期刊
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
卷 57, 期 2, 页码 1860-1871出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIA.2021.3051105
关键词
Training; Forecasting; Electricity supply industry; Uncertainty; Prediction algorithms; Extreme learning machines; Artificial neural networks; Electricity market; electricity price; extreme learning machine; online training; regression analysis
资金
- Australian Research Council [LP0991428]
- ARC [DP140100974]
- ARC Research Hub for Integrated Energy Storage Solutions [IH180100020]
- Hunan province science and technology project funds, China [2018TP1036]
- Australian Research Council [LP0991428] Funding Source: Australian Research Council
This article introduces a novel online learning forecast approach to improve predispatch price forecast using the OS-ELM algorithm. The approach includes a unique data structure and modules that can continuously perceive changes in nonlinear patterns and showed promising results in simulation studies based on Australian electricity market data.
The predispatch price forecast plays a key element in the electricity market. However, such a forecast usually depends on the traditional offline batch-learning technologies, which cannot respond in time to the unexpected changes in the local power system environment. Further, the predispatch local price forecast is often affected by the dynamic price changes from the neighboring regions. This article proposes a novel online learning forecast approach to overcome the above issues to provide a better predispatch price forecast by using the online sequential extreme learning machine (OS-ELM) algorithm. The article proposes a novel data structure in the form of a 2-D orthogonal list and two corresponding OS-ELM modules. One module provides the rolling day-ahead price prediction and prediction intervals using the day-by-day online training update, while the other provides the rolling 30-min prediction using the 2-h-by-2-h online training update. The proposed approach can continuously perceive any unexpected events and any price fluctuations from the neighboring regions in the nonlinear patterns. The proposed approach is validated using simulation studies based on the data from the Australian electricity market, and the simulation results show that the proposed approach can help in improving the forecast accuracy, especially when unexpected changes occur both locally and in the neighboring area.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据