Electric load forecasting for large office building based on radial basis function neural network

Weijie Mai, C. Y. Chung, Ting Wu, Huazhang Huang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

28 Citations (Scopus)

Abstract

The concept of smart grid has enabled many innovative initiatives that focus on boosting building energy efficiency such as intelligent optimal control of building energy systems and demand side management, which require accurate building load prediction. In this study, we present an hourly electric load forecasting model for large commercial office buildings based on radial basis function neural network (RBFNN) using outdoor weather data and historical load data as inputs, which is easy to implement, without tedious trial-and-error parameterizing procedures. Data from a real building under different weather conditions is used to evaluate the performance of the model and promising results are obtained, which demonstrates that the proposed method is able to precisely predict the evolving hourly electric load of the building.

Original languageEnglish
Title of host publication2014 IEEE PES General Meeting / Conference and Exposition
PublisherIEEE Computer Society
EditionOctober
ISBN (Electronic)9781479964154
DOIs
Publication statusPublished - 29 Oct 2014
Event2014 IEEE Power and Energy Society General Meeting - National Harbor, United States
Duration: 27 Jul 201431 Jul 2014

Publication series

NameIEEE Power and Energy Society General Meeting
NumberOctober
Volume2014-October
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Conference

Conference2014 IEEE Power and Energy Society General Meeting
Country/TerritoryUnited States
CityNational Harbor
Period27/07/1431/07/14

Keywords

  • building energy efficiency
  • commercial office buildings
  • demand side management
  • Load forecasting

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Electric load forecasting for large office building based on radial basis function neural network'. Together they form a unique fingerprint.

Cite this