Prediction of office building electricity demand using artificial neural network by splitting the time horizon for different occupancy rates

doi:10.1016/j.egyai.2021.100093

Prediction of office building electricity demand using artificial neural network by splitting the time horizon for different occupancy rates | ResearchHub

Abstract

Due to the impact of occupants’ activities in buildings, the relationship between electricity demand and ambient temperature will show different trends in the long-term and short-term, which show seasonal variation and hourly variation, respectively. This makes it difficult for conventional data fitting methods to accurately predict the long-term and short-term power demand of buildings at the same time. In order to solve this problem, this paper proposes two approaches for fitting and predicting the electricity demand of office buildings. The first proposed approach splits the electricity demand data into fixed time periods, containing working hours and non-working hours, to reduce the impact of occupants’ activities. After finding the most sensitive weather variable to non-working hour electricity demand, the building baseload and occupant activities can be predicted separately. The second proposed approach uses the artificial neural network (ANN) and fuzzy logic techniques to fit the building baseload, peak load, and occupancy rate with multi-variables of weather variables. In this approach, the power demand data is split into a narrower time range as no-occupancy hours, full-occupancy hours, and fuzzy hours between them, in which the occupancy rate is varying depending on the time and weather variables. The proposed approaches are verified by the real data from the University of Glasgow as a case study. The simulation results show that, compared with the traditional ANN method, both proposed approaches have less root-mean-square-error (RMSE) in predicting electricity demand. In addition, the proposed working and non-working hour based regression approach reduces the average RMSE by 35%, while the ANN with fuzzy hours based approach reduces the average RMSE by 42%, comparing with the traditional power demand prediction method. In addition, the second proposed approach can provide more information for building energy management, including the predicted baseload, peak load, and occupancy rate, without requiring additional building parameters.

Open public full text

Rights: ALLOWED · cc-by · Source: journal-auto-sync:external:CROSSREF_ISSN

External reference records

Calibration of building energy models for retrofit analysis under uncertainty

10.1016/j.enbuild.2011.12.029 · 2012

Design and analysis of electrical energy storage demonstration projects on UK distribution networks

10.1016/j.apenergy.2014.09.027 · 2015

Operational supply and demand optimisation of a multi-vector district energy system using artificial neural networks and a genetic algorithm

10.1016/j.apenergy.2018.11.001 · 2019

A review on the prediction of building energy consumption

10.1016/j.rser.2012.02.049 · 2012

Comparative study of data driven methods in building electricity use prediction

10.1016/j.enbuild.2019.04.029 · 2019

An occupancy-based model for building electricity consumption prediction: a case study of three campus buildings in Tianjin

10.1016/j.enbuild.2019.109412 · 2019

Heating and cooling building energy demand evaluation; a simplified model and a modified degree days approach

10.1016/j.apenergy.2014.04.067 · 2014

District heating network demand prediction using a physics-based energy model with a Bayesian approach for parameter calibration

10.3390/en12183408 · 2019

Prediction of optimum heating timing based on artificial neural network by utilizing BEMS data

10.1016/j.jobe.2018.11.012 · 2019

Sensitivity analysis to reduce duplicated features in ANN training for district heat demand prediction

10.1016/j.egyai.2020.100028 · 2020

Load prediction method for heat and electricity demand in buildings for the purpose of planning for mixed energy distribution systems

10.1016/j.enbuild.2007.10.014 · 2008

Unresolved referenced work

2013

A review on applications of ANN and SVM for building electrical energy consumption forecasting

10.1016/j.rser.2014.01.069 · 2014

Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks

10.1016/j.apenergy.2019.02.056 · 2019

A bottom-up stochastic model to predict building occupants’ time-dependent activities

10.1016/j.buildenv.2012.10.021 · 2013

Building-level occupancy data to improve ARIMA-based electricity use forecasts

2010

Genetic algorithm-determined deep feedfor-ward neural network architecture for predicting electricity consumption in real buildings

10.1016/j.egyai.2020.100015 · 2020

Development of a consecutive occupancy estimation framework for improving the energy demand prediction performance of building energy modeling tools

10.3390/en12030433 · 2019

Predictive artificial neural network models to forecast the seasonal hourly electricity consumption for a University campus

10.1016/j.scs.2018.06.019 · 2018

Feasibility study on a novel methodology for short-term real-time energy demand prediction using weather forecasting data

10.1016/j.enbuild.2012.10.041 · 2013

Prediction of building electricity usage using Gaussian process regression

2020

Predicting the energy consumption of residential buildings for regional electricity supply-side and demand-side management

10.1109/access.2019.2901257 · 2019

A review of data-driven building energy consumption prediction studies

10.1016/j.rser.2017.04.095 · 2018

Forecasting electric energy consumption using neural networks

10.1016/0301-4215(95)00116-6 · 1995

Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes

10.1016/j.enbuild.2016.08.081 · 2016

Deep learning versus traditional machine learning methods for aggregated energy demand prediction

2017

Energy demand prediction through novel random neural network predictor for large non-domestic buildings

2017

Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks

10.1016/j.apenergy.2017.12.051 · 2018

Additional external references

No additional external references are available.

Prediction of office building electricity demand using artificial neural network by splitting the time horizon for different occupancy rates

Read manuscript

Read manuscript

Referenced works

Cited by

Read manuscript

External reference records

Additional external references