System Upgrade on Tue, May 28th, 2024 at 2am (EDT)

Existing users will be able to log into the site and access content. However, E-commerce and registration of new users may not be available for up to 12 hours.
For online purchase, please visit us again. Contact us at customercare@wspc.com for any enquiries.

Advanced Search

SEARCH GUIDE

Narrow Results

Results: 1 - 1of1

Follow results:

per page:

Sort: Relevance

Context for search term 1Search term 1*

All Dates

LastSelect static range

Custom Range

Select starting monthSelect starting year

Select ending monthSelect ending year

articleNo Access
A methodology for short term load forecasting based on wavelet filters
- Sudheer Gopinathan and
- Suseelatha Annamareddy
International Journal of Energy and Statistics01 Sep 2014
Preview Abstract
In this paper, a new hybrid method based on DWT and WNN methods is proposed to develop an accurate model for short term load forecasting. The wavelet filters are used to decompose the load series into deterministic and fluctuation components. The deterministic component models the general pattern of the load signal while the fluctuation component models the random characteristics of the load signal. The WNN technique is then used to find and weight similar data to predict the next day load. The effectiveness of the proposed methodology in forecasting the next day load is illustrated by applying it to practical load data of California and Spain energy markets. The performance is compared to the corresponding non-wavelet model and Naive predictors by using the weekly mean absolute percentage error metric and the weekly error variance.

1