改进蚁群算法及其在水利工程项目管理中的应用

为了更加有效解决水利工程项目管理中的多目标决策问题,提出了一种改进蚁群算法。该算法首先利用遗传算法的全局搜索能力将信息素初始化,然后在算法进行遍历过程中引入变异操作和交叉操作,提高算法的鲁棒性和有效性。水利工程项目多目标优化案例分析表明,较传统遗传算法和蚁群算法,本文提出的方法对于解的寻找速度更快,解的质量更高,该算法具有较高的全局寻优能力。该研究为水利工程项目管理多目标决策问题的解决提供了一种新的思路和方法。     

基于组合决策的黄河流域水量调度方案评价方法

为定量评价黄河流域水量调度方案的优劣,选出水资源综合效益最大的方案,结合黄河流域实际特点,选择可供水量、利津入海水量、龙羊峡水库期末水位等10项指标为评价体系,在模糊优选法、灰色关联分析法、集对分析法等评价方法的基础上建立了组合决策模型,综合考虑各方案在不同评价方法下的优劣顺序,帮助决策者做出准确判断和选择。结果表明,组合决策方法克服了单一决策方法的不足,能够综合考虑各评价指标的重要性,较为科学合理地确定出最优方案。     

引江济淮工程（河南段）多目标水量优化调度

引江济淮工程（河南段）涉及河道、闸泵、管道和调蓄水库,约束条件复杂,常规的优化调度算法难以搜索可行解,求解效率低。选用受水区缺水率平均值最小、泵站总抽水量最小和受水区缺水率标准差最小作为目标函数,从供水保障、供水成本和公平性角度构建多目标水量优化调度模型。基于可行搜索思路,结合逆序演算和顺序演算过程对约束条件进行处理,引入决策系数,通过映射关系使搜索空间保持在可行域中,结合多目标非支配排序遗传算法（non-dominated sorting genetic algorithms,NSGA-II）进行求解,得到Pareto最优解集,并采用熵权法进行方案优选。结果表明,基于可行搜索的NSGA-II算法能够有效求解复杂调度系统的多目标优化问题,综合考虑多个目标的最优方案相对单目标方案更加合理,结果可为引江济淮工程（河南段）运行管理提供决策支撑。     

A Life Cycle Oriented Multi‑objective Optimal Maintenance of Water Distribution: Model and Application

Aiming at trading off several conflicting criteria in practical maintenance in a deteriorating water distribution network, a life cycle oriented multi-objective optimization model of water distribution network maintenance is developed, which is composed of seven interrelated sub-models with different functions. This model can provide decision support for preventive maintenance decision, including identifying the pipeline that needs to be maintained, judging the time point for maintenance, determining the type of maintenance technology, calculating the economic cost of maintenance, and presenting the impact under different maintenance strategies. Based on the life cycle of each pipeline, multiple effects in the water distribution can be dynamically evaluated, such as pipeline age, failure rate, hydraulic reliability health level etc. Based on special design of chromosome gene encoding, the algorithm of elitist Non-dominated Sorting Genetic Algorithm (NSGA-II) is incorporated to achieve multi-objective optimization solution effectively. With application of a county in Zhejiang province in China, three strategies including empirical decision single-objective optimization decision and multi-objective optimization decision are evaluated and compared to the baseline systematically. Although the annual maintenance cost of strategy III is not the lowest among those three strategies, the pipeline age, failure rate, hydraulic reliability, and health level of the water distribution network under the strategy are at the best level. With multiple objectives considered simultaneously, the results of strategy III are recommended as the optimal maintenance implementation arrangements. This model can promote to find an optimal maintenance strategy, and provide a technical support for the planning, design and implementation of maintenance arrangements of water distribution network in a long-term period.

