Application of deep learning method for decision making support of dam release operation

Sungho Jung; Xuan Hien Le; Yeonsu Kim; Hyungu Choi; Giha Lee

doi:10.3741/JKWRA.2021.54.S-1.1095

All Issue

2021 Vol.54, Issue 12S Preview Page Next Page

Research Article

Application of deep learning method for decision making support of dam release operation 댐 방류 의사결정지원을 위한 딥러닝 기법의 적용성 평가

31 December 2021. pp. 1095-1105

PDF XML

Abstract

The advancement of dam operation is further required due to the upcoming rainy season, typhoons, or torrential rains. Besides, physical models based on specific rules may sometimes have limitations in controlling the release discharge of dam due to inherent uncertainty and complex factors. This study aims to forecast the water level of the nearest station to the dam multi-timestep-ahead and evaluate the availability when it makes a decision for a release discharge of dam based on LSTM (Long Short-Term Memory) of deep learning. The LSTM model was trained and tested on eight data sets with a 1-hour temporal resolution, including primary data used in the dam operation and downstream water level station data about 13 years (2009~2021). The trained model forecasted the water level time series divided by the six lead times: 1, 3, 6, 9, 12, 18-hours, and compared and analyzed with the observed data. As a result, the prediction results of the 1-hour ahead exhibited the best performance for all cases with an average accuracy of MAE of 0.01m, RMSE of 0.015 m, and NSE of 0.99, respectively. In addition, as the lead time increases, the predictive performance of the model tends to decrease slightly. The model may similarly estimate and reliably predicts the temporal pattern of the observed water level. Thus, it is judged that the LSTM model could produce predictive data by extracting the characteristics of complex hydrological non-linear data and can be used to determine the amount of release discharge from the dam when simulating the operation of the dam.

Keywords

Nam river dam

Dam operation

Water level prediction

Deep learning

LSTM model

기후변화에 따른 집중호우, 태풍 등의 발생빈도의 증가로 인하여 댐 운영의 고도화가 요구되고 있다. 일반적으로 댐 운영의 경우 강우예측, 강우-유출, 홍수추적 등 다양한 수리수문학적 요소들을 반영하여 수행되나 기 계획된 특정 규칙에 기반한 댐 운영 모형의 경우, 때때로 개별 모듈들의 불확실성과 복합적인 인자들로 인하여 댐의 방류량을 능동적으로 제어하는데 제약이 있을 수 있다. 본 연구는 남강댐 직하류 홍수피해 예방을 위하여 댐의 방류량 결정 등 효율적인 댐 운영을 지원하기 위해 딥러닝 기반 LSTM (Long Short-Term Memory) 모형을 구축하고, 선행시간별 댐직하류 수위예측 정확도를 분석하는 것을 목적으로 한다. LSTM 모형의 입력자료는 댐 운영에 사용되는 기초자료 및 하류 장대동 수위관측소의 수위 자료를 시 단위로 2009년부터 2021년 7월까지 수집하였다. 2009년부터 2018년 자료는 모형의 학습과 검증 및 2019년부터 2021년 7월 자료는 선행시간을 7개(1 h, 3 h, 6 h, 9 h, 12 h, 18 h, 24 h)로 구분하여 관측 수위와 예측 수위를 비교·분석하였다. 그 결과, 선행시간 1시간의 예측결과는 평균적으로 MAE가 0.01 m, RMSE가 0.015 m, NSE가 0.99 로 관측 수위에 매우 근접한 예측 결과를 나타내었다. 또한, 선행시간이 길어질수록 예측 정확도는 근소하게 감소하였지만, 관측 수위의 시간적 패턴을 유사하게 안정적으로 예측하는 것으로 분석되었다. 따라서 수리수문학적 비선형의 복잡한 자료간의 특징을 자동으로 추출하여 예측 자료를 생산하는 LSTM 모형은 댐 방류량 의사결정에 있어 활용이 가능할 것으로 판단된다.

키워드

남강댐

댐 운영

수위 예측

딥러닝

LSTM 모형

References

Chang, L.C., and Chang, F.J. (2001). "Intelligent control for modelling of real-time reservoir operation." Hydrological Processes, Vol. 15, No. 9, pp. 1621-1634. 10.1002/hyp.226

Chaves, P., and Chang, F.J. (2008). "Intelligent reservoir operation system based on evolving artificial neural networks." Advances in Water Resources, Vol. 31, No. 6, pp. 926-936. 10.1016/j.advwatres.2008.03.002

Chaves, P., Tsukatani, T., and Kojiri, T. (2004). "Operation of storage reservoir for water quality by using optimization and artificial intelligence techniques." Mathematics and Computers in Simulation, Vol. 67, No. 4-5, pp. 419-432. 10.1016/j.matcom.2004.06.005

Choi, C.K., Choi, Y.S., and Kim, K.T. (2012). "Application of a distributed model for evaluating the effect of Sacheonman spillway on the flood reduction in the downstream of Namgang Dam." Journal of Wetlands Research, Vol. 14, No. 3, pp. 399-411.

