NN-Based Implicit Stochastic Optimization of Multi-Reservoir Systems Management

Multi-reservoir systems management is complex because of the uncertainty on future events and the variety of purposes, usually conflicting, of the involved actors. An efficient management of these systems can help improving resource allocation, preventing political crisis and reducing the conflicts between the stakeholders. Bellman stochastic dynamic programming (SDP) is the most famous among the many proposed approaches to solve this optimal control problem. Unfortunately, SDP is affected by the curse of dimensionality: computational effort increases exponentially with the complexity of the considered system (i.e., number of reservoirs), and the problem rapidly becomes intractable. This paper proposes an implicit stochastic optimization approach for the solution of the reservoir management problem. The core idea is using extremely flexible functions, such as artificial neural networks (NN), for designing release rules which approximate the optimal policies obtained by an open-loop approach. These trained NNs can then be used to take decisions in real time. The approach thus requires a sufficiently long series of historical or synthetic inflows, and the definition of a compromise solution to be approximated. This work analyzes with particular emphasis the importance of the information which represents the input of the control laws, investigating the effects of different degrees of completeness. The methodology is applied to the Nile River basin considering the main management objectives (minimization of the irrigation water deficit and maximization of the hydropower production), but can be easily adopted also in other cases.

[1]  Zhong-kai Feng,et al.  Two Dimension Reduction Methods for Multi-Dimensional Dynamic Programming and Its Application in Cascade Reservoirs Operation Optimization , 2017 .

[2]  Xinyi Xu,et al.  Optimal Reoperation of Multi-Reservoirs for Integrated Watershed Management with Multiple Benefits , 2014 .

[3]  M. Williams,et al.  Shifting sediment sources in the world's longest river: a strontium isotope record for the Holocene Nile , 2015 .

[4]  Mutasem El-Fadel,et al.  The Nile River Basin: A Case Study in Surface Water Conflict Resolution , 2003 .

[5]  Sh. Momtahen,et al.  Direct Search Approaches Using Genetic Algorithms for Optimization of Water Reservoir Operating Policies , 2007 .

[6]  I. Villa,et al.  Tracing Nile sediment sources by Sr and Nd isotope signatures (Uganda, Ethiopia, Sudan) , 2011 .

[7]  A. Turgeon Optimal operation of multireservoir power systems with stochastic inflows , 1980 .

[8]  Andrea Castelletti,et al.  Curses, Tradeoffs, and Scalable Management: Advancing Evolutionary Multiobjective Direct Policy Search to Improve Water Reservoir Operations , 2016 .

[9]  D. Stanley,et al.  Late Quaternary palaeoclimatic oscillations in East Africa recorded by heavy minerals in the Nile delta , 1989, Nature.

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[11]  Rajandrea Sethi,et al.  Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon , 2012, Eng. Appl. Artif. Intell..

[12]  Andrea Castelletti,et al.  Many‐objective reservoir policy identification and refinement to reduce policy inertia and myopia in water management , 2014 .

[13]  Alcigeimes B. Celeste,et al.  Evaluation of stochastic reservoir operation optimization models , 2009 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  A. Tilmant,et al.  Assessing marginal water values in multipurpose multireservoir systems via stochastic programming , 2008 .

[16]  Chong-Yu Xu,et al.  Derivation of operation rules for reservoirs in parallel with joint water demand , 2015 .

[17]  Cristiano Cervellera,et al.  Optimization of a large-scale water reservoir network by stochastic dynamic programming with efficient state space discretization , 2006, Eur. J. Oper. Res..

[18]  M. Janga Reddy,et al.  Multipurpose Reservoir Operation Using Particle Swarm Optimization , 2007 .

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

[20]  Ma Chao,et al.  Reservoir Operation Rules for Controlling Algal Blooms in a Tributary to the Impoundment of Three Gorges Dam , 2014 .

[21]  D. Whittington,et al.  Water Resources Management in the Nile Basin: The Economic Value of Cooperation , 2005 .

