Electricity load forecasting using clustering and ARIMA model for energy management in buildings

Understanding the energy consumption patterns of buildings and investing efforts toward energy load reduction is important for optimizing resources and conserving energy in buildings. In this research, we proposed a forecasting method for the electricity load of university buildings using a hybrid m...

Full description

Saved in:
Bibliographic Details
Published in:Japan architectural review Vol. 3; no. 1; pp. 62 - 76
Main Authors: Nepal, Bishnu, Yamaha, Motoi, Yokoe, Aya, Yamaji, Toshiya
Format: Journal Article
Language:English
Published: Hoboken John Wiley & Sons, Inc 01.01.2020
Wiley
Subjects:
Accuracy
ARIMA model
Artificial intelligence
Autoregressive moving-average models
Buildings
Cluster analysis
Clustering
College campuses
Electricity
Electricity consumption
electricity load forecasting
Electricity pricing
Energy conservation
Energy consumption
Energy management
Forecasting
K‐means algorithm
Machine learning
Methods
Peak load
Reduction
Time series
University buildings
Japan
ISSN:2475-8876, 2475-8876
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Understanding the energy consumption patterns of buildings and investing efforts toward energy load reduction is important for optimizing resources and conserving energy in buildings. In this research, we proposed a forecasting method for the electricity load of university buildings using a hybrid model comprising a clustering technique and the autoregressive integrated moving average (ARIMA) model. The novel approach includes clustering data of an entire year, including the forecasting day using K‐means clustering, and using the result to forecast the electricity peak load of university buildings. The combination of clustering and the ARIMA model has proved to increase the performance of forecasting rather than that using the ARIMA model alone. Forecasting electricity peak load with appreciable accuracy several hours before peak hours can provide the management authorities with sufficient time to design strategies for peak load reduction. This method can also be implemented in the demand response for reducing electricity bills by avoiding electricity usage during the high electricity rate hours. In this research, we proposed a method for forecasting the electricity load of university buildings using a hybrid model of clustering technique and autoregressive integrated moving average (ARIMA) model. The novel approach discussed in this paper includes clustering one whole year data including the forecasting day using K‐means clustering and using the result to forecast the electricity peak load of university buildings. The combination of clustering and ARIMA model has proved to increase the performance of forecasting rather than ARIMA model alone. This method can be used for energy conservation in buildings.
Bibliography:No Funding Information provided.
Funding Information
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2475-8876
2475-8876
DOI:10.1002/2475-8876.12135