Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4915876 | Applied Energy | 2017 | 16 Pages |
Abstract
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.
Related Topics
Physical Sciences and Engineering
Energy
Energy Engineering and Power Technology
Authors
Peter Lusis, Kaveh Rajab Khalilpour, Lachlan Andrew, Ariel Liebman,