Dynesius, M., and Nilsso, C. (1994). "Fragmentation and flow regulation of river systems in the northern third the world." Science, Vol. 266, No. 5186, pp. 753-762. 10.1126/science.266.5186.75317730396

Hejazi, M.I., and Cai, X.M. (2009). "Input variable selection for water resources systems using a modified minimum redundancy maximum relevance (mMRMR) algorithm." Advances in Water Resources. Vol. 32, No. 4, pp. 582-593. 10.1016/j.advwatres.2009.01.009

Jain, S.K., Das, A., and Srivastava, D.K. (1999). "Application of ANN for reservoir inflow prediction and operation." Journal of water resources planning and management, Vol. 125, No. 5, pp. 263-271. 10.1061/(ASCE)0733-9496(1999)125:5(263)

Johnson, S.A., Stedinger, J.R., and Staschus, K. (1991). "Heuristic operating policies for reservoir system simulation." Water Resources Research, Vol. 27, No. 5, pp. 673-685. 10.1029/91WR00320

Jung, S.H., Cho, H.S., Kim, J.Y., and Lee, G.H. (2018). "Prediction of water level in a tidal river using a deep-learning based LSTM model." Journal of Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216.

Kang, T.U., Lee, S.J., and Kang, S.U. (2015). "A study for flood control of a dam using flood guide curves and release determination method in accordance with reservoir water level." Journal of the Korean Society of Hazard Mitigation, Vol. 15, No. 6, pp. 129-136. 10.9798/KOSHAM.2015.15.6.129

Kim, D.P., and Kim, K.H. (2018). "Estimation of travel time in natural river and dam outflow conditions considering rainfall conditions and soil moisture accounting." Journal of the Korean Society of Civil Engineers, Vol. 38, No. 4, pp. 537-545.

Klipsch, J.D., and Hurst, M.B. (2003). HEC-ResSim: Reservoir system simulation 2003 User's manual US army corps of engineers. Hydrologic Engineering Centre, Davis, CA, U.S.

Kwak, J.W. (2021). "A study for the target water level of the dam for flood control." Journal of Korea Water Resources Association, Vol. 54, No. 7, pp. 545-552.

Lehner, B., Liermann, C.R., Revenga, C., Vörösmarty, Fekete, B., Crouzet, P., Döll, P., Endejan, M., Frenken, K., Magome, J., Nilsson, C., Robertson, J.C, Rödel, R., Sindorf, N., and Wisser, D. (2011). "High-resolution mapping of the world's reservoirs and dams for sustainable river-flow management." Frontiers in Ecology and the Environment, Vol. 9, No. 9, pp. 494-502. 10.1890/100125

Oliveira, R., and Loucks, D.P. (1997). "Operating rules for multi-reservoir systems." Water Resources Research, Vol. 33, No. 4, pp. 839-852. 10.1029/96WR03745

Shang, Y., Lu, S., Ye, Y., Liu, R., Shang, L., Liu, C., Meng, X., Li, X., and Fan, Q. (2018). "China' energy-water nexus: Hydropower generation potential of joint operation of the three gorges and qingjiang cascade reservoirs." Energy, Vol. 142, pp. 14-32. 10.1016/j.energy.2017.09.131

Sit, M., Demiray, B.Z., Xiang, Z., Ewing, G.J., Sermet, Y., and Demir, I. (2020). "A comprehensive review of deep learning applications in hydrology and water resources." Water Science and Technology, Vol. 82, No. 12, pp. 2635-2670. 10.2166/wst.2020.36933341760

Thirumalaiah, K., and Deo, M.C. (1998). "River stage forecasting using artificial neural networks." Journal of Hydrologic Engineering, Vol. 3, No. 1, pp. 26-32. 10.1061/(ASCE)1084-0699(1998)3:1(26)

Woo, Y.W., Lee, S.J., and Kim, K.B. (2008). "Controlling of dam gates with outflow control by dynamic fuzzy inference." Journal of The Korea Society of Computer and Information, Vol. 13, No. 7, pp. 75-82.

Would Commission on Dams (WCD) (2000). Dams and development: a new framework for dcision-making. Earthscam Publications Ltd, London.

Yates, D., Sieber, J., Purkey, D., and Huber-Lee, A. (2005). "WEAP21-A demand-, priority-, and preference-driven water planning model: Part1: Model characteristics." Water International, Vol. 30, No. 4, pp. 487-500. 10.1080/02508060508691893

Yi, J.E., Son, K.I., and Kang, M.S. (2015). "Hydraulic & hydrologic design criteria for an emergency drainage of reservoir (II)." Journal of Korea Water Resources Association, Vol. 48, No. 3, pp. 159-167. 10.3741/JKWRA.2015.48.3.159

Zhang, D., Lin, J., Peng, Q., Wang, D., Yang, T., Sorooshian, S., Liu, X., and Zhuang, J. (2018). "Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm." Journal of Hydrology, Vol. 565, pp. 720-736. 10.1016/j.jhydrol.2018.08.050

Information

Publisher :KOREA WATER RESOURECES ASSOCIATION
Publisher(Ko) :한국수자원학회
Journal Title :Journal of Korea Water Resources Association
Journal Title(Ko) :한국수자원학회 논문집
Volume : 54
No :12
Pages :1095-1105
Received Date : 2021-09-30
Revised Date : 2021-10-28
Accepted Date : 2021-10-31
DOI :https://doi.org/10.3741/JKWRA.2021.54.S-1.1095

Journal of Korea Water Resources AssociationISSN:2799-8746(Print) 2799-8754(Online)한국수자원학회

All Issue