skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Journal Article · · Information
DOI:https://doi.org/10.3390/info12120499· OSTI ID:1833467
; ; ORCiD logo

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Sponsoring Organization:
USDOE
Grant/Contract Number:
AR0000936
OSTI ID:
1833467
Journal Information:
Information, Journal Name: Information Vol. 12 Journal Issue: 12; ISSN 2078-2489
Publisher:
MDPI AGCopyright Statement
Country of Publication:
Switzerland
Language:
English

References (16)

Forecasting the short-term demand for electricity journal January 2000
Neural network model ensembles for building-level electricity load forecasts journal December 2014
Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings journal January 2016
Design, Analysis, and Hardware Emulation of a Novel Energy Conservation Scheme for Sensor Enhanced FiWi Networks (ECO-SFiWi) journal May 2016
An ensemble learning framework for anomaly detection in building energy consumption journal June 2017
Deep Learning for Daily Peak Load Forecasting–A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping journal January 2019
Energy Forecasting for Event Venues: Big Data and Prediction Accuracy journal January 2016
Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network journal January 2019
Machine learning for estimation of building energy consumption and performance: a review journal October 2018
Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN journal September 2018
Single and Multi-Sequence Deep Learning Models for Short and Medium Term Electric Load Forecasting journal January 2019
Enhanced Deep Networks for Short-Term and Medium-Term Load Forecasting journal January 2019
Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks journal February 2018
Neural networks for short-term load forecasting: a review and evaluation journal January 2001
Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † journal June 2018
Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation journal August 2017

Similar Records

HOTSPOT ENABLED ACCURATE DETERMINATION OF COMMON AREA OCCUPANCY USING NETWORK TOOLS (HEADCOUNT)
Technical Report · Tue Mar 30 00:00:00 EDT 2021 · OSTI ID:1833467
WHISPER: Wireless Home Identification and Sensing Platform for Energy Reduction
Journal Article · Mon Dec 06 00:00:00 EST 2021 · Journal of Sensor and Actuator Networks · OSTI ID:1833467
+8 more
Voltron Compatible Whole Building Root-Fault Detection and Diagnosis
Technical Report · Sat Dec 01 00:00:00 EST 2018 · OSTI ID:1833467

Related Subjects