Chuntian Cheng

Using support vector machines for long-term discharge prediction

Abstract Accurate time- and site-specific forecasts of streamflow and reservoir inflow are important in effective hydropower reservoir management and scheduling. Traditionally, autoregressive moving-average (ARMA) models have been used in modelling water resource time series as a standard representation of stochastic time series. Recently, artificial neural network (ANN) approaches have been proven to be efficient when applied to hydrological prediction. In this paper, the support vector machine (SVM) is presented as a promising method for hydrological prediction. Over-fitting and local optimal solution are unlikely to occur with SVM, which implements the structural risk minimization principle rather than the empirical risk minimization principle. In order to identify appropriate parameters of the SVM prediction model, a shuffled complex evolution algorithm is performed through exponential transformation. The SVM prediction model is tested using the long-term observations of discharges of monthly river flow discharges in the Manwan Hydropower Scheme. Through the comparison of its performance with those of the ARMA and ANN models, it is demonstrated that SVM is a very potential candidate for the prediction of long-term discharges.

Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall–runoff model calibration

An automatic calibration methodology for the Xinanjiang model that has been successfully and widely applied in China is presented. The automatic calibration of the model consists of two parts: water balance parameter and runoff routing parameter calibration. The former is based on a simple genetic algorithm (GA). The latter is based on a new method which combines a fuzzy optimal model (FOM) with a GA for solving the multiple objective runoff routing parameters calibration problem. Except for the specific fitness where the membership degree of alternative obtained by FOM with limited alternatives and multi-objectives is employed, the GA with multiple objectives in this paper is otherwise the same as the simple GA. The parameter calibration includes optimization of multiple objectives: (1) peak discharge, (2) peak time and (3) total runoff volume. Thirty-four historical floods from 12 years in the Shuangpai Reservoir are applied to calibrate the model parameters whilst 11 floods in recent 2 years are utilized to verify these parameters. Results of this study and application show that the hybrid methodology of GAs and the FOM is not only capable of exploiting more the important characteristics of floods but also efficient and robust.

Long-Term prediction of discharges in manwan reservoir using artificial neural network models

Several artificial neural network (ANN) models with a feed-forward, back-propagation network structure and various training algorithms, are developed to forecast daily and monthly river flow discharges in Manwan Reservoir. In order to test the applicability of these models, they are compared with a conventional time series flow prediction model. Results indicate that the ANN models provide better accuracy in forecasting river flow than does the auto-regression time series model. In particular, the scaled conjugate gradient algorithm furnishes the highest correlation coefficient and the smallest root mean square error. This ANN model is finally employed in the advanced water resource project of Yunnan Power Group.

Long-Term prediction of discharges in manwan hydropower using adaptive-network-based fuzzy inference systems models

Forecasting reservoir inflow is important to hydropower reservoir management and scheduling. An Adaptive-Network-based Fuzzy Inference System (ANFIS) is successfully developed to forecast the long-term discharges in Manwan Hydropower. Using the long-term observations of discharges of monthly river flow discharges during 1953-2003, different types of membership functions and antecedent input flows associated with ANFIS model are tested. When compared to the ANN model, the ANFIS model has shown a significant forecast improvement. The training and validation results show that the ANFIS model is an effective algorithm to forecast the long-term discharges in Manwan Hydropower. The ANFIS model is finally employed in the advanced water resource project of Yunnan Power Group.

Multiple Criteria Rainfall-Runoff Model Calibration Using a Parallel Genetic Algorithm in a Cluster of Computers

Abstract Genetic algorithms are among of the global optimization schemes that have gained popularity as a means to calibrate rainfall–runoff models. However, a conceptual rainfall–runoff model usually includes 10 or more parameters and these are interdependent, which makes the optimization procedure very time-consuming. This may result in the premature termination of the optimization process which will prejudice the quality of the results. Therefore, the speed of optimization procedure is crucial in order to improve the calibration quality and efficiency. A hybrid method that combines a parallel genetic algorithm with a fuzzy optimal model in a cluster of computers is proposed. The method uses the fuzzy optimal model to evaluate multiple alternatives with multiple criteria where chromosomes are the alternatives, whilst the criteria are flood performance measures. In order to easily distinguish the performance of different alternatives and to address the problem of non-uniqueness of optimum, two fuzzy ratios are defined. The new approach has been tested and compared with results obtained by using a two-stage calibration procedure. The current single procedure produces similar results, but is simpler and automatic. Comparison of results between the serial and parallel genetic algorithms showed that the current methodology can significantly reduce the overall optimization time and simultaneously improve the solution quality.

