A novel modeling approach for hourly forecasting of long-term electric energy demand
A novel modeling approach for hourly forecasting of long-term electric energy demand
复制标题
DOI：
10.1016/j.enconman.2010.06.059
复制
发表时间：
2011-01-01
影响因子：
10.4
通讯作者：
Kurban, Mehmet
中科院分区：
文献类型：
--
作者：
Filik, Ummuhan Basaran;Gerek, Omer Nezih;Kurban, Mehmet
在这项研究中，提出了一种新的建模和预测电力需求的数学方法。该方法能够做出长期预测。然而，与其他长期预测模型不同的是，该方法每小时产生一次结果，并提高了精度。该模型是使用从土耳其电力公司获得的长达26年的实际负荷数据(按小时分辨率计算的4年)构建和验证的。整个方法由用于建模的三个子部分的嵌套组合组成。第一部分是模拟年平均负荷变化的粗略水平。第二部分通过模拟一年内的每周剩余负荷变化来改进这种结构。最后的部分通过模拟一周内的变化来达到小时分辨率，使用该分辨率的新颖的2-D数学表示。这种嵌套预测方法的采用，以及提出的每小时负荷的二维表示，构成了这项工作的新颖性。建议的方法的主要优点是，它使在单一框架内进行短期、中期和长期每小时负荷预测成为可能。为了实现最小的预测误差，在嵌套系统的每一层都应用了几个数学函数作为模型。提出了以均方根误差(RMSE)和平均绝对百分比误差(MAPE)表示的模型函数及其相应的预测精度。(C)2010爱思唯尔有限公司。保留所有权利。
In this study, a novel mathematical method is proposed for modeling and forecasting electric energy demand. The method is capable of making long-term forecasts. However, unlike other long-term forecasting models, the proposed method produces hourly results with improved accuracy. The model is constructed and verified using 26-year-long real-life load data (4 years with hourly resolution) obtained from the Turkish Electric Power Company. The overall method consists of a nested combination of three subsections for modeling. The first section is the coarse level for modeling variations of yearly average loads. The second section refines this structure by modeling weekly residual load variations within a year. The final section reaches to the hourly resolution by modeling variations within a week, using a novel 2-D mathematical representation at this resolution. The adoptions of such nested forecasting methodology together with the proposed 2-D representation for hourly load constitute the novelties of this work. The major advantage of the proposed approach is that it enables the possibility of making short-, medium-, and long-term hourly load forecasting within a single framework. Several mathematical functions are applied as models at each level of the nested system for achieving the minimal forecasting error. Proposed model functions with their corresponding forecasting accuracies are presented in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE). (C) 2010 Elsevier Ltd. All rights reserved.