期刊
ADVANCES IN COMPUTATIONAL INTELLIGENCE (IWANN 2021), PT II
卷 12862, 期 -, 页码 196-207出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-85099-9_16
关键词
Multiple seasonality; Pattern representation of time series; Randomized neural networks; Short-term load forecasting; Time series forecasting
类别
资金
- National Science Centre, Poland [2017/27/B/ST6/01804]
This study contributes to the development of neural forecasting models with novel randomization-based learning methods, which improve fitting abilities and allow for forecasting time series with multiple seasonality. The proposed models show promising performance in terms of forecasting accuracy, training speed, simplicity, and robustness in dealing with nonstationarity and multiple seasonality in time series.
This work contributes to the development of neural forecasting models with novel randomization-based learning methods. These methods improve the fitting abilities of the neural model, in comparison to the standard method, by generating network parameters in accordance with the data and target function features. A pattern-based representation of time series makes the proposed approach useful for forecasting time series with multiple seasonality. In the simulation study, we evaluate the performance of the proposed models and find that they can compete in terms of forecasting accuracy with fully-trained networks. Extremely fast and easy training, simple architecture, ease of implementation, high accuracy as well as dealing with nonstationarity and multiple seasonality in time series make the proposed model very attractive for a wide range of complex time series forecasting problems.
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