Revisit Neural Network based Load Forecasting

Yingshan Tao; Fei Zhao; Haoliang Yuan; Chun Sing Lai; Zhao Xu; Wing Ng; Rongwei Li; Xuecong Li; Loi Lei Lai

doi:10.1109/ISAP48318.2019.9065930

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

The application of artificial neural network to load forecasting can overcome the problem of dynamic load change, and its ability to adapt to nonlinear relationships makes the prediction result satisfactory. This paper firstly reviews and introduces the concepts and basic principles of load prediction, discusses various methods for load forecasting, and then selects artificial neural network to establish a predictive model. In this paper, the European electric load is predicted with a BP neural network. From the prediction results, it is feasible to use BP neural network for load forecasting, and its accuracy can meet the needs of real-life engineering work. However, BP neural networks have the problem of slow convergence and easily falling into local minimum points. Therefore, this paper also uses three other neural networks for load forecasting, which are Radial Basis Network (RBF), Elman Network, and Long-Short Term Memory Network (LSTM). In the experiment, the four neural networks achieved expected prediction results, and the LSTM network had the best prediction effect. Scientific discussions are offered.

Original language	English
Title of host publication	2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728131924
DOIs	https://doi.org/10.1109/ISAP48318.2019.9065930
Publication status	Published - Dec 2019
Event	20th International Conference on Intelligent System Application to Power Systems, ISAP 2019 - New Delhi, India Duration: 10 Dec 2019 → 14 Dec 2019

Publication series

Name	2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019

Conference

Conference	20th International Conference on Intelligent System Application to Power Systems, ISAP 2019
Country/Territory	India
City	New Delhi
Period	10/12/19 → 14/12/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

back propagation
Elman Network
load forecasting
long-short term memory
neural networks
radial basis function

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Control and Optimization

More information

10.1109/ISAP48318.2019.9065930

Cite this

Tao, Y., Zhao, F., Yuan, H., Lai, C. S., Xu, Z., Ng, W., Li, R., Li, X., & Lai, L. L. (2019). Revisit Neural Network based Load Forecasting. In 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019 Article 9065930 (2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISAP48318.2019.9065930

@inproceedings{47c8bbbda6af4a528cb8c8e0d1a1ad7c,

title = "Revisit Neural Network based Load Forecasting",

abstract = "The application of artificial neural network to load forecasting can overcome the problem of dynamic load change, and its ability to adapt to nonlinear relationships makes the prediction result satisfactory. This paper firstly reviews and introduces the concepts and basic principles of load prediction, discusses various methods for load forecasting, and then selects artificial neural network to establish a predictive model. In this paper, the European electric load is predicted with a BP neural network. From the prediction results, it is feasible to use BP neural network for load forecasting, and its accuracy can meet the needs of real-life engineering work. However, BP neural networks have the problem of slow convergence and easily falling into local minimum points. Therefore, this paper also uses three other neural networks for load forecasting, which are Radial Basis Network (RBF), Elman Network, and Long-Short Term Memory Network (LSTM). In the experiment, the four neural networks achieved expected prediction results, and the LSTM network had the best prediction effect. Scientific discussions are offered.",

keywords = "back propagation, Elman Network, load forecasting, long-short term memory, neural networks, radial basis function",

author = "Yingshan Tao and Fei Zhao and Haoliang Yuan and Lai, \{Chun Sing\} and Zhao Xu and Wing Ng and Rongwei Li and Xuecong Li and Lai, \{Loi Lei\}",

year = "2019",

month = dec,

doi = "10.1109/ISAP48318.2019.9065930",

language = "English",

series = "2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019",

note = "20th International Conference on Intelligent System Application to Power Systems, ISAP 2019 ; Conference date: 10-12-2019 Through 14-12-2019",

}

Tao, Y, Zhao, F, Yuan, H, Lai, CS, Xu, Z, Ng, W, Li, R, Li, X & Lai, LL 2019, Revisit Neural Network based Load Forecasting. in 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019., 9065930, 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019, Institute of Electrical and Electronics Engineers Inc., 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019, New Delhi, India, 10/12/19. https://doi.org/10.1109/ISAP48318.2019.9065930

Revisit Neural Network based Load Forecasting. / Tao, Yingshan; Zhao, Fei; Yuan, Haoliang et al.
2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9065930 (2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Revisit Neural Network based Load Forecasting

AU - Tao, Yingshan

AU - Zhao, Fei

AU - Yuan, Haoliang

AU - Lai, Chun Sing

AU - Xu, Zhao

AU - Ng, Wing

AU - Li, Rongwei

AU - Li, Xuecong

AU - Lai, Loi Lei

PY - 2019/12

Y1 - 2019/12

N2 - The application of artificial neural network to load forecasting can overcome the problem of dynamic load change, and its ability to adapt to nonlinear relationships makes the prediction result satisfactory. This paper firstly reviews and introduces the concepts and basic principles of load prediction, discusses various methods for load forecasting, and then selects artificial neural network to establish a predictive model. In this paper, the European electric load is predicted with a BP neural network. From the prediction results, it is feasible to use BP neural network for load forecasting, and its accuracy can meet the needs of real-life engineering work. However, BP neural networks have the problem of slow convergence and easily falling into local minimum points. Therefore, this paper also uses three other neural networks for load forecasting, which are Radial Basis Network (RBF), Elman Network, and Long-Short Term Memory Network (LSTM). In the experiment, the four neural networks achieved expected prediction results, and the LSTM network had the best prediction effect. Scientific discussions are offered.

AB - The application of artificial neural network to load forecasting can overcome the problem of dynamic load change, and its ability to adapt to nonlinear relationships makes the prediction result satisfactory. This paper firstly reviews and introduces the concepts and basic principles of load prediction, discusses various methods for load forecasting, and then selects artificial neural network to establish a predictive model. In this paper, the European electric load is predicted with a BP neural network. From the prediction results, it is feasible to use BP neural network for load forecasting, and its accuracy can meet the needs of real-life engineering work. However, BP neural networks have the problem of slow convergence and easily falling into local minimum points. Therefore, this paper also uses three other neural networks for load forecasting, which are Radial Basis Network (RBF), Elman Network, and Long-Short Term Memory Network (LSTM). In the experiment, the four neural networks achieved expected prediction results, and the LSTM network had the best prediction effect. Scientific discussions are offered.

KW - back propagation

KW - Elman Network

KW - load forecasting

KW - long-short term memory

KW - neural networks

KW - radial basis function

UR - https://www.scopus.com/pages/publications/85084304004

U2 - 10.1109/ISAP48318.2019.9065930

DO - 10.1109/ISAP48318.2019.9065930

M3 - Conference article published in proceeding or book

AN - SCOPUS:85084304004

T3 - 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019

BT - 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019

Y2 - 10 December 2019 through 14 December 2019

ER -

Tao Y, Zhao F, Yuan H, Lai CS, Xu Z, Ng W et al. Revisit Neural Network based Load Forecasting. In 2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9065930. (2019 20th International Conference on Intelligent System Application to Power Systems, ISAP 2019). doi: 10.1109/ISAP48318.2019.9065930