English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Predicting the next-day power demand has been one of the most important research areas in the electricity industry for the past decade. A successful and more accurate prediction can help both the policy-makers and consumers to plan their bidding strategies. Self-organizing maps (SOM) and K-means are the two classical algorithms among many clustering ones. In this paper, they were used to predict the electric demand with the combination of the least-square support vector machine (LSSVM). The purpose of this paper is to analyze the capacity of the SOM-LSSVM by comparing it with the K-means-LSSVM and a single LSSVM for one-day-ahead electric demand forecasting. A new parallel-grid search algorithm for LSSVM is also proposed to improve orecasting speed. The empirical testing shows that all of the three models provide good prediction results, but the results of the mean absolute percentage error obtained with the SOM-LSSVM method can achieve better prediction accuracy compared with the K-means-LSSVM and a single LSSVM models.

Using Cluster Analysis and Least Square Support Vector Machine to Predicting Power Demand for the Next-Day