A New CIGWO-Elman Hybrid Model for Power Load Forecasting

Time series forecasting is a common task that needs to be implemented in many engineering applications. In this paper, for the power load forecasting problem, we explore the advantages of the grey wolf optimization (GWO) algorithm for Elman network optimization. To avoid model complexity, the struct...

Full description

Saved in:
Bibliographic Details
Published in:Journal of electrical engineering & technology 2022, 17(2), , pp.1319-1333
Main Authors: Hao, Jie, Zhu, Changsheng, Guo, Xiuting
Format: Article
Language:English
Subjects:
Electrical Engineering
Electrical Machines and Networks
Electronics and Microelectronics
Engineering
Instrumentation
Original Article
Power Electronics
전기공학
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Time series forecasting is a common task that needs to be implemented in many engineering applications. In this paper, for the power load forecasting problem, we explore the advantages of the grey wolf optimization (GWO) algorithm for Elman network optimization. To avoid model complexity, the structure of the Elman network is simplified to improve its training efficiency. Then, a chaotic sequence and random cosine function are introduced into the GWO algorithm. In addition, the updating methods of individual positions in the particle swarm optimization (PSO) algorithm and differential evolution (DE) algorithm are used as references for improving the GWO algorithm. The new chaotic cosine inertial weights GWO (CIGWO) algorithm is used to optimize the parameters of the Elman network, and the CIGWO-Elman network model is formed. Finally, CIGWO-Elman is applied to the actual load data of a city in eastern China to realize short-term power load prediction. The results show that the proposed model has better predictive accuracy and real-time performance than those of other methods.
ISSN:1975-0102
2093-7423
DOI:10.1007/s42835-021-00928-w