     

FUZZY OPTIMAL DECISIONS FOR MULTIOBJECTIVE FLOOD CONTROL SYSTEM OF CASCADE RESERVOIRS

１．　ＩＮＴＲＯＤＵＣＴＩＯＮＴｈｅｏｐｅｒａｔｉｏｎｄｅｃｉｓｉｏｎｓｏｆｍｕｌｔｉｏｂｊｅｃｔｉｖｅｆｌｏｏｄｃｏｎｔｒｏｌｓｙｓｔｅｍｓａｒｅｎｏｔｏｎｌｙｒｅｌａｔｅｄｔｏｔｈｅｓａｆｅｔｙｏｆｗｈｏｌｅｓｙｓｔｅｍａｎｄｔｈｅｆｌｏｏｄｄａｍａｇｅｌｏｓｓ，ｂｕｔａｌｓｏｈａｖｅｇｒｅａｔｉｎｆｌｕｅｎｃｅｏｎｔｈｅｉｒｃｏｍｐｒｅｈｅｎｓｉｖｅｂｅｎｅｆｉｔ．Ｉｔｉｓｖｅｒｙｉｍｐｏｒｔａｎｔｔｏｓｔｕｄｙｔｈｅｐｒａｃｔｉｃａｌａｎｄｅｆｆｅｃｔｉｖｅｍｅｔｈｏｄｓｏｆｆｌｏｏｄ…     

Multi-Criteria Decision Analysis for the Purposes of Groundwater Control System Design

The best way for an engineer or scientist to express their knowledge, experience and opinions is day-to-day verbal communication. When a decision needs to be made about an optimal groundwater control system, the decision-making criteria need not always be numerical values. If fuzzy logic is used in multi-criteria decision-making, the criteria are described by linguistic variables that can be represented through fuzzy membership and expert judgment is used to describe such a system. Prior hydrodynamic modeling of the aquifer regime defines the management scenarios for groundwater control and provides an indication of their effectiveness. In this paper, the fuzzy analytic hierarchy process is applied to deal with a trending decision problem such as the selection of the optimal groundwater management system. Linguistic variables are used to evaluate all the criteria and sub-criteria that influence the final decision and the numerical weights of each alternative are determined by mathematical calculations. The paper presents a part of the algorithm – fuzzy optimization in hydrodynamic analysis, which leads to the selection of the optimal groundwater control system. The proposed method is applied in a real case study of an open-cast mine.     

多目标系统模糊关系优选决策理论与应用

本文将模糊优选与模糊关系有机的结合起来，提出了多目标系统模糊关系优选决策理论，它可用于解决多目标水资源与农业系统，多目标社会和经济系统等的决策问题。     

水环境污染系统规划的模糊非线性规划模型

本文将模糊集理论与非线性规划优化方法有机地结合起来，首次提出水环境污染系统规划的模糊非线性规划模型．并将它应用于沈阳市南部污水排放系统的最优化处理规划．在满足水质要求的同时，可以显著地降低污水处理的总费用．     

Application of the modified fibonacci search-based search beam method to derive a nondominated release policy for a multi-purpose reservoir

One of the most serious problems of water resources development planning is the lack of acceptable procedures to deal with conflicts among different purposes at the early conceptual planning stage of any water resources system. As far as the consideration of formulating planning strategies is concerned, a new interactive multi-objective decision making (MODM) is approach, the search beam method (SBM) has been conceived. This model is expected to provide a reliable systematic procedure to search for the nondominated solutions along prespecified lines representing hypothetical search beams (SB) in the objective space. The proposed SBM consists of two major parts, an optimization phase and a subsequent evaluation phase. Incremental dynamic programming (IDP), one of the best known approximative techniques of dynamic programming (DP), is applied in the optimization phase. The modified Fibonacci search is heuristically used to seek, in a successive search for the intersection with the Pareto optimal surface along each SB. The viability of the SBM is demonstrated by applying it to an existing single unit reservoir system. This reservoir is assumed to accommodate two conflicting objectives: maximizing hydropower generation and maximizing water surface elevation to sustain accessibility of the navigation structures and to enable low head pumping of irrigation water.     

