Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting

Load forecasting is critical for power system operation and market planning.With the increased penetration of renewable energy and the massive consumption of electric energy, improving load forecasting accuracy has become a dif�cult task. Recently, it was demonstrated that deep learning models perfo...

Full description

Bibliographic Details
Main Authors: Goh, Hui Hwang, He, Biliang, Hui Liu, Hui Liu, Zhang, Dongdong, Wei Dai, Wei Dai, Kurniawan, Tonni Agustiono, Goh, Kai Chen
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers 2021
Subjects:
Online Access:http://eprints.uthm.edu.my/6263/
http://eprints.uthm.edu.my/6263/1/J13190_7ec3c064e09d1a741eeb13c13aa40aaf.pdf
_version_ 1848888760476893184
author Goh, Hui Hwang
He, Biliang
Hui Liu, Hui Liu
Zhang, Dongdong
Wei Dai, Wei Dai
Kurniawan, Tonni Agustiono
Goh, Kai Chen
author_facet Goh, Hui Hwang
He, Biliang
Hui Liu, Hui Liu
Zhang, Dongdong
Wei Dai, Wei Dai
Kurniawan, Tonni Agustiono
Goh, Kai Chen
author_sort Goh, Hui Hwang
building UTHM Institutional Repository
collection Online Access
description Load forecasting is critical for power system operation and market planning.With the increased penetration of renewable energy and the massive consumption of electric energy, improving load forecasting accuracy has become a dif�cult task. Recently, it was demonstrated that deep learning models perform well for short-term load forecasting (STLF). However, prior research has demonstrated that the hybrid deep learning model outperforms the single model. We propose a hybrid neural network in this article that combines elements of a convolutional neural network (1D-CNN) and a long short memory network (LSTM) in novel ways. Multiple independent 1D-CNNs are used to extract load, calendar, and weather features from the proposed hybrid model, while LSTM is used to learn time patterns. This architecture is referred to as a CNN-LSTM network with multiple heads (MCNN-LSTM). To demonstrate the proposed hybrid deep learning model's superior performance, the proposed method is applied to Ireland's load data for single-step and multi-step load forecasting. In comparison to the widely used CNN-LSTM hybrid model, the proposed model improved single-step prediction by 16.73% and 24-step load prediction by 20.33%. Additionally, we use the Maine dataset to verify the proposed model's generalizability.
first_indexed 2025-11-15T20:15:24Z
format Article
id uthm-6263
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:15:24Z
publishDate 2021
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling uthm-62632022-01-28T00:06:18Z http://eprints.uthm.edu.my/6263/ Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting Goh, Hui Hwang He, Biliang Hui Liu, Hui Liu Zhang, Dongdong Wei Dai, Wei Dai Kurniawan, Tonni Agustiono Goh, Kai Chen TK452-454.4 Electric apparatus and materials. Electric circuits. Electric networks Load forecasting is critical for power system operation and market planning.With the increased penetration of renewable energy and the massive consumption of electric energy, improving load forecasting accuracy has become a dif�cult task. Recently, it was demonstrated that deep learning models perform well for short-term load forecasting (STLF). However, prior research has demonstrated that the hybrid deep learning model outperforms the single model. We propose a hybrid neural network in this article that combines elements of a convolutional neural network (1D-CNN) and a long short memory network (LSTM) in novel ways. Multiple independent 1D-CNNs are used to extract load, calendar, and weather features from the proposed hybrid model, while LSTM is used to learn time patterns. This architecture is referred to as a CNN-LSTM network with multiple heads (MCNN-LSTM). To demonstrate the proposed hybrid deep learning model's superior performance, the proposed method is applied to Ireland's load data for single-step and multi-step load forecasting. In comparison to the widely used CNN-LSTM hybrid model, the proposed model improved single-step prediction by 16.73% and 24-step load prediction by 20.33%. Additionally, we use the Maine dataset to verify the proposed model's generalizability. Institute of Electrical and Electronics Engineers 2021 Article PeerReviewed text en http://eprints.uthm.edu.my/6263/1/J13190_7ec3c064e09d1a741eeb13c13aa40aaf.pdf Goh, Hui Hwang and He, Biliang and Hui Liu, Hui Liu and Zhang, Dongdong and Wei Dai, Wei Dai and Kurniawan, Tonni Agustiono and Goh, Kai Chen (2021) Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting. IEEE Access, 9. pp. 118528-118540. ISSN 2169-3536
spellingShingle TK452-454.4 Electric apparatus and materials. Electric circuits. Electric networks
Goh, Hui Hwang
He, Biliang
Hui Liu, Hui Liu
Zhang, Dongdong
Wei Dai, Wei Dai
Kurniawan, Tonni Agustiono
Goh, Kai Chen
Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title_full Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title_fullStr Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title_full_unstemmed Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title_short Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
title_sort multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting
topic TK452-454.4 Electric apparatus and materials. Electric circuits. Electric networks
url http://eprints.uthm.edu.my/6263/
http://eprints.uthm.edu.my/6263/1/J13190_7ec3c064e09d1a741eeb13c13aa40aaf.pdf