Deep Learning Based Building Load Prediction for Residences of an Academic Institutions

Sula Ntsaluba, Nnamdi Nwulu, Kuselo Ntsaluba

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Effective energy planning has in many instances been identified as a critical operation in order to achieve economic and sustainable building energy usage. Accurate building load prediction is a key factor that can result in energy usage and cost reduction. This paper presents an energy usage analysis for an academic institution over a period of four years. Building load prediction was then considered, where three different deep learning models were implemented in an attempt to identify the model that would perform best at predicting the load demand of a selected building over a 1 year period. The accuracy of the implemented models was evaluated through analysis of the Mean Absolute Percentage Error. The selected models produced values ranging from 0.09 to 0.22, which compare well with results highlighted in other literature studies for similar buildings.

Original languageEnglish
Title of host publicationInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665442312
DOIs
Publication statusPublished - 2021
Event2021 International Conference on Electrical, Computer, and Energy Technologies, ICECET 2021 - Cape Town, South Africa
Duration: 9 Dec 202110 Dec 2021

Publication series

NameInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2021

Conference

Conference2021 International Conference on Electrical, Computer, and Energy Technologies, ICECET 2021
Country/TerritorySouth Africa
CityCape Town
Period9/12/2110/12/21

Keywords

  • building load prediction
  • energy consumption
  • feed forward neural network
  • mean absolute percentage error
  • recurrent neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • General Computer Science
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'Deep Learning Based Building Load Prediction for Residences of an Academic Institutions'. Together they form a unique fingerprint.

Cite this