Knowledge management system on flow and water quality modeling

Abstract Due to the complexity of the numerical simulation of flow and/or water quality, there is an increasing demand for integration of recent knowledge management, artificial intelligence technology with the conventional hydraulic algorithmic models in order to assist novice application users in selection and manipulation of various mathematical tools. In this paper, a prototype knowledge management system on flow and water quality is addressed to simulate human expertise during the problem solving by incorporating artificial intelligence and coupling various descriptive knowledge, procedural knowledge and reasoning knowledge involved in the coastal hydraulic and transport processes. The system is developed through employing Visual Rule Studio, a hybrid expert system shell, as an ActiveX Designer under Microsoft Visual Basic 6.0 environment since it combines the advantages of both production rules and object-oriented programming technology. The architecture, the development and the implementation of the prototype system are delineated in details. Based on the succinct features and conditions of a variety of flow and water quality models, three kinds of class definitions, Section and Problem as well as Question are defined and the corresponding knowledge rule sets are also established. Both forward chaining and backward chaining are used collectively during the inference process. A typical example is also presented to demonstrate the application of the prototype knowledge management system.

Flood control management system for reservoirs

Abstract Flood disaster is one of the most damaging natural disasters in China, with annual average losses more than 200 billion yuan in recent years. After 1995 floods in the Liaohe River and 1998 floods in the Yangtze River, the governments from national to local have realized that the flood control operation of reservoirs can play a major role in alleviating flood losses but there are some problems in flood control management for reservoirs. Most of the existing flood control management systems for reservoir were established for special purposes and are lack of data share and communication with governments, it is very difficult for decision-making departments to get real-time information in short time. Thus, a national programming about flood control management system for reservoirs is presented. The paper is a summary of the outcome of national programming about the flood control management system for reservoirs in China. The background, objectives, main challenges and main contents of the programming are introduced. The main focus is on the issues of the software integration flood control management system for reservoirs. Emphasis is concentrated on the flowchart design of the system and its core components. The current system can be applied to a river control center or a single reservoir because of using the national standard databases and easily integrated into the national flood control system in the future. An application system is briefly introduced in order to understand the system.

Short-Term Scheduling for Large-Scale Cascaded Hydropower Systems with Multivibration Zones of High Head

AbstractConstruction of huge hydropower plants in the southern region of China has been rapidly increasing in recent years. These plants usually have multiple vibration zones of high head that have a great effect on short-term scheduling and real-time operations. This paper presents a novel approach for optimizing short-term scheduling of large-scale cascaded hydropower systems with multivibration zones of high head. For the purpose of cutting down peak loads, standard deviation minimization relevant to the remaining load series for thermal systems was chosen as the objective nonlinear function. Before the optimization, unit forbidden operation zones were identified by assembled mathematical techniques and hydro unit commitments were optimized using dynamic programming. The combined sets of forbidden operation zones and hydro unit commitments were repeatedly used during the search process. An optimization framework that combined the progressive optimality algorithm with a vibration zone avoidance strategy...

Parallel discrete differential dynamic programming for multireservoir operation

The curse of dimensionality and computational time cost are a great challenge to operation of large-scale hydropower systems (LSHSs) in China because computer memory and computational time increase exponentially with increasing number of reservoirs. Discrete differential dynamic programming (DDDP) is one of the most classical algorithms for alleviating the dimensionality problem for operation of LSHSs. However, the computational time performed on DDDP still increases exponentially with increasing number of reservoirs. Therefore, a fine-grained parallel DDDP (PDDDP) algorithm, which is based on Fork/Join parallel framework in multi-core environment, is proposed to improve the computing efficiency for long-term operation of multireservoir hydropower systems. The proposed algorithm is tested using a huge cascaded hydropower system located on the Lancang River in China. The results demonstrate that the PDDDP algorithm enhances the computing efficiency significantly and takes full advantage of multi-core resources, showing its potential practicability and validity for operation of LSHSs in future.

A web-based flood forecasting system for Shuangpai region

Traditional flood forecasting and operation of reservoirs in China are based on manual calculations by hydrologists or through standalone computer programs. The main drawbacks of these methods are long forecasting time due to time-consuming nature, individual knowledge, lack of communication, absence of experts, etc. A Web-based flood forecasting system (WFFS), which includes five main modules: real-time rainfall data conversion, model-driven hydrologic forecasting, model calibration, precipitation forecasting, and flood analysis, is presented in this paper. The WFFS brings significant convenience to personnel engaged in flood forecasting and control and allows real-time contribution of a wide range of experts at other spatial locations in times of emergency. The conceptual framework and detailed components of the proposed WFFS, which employs a multi-tiered architecture, are illustrated. Multi-tiered architecture offers great flexibility, portability, reusability and reliability. The prototype WFFS has been developed in Java programming language and applied in Shuangpai region with a satisfactory result. sult.