Next Article in Journal
The Optimal Price Ratio of Typical Energy Sources in Beijing Based on the Computable General Equilibrium Model
Next Article in Special Issue
Valuation of Wind Energy Projects: A Real Options Approach
Previous Article in Journal
Battery Management System—Balancing Modularization Based on a Single Switched Capacitor and Bi-Directional DC/DC Converter with the Auxiliary Battery
Previous Article in Special Issue
Enabling Privacy in Vehicle-to-Grid Interactions for Battery Recharging
Energies 2014, 7(5), 2938-2960; doi:10.3390/en7052938
Article

Autoregressive with Exogenous Variables and Neural Network Short-Term Load Forecast Models for Residential Low Voltage Distribution Networks

,
*  and
Griffith School of Engineering, Griffith University, Gold Coast Campus, Southport Qld 4222, Australia
* Author to whom correspondence should be addressed.
Received: 21 December 2013 / Revised: 19 March 2014 / Accepted: 15 April 2014 / Published: 30 April 2014
(This article belongs to the Special Issue Smart Grids: The Electrical Power Network and Communication System)
View Full-Text   |   Download PDF [2077 KB, 17 March 2015; original version 17 March 2015]   |   Browse Figures

Abstract

This paper set out to identify the significant variables which affect residential low voltage (LV) network demand and develop next day total energy use (NDTEU) and next day peak demand (NDPD) forecast models for each phase. The models were developed using both autoregressive integrated moving average with exogenous variables (ARIMAX) and neural network (NN) techniques. The data used for this research was collected from a LV transformer serving 128 residential customers. It was observed that temperature accounted for half of the residential LV network demand. The inclusion of the double exponential smoothing algorithm, autoregressive terms, relative humidity and day of the week dummy variables increased model accuracy. In terms of R2 and for each modelling technique and phase, NDTEU hindcast accuracy ranged from 0.77 to 0.87 and forecast accuracy ranged from 0.74 to 0.84. NDPD hindcast accuracy ranged from 0.68 to 0.74 and forecast accuracy ranged from 0.56 to 0.67. The NDTEU models were more accurate than the NDPD models due to the peak demand time series being more variable in nature. The NN models had slight accuracy gains over the ARIMAX models. A hybrid model was developed which combined the best traits of the ARIMAX and NN techniques, resulting in improved hindcast and forecast fits across the all three phases.
Keywords: forecast; electricity demand; residential; time series; autoregressive integrated moving average (ARIMA); ARIMA with exogenous variables (ARIMAX); neural network (NN) forecast; electricity demand; residential; time series; autoregressive integrated moving average (ARIMA); ARIMA with exogenous variables (ARIMAX); neural network (NN)
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
EndNote
MDPI and ACS Style

Bennett, C.; Stewart, R.A.; Lu, J. Autoregressive with Exogenous Variables and Neural Network Short-Term Load Forecast Models for Residential Low Voltage Distribution Networks. Energies 2014, 7, 2938-2960.

View more citation formats

Related Articles

Article Metrics

For more information on the journal, click here

Comments

Cited By

[Return to top]
Energies EISSN 1996-1073 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert