Long-term Energy and Peak Power Demand Forecasting based on Sequential-XGBoost

Tingze Zhang, Xinan Zhang, Osaka Rubasinghe, Yulin Liu, Yau Chow, Herbert Iu, Tyrone Fernando

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)

Abstract

Long-term energy and peak power forecast are essential tasks for the effective planning of power systems. Utilities often conduct long-term energy consumption and peak power demand forecasting separately through different forecasting frameworks, resulting in high complexities. To overcome this issue, this paper proposes a complete long-term forecasting model using an eXtreme Gradient Boosting algorithm with different sequential configurations. Firstly, it contributes to establish a 1-3 years ahead monthly energy consumption forecasting model, considering some external drivers such as macro-economic and climatic conditions. Based on the nature of energy consumption profile, a multi-input multi-output sequential strategy is applied. Then, the forecasted energy consumption forms an influencing input of a multivariate 1-3 years ahead monthly peak power demand forecast model. A hybrid direct-recursive sequential configuration is adopted to handle the highly fluctuating nature of peak power demand. By forecasting peak power demand using the information of forecasted energy consumption, better forecasting accuracy was obtained. The validity of the proposed long-term forecasting model was tested using the data from New South Wales (NSW) power network. The results were compared with several state-of-the-art long-term forecast models to show its superiority.

Original languageEnglish
Pages (from-to)3088-3104
Number of pages17
JournalIEEE Transactions on Power Systems
Volume39
Issue number2
Early online date26 Jun 2023
DOIs
Publication statusPublished - 1 Mar 2024

Fingerprint

Dive into the research topics of 'Long-term Energy and Peak Power Demand Forecasting based on Sequential-XGBoost'. Together they form a unique fingerprint.

Cite this