改良式自組織映射線性輸出模式於水庫入流量預報之研究

Improved Self-organizing Linear Output Map for Reservoir Inflow Forecasting

張家銓(Chia-Chuang Chang)

指導教授 ： 林國峰

國立臺灣大學/工學院/土木工程學研究所/碩士(2009年)

https://doi.org/10.6342/NTU.2009.00673

摘要

本研究以自組織映射線性輸出模式(Self-organizing Linear Output Map, SOLO)架構一個有效的水庫時入流量預報模式。在類神經網路領域裡，倒傳遞類神經網路模式(Back-propagation Neural Network, BPNN) 被廣泛使用。相對於BPNN而言，SOLO模式的優勢在於：(1)準確度高、(2)架構簡單、(3)訓練所需時間少、(4)有助於分析。為了展示上述的四個優勢，本研究將SOLO應用於翡翠水庫入流量預報，研究結果顯示SOLO的效能及效率比BPNN來得佳。又為了改善SOLO尖峰入流量的預報，本研究進一步加入資料前處理的步驟以改良SOLO，並命名為改良式自組織映射線性輸出模式(Improved Self-organizing Linear Output Map, ISOLO)。研究成果證實ISOLO可以明顯改善SOLO尖峰入流量的預報。因此，建議可以ISOLO作為現有模式的替代方案，其優異的預報能力對水庫操作也相當有幫助。

關鍵字

自組織映射線性輸出模式 ； 水庫入流量預報 ； 自組織映射圖 ； 尖峰入流量預報 ； 資料前處理 ； 類神經網路

並列摘要

Based on self-organizing linear output map (SOLO), effective hourly reservoir inflow forecasting models are proposed. As compared with back-propagation neural network (BPNN) which is the most frequently used conventional neural network (NN), SOLO has four advantages: (1) SOLO has better generalization ability; (2) the architecture of the SOLO is simpler; (3) SOLO is trained much more rapidly, and (4) SOLO could provide features that facilitate insight into underlying processes. An application is conducted to clearly demonstrate these four advantages. The results indicate that the SOLO model is more well-performed and efficient than the existing BPN-based models. To further improve the peak inflow forecasting, SOLO with data preprocessing named ISOLO is also proposed. The comparison between SOLO and ISOLO confirms the significant improvement in peak inflow forecasting. The proposed model is recommended as an alternative to the existing models. The proposed modeling technique is also expected to be useful to support reservoir operation systems.

並列關鍵字

self-organizing linear output map ； reservoir inflow forecasting ； self-organizing map ； peak inflow forecasting ； data preprocessing ； neural network

參考文獻

1. Abrahart, R.J., See, L., (2000). "Comparing Neural Network and Autoregressive Moving Average Techniques for the Provision of Continuous River Flow Forecasts in Two Contrasting Catchments." Hydrological Processes 14: 2157-2172.

2. Bae, D.H., Jeong, D.M., Kim, G., (2007). "Monthly Dam Inflow Forecasts Using Weather Forecasting Information and Neuro-fuzzy Technique." Hydrological Sciences Journal 52(1): 99-113.

3. Bowden, G.J., Dandy, G.C., Maier, H.R., (2005). "Input Determination for Neural Network Models in Water Resources Applications: Part I - Background and Methodology." Journal of Hydrology 301(1-4): 75-92.

4. Chang, F.J., Chang, Y.T., (2006). "Adaptive Neuro-fuzzy Inference System for Prediction of Water Level in Reservoir." Advances in Water Resources 29(1): 1-10.

5. Chang, F.J., Chang, L.C., Wang, Y.S., (2007). "Enforced Self-organizing Map Neural Network for River Flood Forecasting." Hydrological Processes 21: 741-749.