Skip to main content

Research Repository

Advanced Search

A spatio-temporal graph convolutional approach to real-time load forecasting in an edge-enabled distributed Internet of Smart Grids energy system

Liu, Qi; Pan, Li; Cao, Xuefei; Gan, Jixiang; Huang, Xianming; Liu, Xiaodong

Authors

Qi Liu

Li Pan

Xuefei Cao

Jixiang Gan

Xianming Huang



Abstract

As the edge nodes of the Internet of Smart Grids (IoSG), smart sockets enable all kinds of power load data to be analyzed at the edge, which create conditions for edge calculation and real-time (RT) load forecasting. In this article, an edge-cloud computing analysis energy system is proposed to collect and analyze power load data, and a combination of graph convolutional network (GCN) with LSTM, called KGLSTM is used to achieve mid-long term mixed sequential mode RT forecasting. In the proposed edge-cloud framework, distributed intelligent sockets are regarded as edge nodes to collect, analyze and upload data to cloud services for further processing. The proposed KGLSTM network adopts a double branch structure. One branch extracts the data characteristics of mid-short term time-series data through an encoding–decoding LSTM module; the other branch extracts the data features of long term timing data through an adapted GCN. GCN is used to extract spatial correlations between different nodes. In addition, by combining a dynamic weighted loss function, the accuracy of peak forecasting is effectively improved. Finally, through various experimental indicators, this article shows that KGLSTM and weighted KGLSTM have achieved significant performance improvement over recent methods in mid-long term time-series forecasting and peak forecasting.

Journal Article Type Article
Acceptance Date Feb 13, 2024
Online Publication Date Mar 13, 2024
Deposit Date Mar 18, 2024
Publicly Available Date Mar 14, 2025
Print ISSN 1532-0626
Electronic ISSN 1532-0634
Publisher Wiley
Peer Reviewed Peer Reviewed
Article Number e8060
DOI https://doi.org/10.1002/cpe.8060
Keywords Real-time Intelligent Methods, Time-series Forecasting, Graph Convolutional Network, Long Short-Term Memory, Energy Systems
Public URL http://researchrepository.napier.ac.uk/Output/3562957