A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting

Fusen Guo; Huadong Mo; Jianzhang Wu; Lei Pan; Hailing Zhou; Zhibo Zhang; Lin Li; Fengling Huang

doi:10.3390/electronics13142719

Back

A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting

Journal article

Open access

Peer reviewed

A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting

Fusen Guo, Huadong Mo, Jianzhang Wu, Lei Pan, Hailing Zhou, Zhibo Zhang, Lin Li and Fengling Huang

Electronics (Basel), Vol.13(14), 2719

11/07/2024

DOI: https://doi.org/10.3390/electronics13142719

Appears in Recent Faculty of Science and Engineering Publications

Files and links (2)

pdf

A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting3.07 MBDownload View

Published (Version of record)CC BY V4.0, Open Access

url

A Hybrid Stacking Model for Enhanced Short-Term Load ForecastingView

Published (Version of record)CC BY V4.0, Open

Metrics

1 Record Views

2 Times Cited - Web of Science

Abstract

Computer Science

Computer Science, Information Systems

Engineering

Engineering, Electrical & Electronic

Physical Sciences

Physics

Physics, Applied

Science & Technology

Technology

smart grid

short-term load forecasting

deep learning

stacking approach

time series analysis

The high penetration of distributed energy resources poses significant challenges to the dispatch and operation of power systems. Improving the accuracy of short-term load forecasting (STLF) can optimize grid management, thus leading to increased economic and social benefits. Currently, some simple AI and hybrid models have issues to deal with and struggle with multivariate dependencies, long-term dependencies, and nonlinear relationships. This paper proposes a novel hybrid model for short-term load forecasting (STLF) that integrates multiple AI models with Lasso regression using the stacking technique. The base learners include ANN, XgBoost, LSTM, Stacked LSTM, and Bi-LSTM, while lasso regression serves as the metalearner. By considering factors such as temperature, rainfall, and daily electricity prices, the model aims to more accurately reflect real-world conditions and enhance predictive accuracy. Empirical analyses on real-world datasets from Australia and Spain show significant improvements in the forecasting accuracy, with a substantial reduction in the mean absolute percentage error (MAPE) compared to existing hybrid models and individual AI models. This research highlights the efficiency of the stacking technique in improving STLF accuracy, thus suggesting potential operational efficiency benefits for the power industry.

Details

Title: A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting
Creators: Fusen Guo - Swinburne University of Technology
Huadong Mo - University of NSW
Jianzhang Wu - Deakin Univ, Sch Informat Technol, Geelong, Vic 3216, Australia
Lei Pan - Deakin University
Hailing Zhou - Swinburne University of Technology
Zhibo Zhang - University of NSW
Lin Li - RMIT University
Fengling Huang - Shanghai Jiao Tong Univ, Sch Aeronaut & Astronaut, Shanghai 200240, Peoples R China
Publication Details: Electronics (Basel), Vol.13(14), 2719
Publisher: MDPI AG
Number of pages: 16
Identifiers: 991013225779402368
Academic Unit: Faculty of Science and Engineering
Language: English
Resource Type: Journal article

A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting

Files and links (2)

Metrics

Abstract

Details

Southern Cross University Social media