Unsupervised/supervised learning concept for 24-hour load forecasting
Unsupervised/supervised learning concept for 24-hour load forecasting
复制标题
用于 24 小时负荷预测的无监督/监督学习概念
DOI：
--
复制
发表时间：
1993
期刊：
影响因子：
--
通讯作者：
Y. Pao
中科院分区：
文献类型：
--
作者：
M. Djukanovic;B. Babic;D. Sobajic;Y. Pao
介绍了人工神经网络在短期负荷预测中的应用。提出了一种利用无监督/监督学习概念和给定季节、日型和小时的负荷与温度之间的历史关系预测24小时提前期的小时电力负荷的算法。介绍了一种利用函数连接网络、温度变量、平均负荷和前一天最后一小时负荷的预测方法，并与单隐层神经网络负荷预测方法进行了比较。尽管有限的可用天气变量（最高，最低和平均温度的一天）相当可以接受的结果已经取得。24小时前的预测误差（绝对平均值）从星期六的2.78%和工作日的3.12%到星期日的3.54%不等。
An application of artificial neural networks in short-term load forecasting is described. An algorithm using an unsupervised/supervised learning concept and historical relationship between the load and temperature for a given season, day type and hour of the day to forecast hourly electric load with a lead time of 24 hours is proposed. An additional approach using functional link net, temperature variables, average load and last one-hour load of previous day is introduced and compared with the ANN model with one hidden layer load forecast. In spite of limited available weather variables (maximum, minimum and average temperature for the day) quite acceptable results have been achieved. The 24-hour-ahead forecast errors (absolute average) ranged from 2.78% for Saturdays and 3.12% for working days to 3.54% for Sundays.