[22]  Bellie Sivakumar,et al.  Neural network river forecasting through baseflow separation and binary-coded swarm optimization , 2015 .

[23]  Alcigeimes B. Celeste,et al.  Implicit Stochastic Optimization for deriving reservoir operating rules in semiarid Brazil , 2009 .

[24]  Giorgio Guariso,et al.  Implications of ethiopian water development for Egypt and Sudan , 1987 .

[25]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[26]  Bin Xu,et al.  Decomposition–coordination model of reservoir group and flood storage basin for real-time flood control operation , 2015 .

[27]  Gregory B. Baecher,et al.  NileSim: A Windows-Based Hydrologic Simulator of the Nile River Basin , 1999 .

[28]  Xiaocong He,et al.  Extraction and Preference Ordering of Multireservoir Water Supply Rules in Dry Years , 2016 .

[29]  D. E. Rheinheimer,et al.  Parameter uncertainty analysis of reservoir operating rules based on implicit stochastic optimization. , 2014 .

[30]  Marc Jeuland,et al.  Economic implications of climate change for infrastructure planning in transboundary water systems: An example from the Blue Nile , 2010 .

[31]  Ping-an Zhong,et al.  Scenario tree reduction in stochastic programming with recourse for hydropower operations , 2015 .

[32]  W. Yeh,et al.  Optimization of real time operation of a multiple-reservoir system , 1974 .

[33]  Kwok-wing Chau,et al.  A Hybrid Double Feedforward Neural Network for Suspended Sediment Load Estimation , 2016, Water Resources Management.

[34]  Bin Xu,et al.  Risk analysis for the downstream control section in the real-time flood control operation of a reservoir , 2015, Stochastic Environmental Research and Risk Assessment.

[35]  Pan Liu,et al.  Dynamic control of flood limited water level for reservoir operation by considering inflow uncertainty , 2010 .

[36]  E. McClelland,et al.  Opportunities for Regional and International Cooperation in the Nile Basin , 1992 .

[37]  L. Garrote,et al.  A Parametric Flood Control Method for Dams with Gate-Controlled Spillways , 2017 .

[38]  Daniele de Rigo,et al.  Neuro-dynamic programming for designing water reservoir network management policies , 2007 .

[39]  Bin Xu,et al.  Optimal Hedging Rules for Water Supply Reservoir Operations under Forecast Uncertainty and Conditional Value-at-Risk Criterion , 2017 .

[40]  D. H. Marks,et al.  A New Method for the Real-Time Operation of Reservoir Systems , 1987 .

[41]  Tohid Erfani,et al.  Agent Based Modelling for Water Resource Allocation in the Transboundary Nile River , 2016 .

[42]  S. Yakowitz,et al.  Constrained differential dynamic programming and its application to multireservoir control , 1979 .

[43]  Marc Jeuland,et al.  Water resources planning under climate change: Assessing the robustness of real options for the Blue Nile , 2014 .

[44]  Andrea Castelletti,et al.  A Matlab toolbox for designing Multi-Objective Optimal Operations of water reservoir systems , 2016, Environ. Model. Softw..

[45]  Pan Liu,et al.  Derivation of Aggregation-Based Joint Operating Rule Curves for Cascade Hydropower Reservoirs , 2011 .

[46]  Wei Li,et al.  Deriving Reservoir Refill Operating Rules by Using the Proposed DPNS Model , 2006 .

[47]  Pan Liu,et al.  Deriving multiple near‐optimal solutions to deterministic reservoir operation problems , 2011 .

[48]  Marc Jeuland,et al.  The Grand Renaissance Dam and prospects for cooperation on the Eastern Nile , 2014 .

[49]  Kwok-Wing Chau,et al.  A comparison of various artificial intelligence approaches performance for estimating suspended sediment load of river systems: a case study in United States , 2015, Environmental Monitoring and Assessment.

[50]  D. Whittington,et al.  Infrastructure development and the economics of cooperation in the Eastern Nile , 2017, A River Flows Through It.