RESERVOIR WATER RELEASE DECISION MODELLING

Reservoir water release decision during emergency situations typically, flood and drought is very crucial as early and accurate decision can reduce the negative impact of the events.In practice, decision regarding the water release is made by experience reservoir operator. During emergency such as heavy upstream rainfall that may causes massive inflow into the reservoir, early water release cannot be done without the attendance and knowledge of the operator. Additionally, the operator has to be very certain that the water released will be replaced with the incoming inflow as maintaining the water level at the normal range is very critical for multipurpose reservoir. Having this situation every year the reservoir operation record or the log book has become knowledge or experience rich "repository". Mining this "repository" will give an insight on how and when the decision was made to release the water from the reservoir during the emergency situations.The neural network (NN) model was developed to classify the data that in turn can be used to aid the reservoir water release decision. In this study NN model 8-23-2 has produced the acceptable performance during training (93.94%), validation (100%) and testing (100%).

[1]  Keith Smith,et al.  Floods: Physical Processes and Human Impacts , 1998 .

[2]  P. S. Sastry,et al.  A survey of temporal data mining , 2006 .

[3]  Ku Ruhana Ku-Mahamud,et al.  Flood Pattern Detection Using Sliding Window Technique , 2009, 2009 Third Asia International Conference on Modelling & Simulation.

[4]  Joseph P. Bigus,et al.  Data mining with neural networks , 1996 .

[5]  Warren S. Sarle,et al.  Stopped Training and Other Remedies for Overfitting , 1995 .

[6]  Younès Bennani,et al.  New Self-organizing Maps for Multivariate Sequences Processing , 2005, Int. J. Comput. Intell. Appl..

[7]  Theophano Mitsa,et al.  Temporal Data Mining , 2010 .

[8]  Raul Luís Monteiro Moisão.  Prediction Model , Based on Neural Networks , for Time Series with Origin in Chaotic Systems , 2001 .

[9]  Andrew R. Post,et al.  Temporal data mining. , 2008, Clinics in laboratory medicine.

[10]  Mehmet A. Orgun,et al.  An Overview Of Temporal Data Mining , 2002, AusDM.

[11]  John F. Roddick,et al.  A Survey of Temporal Knowledge Discovery Paradigms and Methods , 2002, IEEE Trans. Knowl. Data Eng..

[12]  Suh-Yin Lee,et al.  Mining frequent itemsets over data streams using efficient window sliding techniques , 2009, Expert Syst. Appl..

[13]  Vijay P. Singh,et al.  Chapter 11 - Reservoir Operation , 2003 .

[14]  Ralph A. Wurbs.  Reservoir‐System Simulation and Optimization Models , 1993 .

[15]  Ximing Cai,et al.  How reservoirs were operated - Exploring the role of hydrologic information , 2008 .

[16]  K. Ku-Mahamud,et al.  Reservoir water level forecasting model using neural network , 2010 .

[17]  Margaret H. Dunham,et al.  Data Mining: Introductory and Advanced Topics , 2002 .

[18]  John W. Labadie,et al.  Optimal Operation of Multireservoir Systems: State-of-the-Art Review , 2004 .

[19]  Daniel Graupe,et al.  Principles of Artificial Neural Networks , 2018, Advanced Series in Circuits and Systems.