Recently, a “memory based” approach towards various kinds of problems has been proposed. The underlying principles of the memory based approach are : (1) storing past examples in a memory. (2) searching “near” examples to a given input in a memory. In this paper, we apply the memory based approach to water demand forecasting, and present a hybrid method which consists of MBL (Memory Based Learning) and the conventional multiregression. In the memory based method, the distance metric is crucial. In our method, the local distance metric is defined from examples when an input data is given, then the neighborhood of the input is determined based on the distance metric. If there exist examples within the “neighborhood” of the input data, then the forecast is given by MBL. Otherwise, local multiregression is used. We applied this method to the daily water demand forecasting. The forecasting results by our method are approximately 5% better than those by the multiregression method. Especially, when there exist past examples in the neighborhood, namely in the case where MBL is applicable, the results are approximately 10-30% better than those by the conventional multiregression.
Water Demand Forecasting by Memory Based Learning
Takashi Tamada, Minoru Maruyama, Yasuaki Nakamura, Shigeru Abe, Kazuo Maeda; Water Demand Forecasting by Memory Based Learning. Water Sci Technol 1 December 1993; 28 (11-12): 133–140. doi: https://doi.org/10.2166/wst.1993.0653
Download citation file:
Impact Factor 1.915
CiteScore 3.3 • Q2
First Decision in 30 days