An Inexact Chance-constrained Quadratic Programming Model for Stream Water Quality Management

Water quality management is complicated with a variety of uncertainties and nonlinearities. This leads to difficulties in formulating and solving the resulting inexact nonlinear optimization problems. In this study, an inexact chance-constrained quadratic programming (ICCQP) model was developed for stream water quality management. A multi-segment stream water quality (MSWQ) simulation model was provided for establishing the relationship between environmental responses and pollution-control actions. The relationship was described by transformation matrices and vectors that could be used directly in a multi-point-source waste reduction (MWR) optimization model as water-quality constraints. The interval quadratic polynomials were employed to reflect the nonlinearities and uncertainties associated with wastewater treatment costs. Uncertainties associated with the water-quality parameters were projected into the transformation matrices and vectors through Monte Carlo simulation. Uncertainties derived from water quality standards were characterized as random variables with normal probability distributions. The proposed ICCQP model was applied to a water quality management problem in the Changsha section of the Xiangjiang River in China. The results demonstrated that the proposed optimization model could effectively communicate uncertainties into the optimization process, and generate inexact solutions containing a spectrum of wastewater treatment options. Decision alternatives could then be obtained by adjusting different combinations of the decision variables within their solution intervals. Solutions from the ICCQP model could be used to analyze tradeoffs between the wastewater treatment cost and system-failure risk due to inherent uncertainties. The results are valuable for supporting decision makers in seeking cost-effective water management strategies.     

Modelling Intelligent Water Resources Allocation for Multi-users

This study proposes intelligent water resources allocation strategies for multiple users through hybrid artificial intelligence techniques implemented for reservoir operation optimization and water shortage rate estimation. A two-fold scheme is developed for (1) knowledge acquisition through searching input–output patterns of optimal reservoir operation by optimization methods and (2) the inference system through mapping the current input pattern to estimate the water shortage rate by artificial neural networks (ANNs). The Shihmen Reservoir in northern Taiwan is the study case. We first design nine possible water demand conditions by investigating the changes in historical water supply. With the nine designed conditions and 44-year historical 10-day reservoir inflow data collected during the growth season (3 months) of the first paddy crop, we first conduct the optimization search of reservoir operation by using the non-dominated sorting genetic algorithm-II (NSGA-II) in consideration of agricultural and public water demands simultaneously. The simulation method is used as a comparative model to the NSGA-II. Results demonstrate that the NSGA-II can suitably search the optimal water allocation series and obtain much lower seasonal water shortage rates than those of the simulation method. Then seasonal water shortage rates in response to future water demands for both sectors are estimated by using the adaptive network fuzzy inference system (ANFIS). The back-propagation neural network (BPNN) is adopted as a comparative model to the ANFIS. During model construction, future water demands, predicted monthly inflows (or seasonal inflow) of the reservoir in the next coming quarter and historical initial reservoir storages configure the input patterns while the optimal seasonal water shortage rates obtained from the NSGA-II serve as output targets (training targets) for both neural networks. Results indicate that the ANFIS and the BPNN models produce almost equally good performance in estimating water shortage rates, yet the ANFIS model produces even better stability. The reliability of the proposed scheme is further examined by scenario analysis. The scenario analysis indicates that an increase in public water demand or a decrease in agricultural water demand would bring more impacts of water supply on agricultural sectors than public sectors. Similarly, a bigger decrease in inflow amount would obviously bring more influence on agricultural sectors than public one. Consequently, given predicted inflow, decision makers can pre-experience the possible outcomes in response to competing water demands through the estimation models in order to determine adequate water supply as well as preparedness measures, if needed, for drought mitigation.     

