Abstract
Buildings are considered to be one of the world's largest consumers of energy. The productive utilization of energy will spare the accessible energy assets for the following ages. In this paper, we analyze and predict the domestic electric power consumption of a single residential building, implementing deep learning approach (LSTM and CNN). In these models, a novel feature is proposed, the “best N window size” that will focus on identifying the reliable time period in the past data, which yields an optimal prediction model for domestic energy consumption known as deep learning recurrent neural network prediction system with improved sliding window algorithm. The proposed prediction system is tuned to achieve high accuracy based on various hyperparameters. This work performs a comparative study of different variations of the deep learning model and records the best Root Mean Square Error value compared to other learning models for the benchmark energy consumption dataset.
Highlights
Today’s modern world faces steady acceleration in the development of technology, population, and economic growth, which dramatically increases energy consumption
As per the International Energy Agency (IEA) report, more than 30% of the global energy is consumed in buildings, and nearly one-third of carbon dioxide (CO2) emitted by the building accounts for a significant part of the total CO2 emissions [1]
Various experimental results are discussed for all variations of models implemented using Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN) enhanced with a sliding window approach
Summary
Today’s modern world faces steady acceleration in the development of technology, population, and economic growth, which dramatically increases energy consumption. Ough being a good consumer of energy, buildings are connected with a significant proportion of energy waste as well [3], and this dissipated form of energy shows an alarming situation to sustainability Such frightening circumstances address the concerns of growing energy demand, development of urbanization, and pollutant emissions, the increasing need of new smart sustainable energy resources. It is necessary to emerge with solutions that deal with building energy efficiently as it is extremely crucial With this pattern, accurate predictions of future electric power consumption have become a fundamental advance in the computerized administration of power systems. E proposed work introduces an LSTM and CNN model with an enhanced sliding window algorithm Both deep learning techniques are established on a benchmark electricity consumption dataset for an individual residential building with daily time resolutions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
