Short-term residential load forecasting

Impact of calendar effects and forecast granularity

Peteris Lusis, Kaveh Rajab Khalilpour, Lachlan Andrew, Ariel Liebman

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads.

This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better.

The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.
Original languageEnglish
Pages (from-to)654-669
Number of pages16
JournalApplied Energy
Volume205
DOIs
Publication statusPublished - 1 Nov 2017

Keywords

  • Short-term load forecasting
  • Residential load
  • Calendar effects
  • Granularity
  • Distributed generation and storage
  • management
  • Disaggregated load

Cite this

@article{a75236dc94da4ffdb2624b8194e7384d,
title = "Short-term residential load forecasting: Impact of calendar effects and forecast granularity",
abstract = "Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads.This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better.The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.",
keywords = "Short-term load forecasting, Residential load, Calendar effects, Granularity, Distributed generation and storage, management, Disaggregated load",
author = "Peteris Lusis and Khalilpour, {Kaveh Rajab} and Lachlan Andrew and Ariel Liebman",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.apenergy.2017.07.114",
language = "English",
volume = "205",
pages = "654--669",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Elsevier",

}

Short-term residential load forecasting : Impact of calendar effects and forecast granularity. / Lusis, Peteris; Khalilpour, Kaveh Rajab; Andrew, Lachlan; Liebman, Ariel.

In: Applied Energy, Vol. 205, 01.11.2017, p. 654-669.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Short-term residential load forecasting

T2 - Impact of calendar effects and forecast granularity

AU - Lusis, Peteris

AU - Khalilpour, Kaveh Rajab

AU - Andrew, Lachlan

AU - Liebman, Ariel

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads.This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better.The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.

AB - Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads.This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better.The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.

KW - Short-term load forecasting

KW - Residential load

KW - Calendar effects

KW - Granularity

KW - Distributed generation and storage

KW - management

KW - Disaggregated load

UR - http://www.scopus.com/inward/record.url?scp=85029810700&partnerID=8YFLogxK

U2 - 10.1016/j.apenergy.2017.07.114

DO - 10.1016/j.apenergy.2017.07.114

M3 - Article

VL - 205

SP - 654

EP - 669

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -