Cheng Chuntian

New similarity measures of intuitionistic fuzzy sets and application to pattern recognitions

The concept of an intuitionistic fuzzy set (IFS), which is a generalization of the concept of a fuzzy set (FS), has been introduced by K. Atanassov. Although many measures of similarity between FSs have been proposed in the literature, those measures cannot deal with the similarity measures between IFSs. In this paper, first, the definition of the degree of similarity between IFSs is introduced. Then, several new similarity measures between IFSs are proposed and corresponding proofs are given. Finally, the similarity measures of IFSs are applied to pattern recognitions.

Three-person multi-objective conflict decision in reservoir flood control

Reservoir flood control decisions are often compromised by various parties with conflicting benefits. In this paper, a three-person multi-objective conflict decision model is presented for reservoir flood control. In order to obtain the group decision, the ideal bargaining solution is first sought by two stages satisfying programming and then the decision alternative is chosen using the fuzzy pattern recognition. The advantages of this model are simple and more adaptable to the real problem. The model is demonstrated by application to Fengman Reservoir in China.

Fuzzy optimal model for the flood control system of the upper and middle reaches of the Yangtze River

Abstract Based on the characteristics of the Yangtze River floods and the principles of fuzzy sets theory, a fuzzy optimal model has been established for the flood system of the upper and middle reaches of this river. The system is divided into three subsystems with specific flood control objectives. The Three-Gorges Reservoir plays an important role in the system. A method for producing flood operation alternatives of the Three-Gorges Reservoir is presented. Finally, the model is validated with three typical historical floods. The results show that the model is effective and flexible.

Fuzzy multiobjective programming methods for fuzzy constrained matrix games with fuzzy numbers

The purpose of the paper is to introduce a new type of fuzzy matrix games: fuzzy constrained matrix games. A computational method for its solution based on establishment of the auxiliary fuzzy linear programming for each player is proposed. The approach based on the multiobjective programming is established to solve these fuzzy linear programming. Effectiveness is illustrated with a numerical example.The purpose of the paper is to introduce a new type of fuzzy matrix games: fuzzy constrained matrix games. A computational method for its solution based on establishment of the auxiliary fuzzy linear programming for each player is proposed. The approach based on the multiobjective programming is established to solve these fuzzy linear programming. Effectiveness is illustrated with a numerical example.

Parallel stochastic dynamic programming for long-term generation operation of cascaded hydropower stations

Stochastic Dynamic Programming (SDP) for long-term generation operation of cascaded hydropower stations will bring about the curse of dimensionality, resulting in the rapid increase of computational time and the decrease of computational efficiency. Therefore, alleviate the dimensionality problem and improve the computational efficiency are always difficult issues for long-term generation operation of cascaded hydropower stations. On the basis of the parallelism analysis for SDP, a parallel stochastic dynamic programming (PSDP) based on Fork/Join parallel framework was proposed. In this method, all computational tasks for the returns from all discrete combinations in one stage were taken as parent task, which was decomposed into several subtasks by divide-and-conquer method. After this, the decomposed subtasks were solved in different cores respectively for achieving fine-grain parallel computation. The proposed approach was implemented to long-term generation operation of cascaded hydropower stations located on Lancangjiang River, and 3 different schemes with different discrete number of variables were established for testing the computational efficiency in multi-core environment. The result shows that the computational time, compared with serial computation, decreased respectively about 50% in 2-core environment and 70% in 4-core environment, making full use of multi-core resources. In addition, the larger computational scale can reduce more computational time in multi-core environment. Hence, the proposed approach is effective for operation of large-scale hydropower system, and can provide guidance for other applications.

Knowledge rules dimensionality reduction method for multi-reservoir joint operation optimization

In general, reservoirs were used for many purposes, such as power generation, flood control, navigation, zoology and so on. During the process of modelling, we should consider the interest demand of relevant departments represented by water resources, electric power sector and environmental protection administration. Thus, there are numerous complex constraints with different forms in the operation model of multi-reservoir system. These constraints have such comprehensive effects as delivery, intertexture and coupling, which narrows the feasible region characterized by the complex spatiotemporal features and makes it hard for optimization method to enhance the quality of solution. Hence, based on the set operation theory, we proposed the knowledge rules dimensionality reduction method that combines multiple different operation constraints of multi-reservoir system. According to actual problems, the proposed method first identify the feasible region of single reservoir at one stage, two stages and multiple stages. Then, the feasible search space for multi-reservoir system can be identified by the dynamic coordination of various reservoirs. In this way, the infeasible state and decision variables can be removed during the calculation process of the optimization method. The results demonstrate that the proposed method can reduce the difficulty of the system modeling and calculation, and ensure the feasibility and availability of the scheduling process.

Daily rainfall-runoff forecasting using Bayesian echo state network

The echo state network (ESN) is simpler and costs less training time than traditional recurrent neural networks. Due to linear regression algorithm usually adopted by standard ESN to calibrate model parameters, the over-fitting phenomenon easily occurs. To overcome this shortcoming, a Bayesian echo state network (BESN) model is proposed for daily rainfall-runoff forecasting. The BESN model combined Bayesian theory and ESN obtains the optimal output weights via maximizing posterior probabilistic density and improves its generalization ability. Two Case studies on daily inflow forecasting for Ansha Reservoir and Xinfengjiang Reservoir show that the BESN model is effective and feasible and can provide better forecast accuracy than the traditional BP neural network and ESN models.

A hybrid nonlinear optimization method for operation of large-scale cascaded hydropower plants

This paper develops a hybrid nonlinear optimization method for solving long-term optimal operation of large-scale cascaded hydropower plants with complex spatial coupling constraints. This method proposes conversion factors relevant to generation and discharge in order to cope with complex nonlinear total generation limitation considered in the optimization problem. Thus, the original nonlinear optimization problem can be broken down into a sequence of standard quadratic programming sub-problems. A combination of progressive optimality algorithm (POA) and quadratic programming (QP) method is employed to optimize the operation of hydropower systems. The results obtained from POA are first chosen as the initial solution of QP, which also decide the feasible decision space. During the solution process, the previous conversion factors are dynamically updated depending on the destroying range of total generation limitation. The boundary values of these constraints are accordingly modified in the new QP model. Solving the QP problem and updating the convention factors are performed alternately until the optimal solution or satisfactory solution for original problem is obtained. The proposed hybrid nonlinear method is applied to scheduling Hongshui River cascaded hydropower plants. The simulation results show that our method can enhance the total power generation in dry season and produce more energy than POA.

Discrete process neural networks and its application in the predication of sunspot number series

Considering that inputs of a process neural network (PNN) are generally time-varying functions while the inputs of many practical problems are discrete values of multiple series, in this paper, a process neural network with discrete inputs is presented to provide improved forecasting results for solving the complex time series prediction. The presented method first makes discrete input series carry out Walsh transformation, and submits the transformed series to the network for training. It can solve the problem of space-time aggregation operation of PNN. In order to examine the effectiveness of the presented method, the actual data of sunspots during 1749–2007 are employed. To predict the number of sunspots, the suitability of the developed model is examined in comparison with the other models to show its superiority and be an effective way of improving forecasting accuracy of networks.