 3.63-8.57% error range in hourly data prediction for one month ahead. The combination of the deep learning forecasting, energy storage, and scheduling algorithm enables reducing annual energy import from the grid by 84%, which offers electricity cost savings by 87%. Finally, two smart active buildings configurations are financially analyzed for the next thirty years. Based on the results, the proposed smart building with solar Photo-Voltaic (PV), wind turbine, inverter, and 40.5 kWh energy storage has a financial breakeven point after 9 years with wind turbine and 8 years without it. This implies that implementing wind turbines in the proposed building is not financially beneficial.

Highlights

The growth of energy consumption in residential and commercial buildings leads to substantial greenhouse gas (GHG) emissions
The Discrete Wavelet Transform (DWT) approach effectively increased the accuracy of the DWTequipped Long Short-Term Memory (LSTM) in comparison with the LSTM model
In this paper, using weather and energy consumption/generation patterns, we developed deep learning models to forecast energy demand and supply for five buildings in Vancouver in British Columbia

Summary

Introduction

The growth of energy consumption in residential and commercial buildings leads to substantial greenhouse gas (GHG) emissions. Building energy accounts for 33% of the world’s energy consumption and 40% of the world’s direct and indirect GHG emissions [1], [2]. Providing reliable and green energy sources improve the building energy supply, which enhances the life quality [2]. Smart active buildings and net-zero energy buildings aim to preserve interior thermal convenience and minimize energy consumption in order to mitigate the building energy consumption, and GHG emission [3], [4]. Smart active building modelling has a pivotal role in improving energy efficiency, Energy Storage (ES) measures and the development of renewable.

Objectives

Methods

Results

Conclusion