Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Random forests and artificial neural network for predicting daylight illuminance and energy consumption

Ahmad, Muhammad, Hippolyte, Jean-Laurent, Mourshed, Monjur and Rezgui, Yacine 2017. Random forests and artificial neural network for predicting daylight illuminance and energy consumption. Presented at: Building Simulation 2017: 15th Conference of International Building Performance Simulation Association, San Francisco, 7-9 August 2017. Proceedings of BS2017: 15th Conference of International Building Performance Simulation Association, San Francisco, USA. pp. 1-7.

[img]
Preview
PDF
Download (1MB) | Preview

Abstract

Predicting energy consumption and daylight illuminance plays an important part in building lighting control strategies. The use of simplified or data-driven methods is often preferred where a fast response is needed e.g. as a performance evaluation engine for advanced real-time control and optimization applications. In this paper we developed and then compared the performance of the widely-used Artificial Neural Network (ANN) with Random Forest (RF), a recently developed ensemble-based algorithm. The target application was predicting the hourly energy consumption and daylight illuminance values of a classroom in Cardiff, UK. Overall, RF performed better than ANN for predicting daylight illuminance; with coefficients of determination (R^2) of 0.9881 and 0.9799 respectively. On the energy consumption testing dataset, ANN performed marginally better than RF with R^2 values of 0.9973 and 0.9966 respectively. RF performs internal cross-validation and is relatively easy to tune as it has few tuning parameters. The paper also highlighted possible future research directions.

Item Type: Conference or Workshop Item (Paper)
Date Type: Completion
Status: In Press
Schools: Engineering
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Funders: European Research Council
Last Modified: 04 Jun 2017 09:49
URI: http://orca-mwe.cf.ac.uk/id/eprint/100415

Actions (repository staff only)

Edit Item Edit Item

Full Text Downloads from ORCA for this publication

Top Downloads of this item by Country

Monthly Full Text Downloads of this item

More statistics for this item...