水资源优化配置方案综合评价的模糊熵模型

由于水资源优化配置方案具有多目标性和模糊不相容性的特点,在模糊理论分析的墓础上,结合欧氏贴近度的概念,建立了基于欧氏贴近度的水资源优化配置方案综合评价的模糊优选模型。模型中基于信息熵建立了专家自身权重模型来修正层次分析法得到的指标主观权重,得到的指标融合权重减少了权重确定的主观性。以天津市水资源优化配置方案综合评价为例介绍了该模型的具体运用,该模型为水资源优化配置方案综合计价提供了一种新的决策方法。     

Application of ANN, Fuzzy Logic and Decision Tree Algorithms for the Development of Reservoir Operating Rules

Optimal use of scarce water resources is the prime objective for water resources development projects in the developing country like India. Optimal releases have been generally expressed as a function of reservoir state variables and hydrologic inputs by a relationship which ultimately allows the policy/water managers to determine the water to be released as a function of available information. Optimal releases were obtained by using optimal control theory with inflow series and revised reservoir characteristics such as elevation area capacity table, zero elevation level as input in this study. Operating rules for reservoir were developed as a function of demand, water level and inflow. Artificial Neural Network (ANN) with back propagation algorithm, Fuzzy Logic and decision tree algorithms such as M5 and REPTree were used for deriving the operating rules using the optimal releases for an irrigation and power supply reservoir, located in northern India. It was found that fuzzy logic model performed well compared to other soft computing techniques such as ANN, M5P and REPTree investigated in this study.     

Basin Scale Water Resources Systems Modeling Under Cascading Uncertainties

Global change in climate and consequent large impacts on regional hydrologic systems have, in recent years, motivated significant research efforts in water resources modeling under climate change. In an integrated future hydrologic scenario, it is likely that water availability and demands will change significantly due to modifications in hydro-climatic variables such as rainfall, reservoir inflows, temperature, net radiation, wind speed and humidity. An integrated regional water resources management model should capture the likely impacts of climate change on water demands and water availability along with uncertainties associated with climate change impacts and with management goals and objectives under non-stationary conditions. Uncertainties in an integrated regional water resources management model, accumulating from various stages of decision making include climate model and scenario uncertainty in the hydro-climatic impact assessment, uncertainty due to conflicting interests of the water users and uncertainty due to inherent variability of the reservoir inflows. This paper presents an integrated regional water resources management modeling approach considering uncertainties at various stages of decision making by an integration of a hydro-climatic variable projection model, a water demand quantification model, a water quantity management model and a water quality control model. Modeling tools of canonical correlation analysis, stochastic dynamic programming and fuzzy optimization are used in an integrated framework, in the approach presented here. The proposed modeling approach is demonstrated with the case study of the Bhadra Reservoir system in Karnataka, India.     

灌区水资源实时优化调度

根据实时调度原理及农业水资源配置特点,建立了分层耦合的水资源实时优化调度模型,该模型包括供需水中长期预测、中长期优化配置、供需水实时预报、短期渠系配水和基于模糊识别的实时修正5个模块,应用该模型可实现对预报、决策、实施、修正的滚动向前调度。在中长期优化调度模块中提出了利用模糊聚类和马尔科夫时间序列的预测方法对有效降水量进行预测,并根据预测的年型计算作物需水量和地下水可开采量。实例计算表明,应用该模型实行的实时优化调度与各种供水已知情况下的理想最优调度方案偏差较小。     

Optimal Allocation of Flood Control Capacity for Multi-Reservoir Systems Using Multi-Objective Optimization Approach

Operation of multi-reservoir systems during flood periods is of great importance in the field of water resources management. This paper proposes a multi-objective optimization model with new formulation for optimal operation of multi-reservoir systems. In this model, the release rate and the flood control capacity of each reservoir is considered as decision variable and the resulting nonlinear non-convex multi-objective optimization problem is solved with ε-constraint method through the mixed integer linear programming (MILP). Objective functions of the model are minimizing the flood damage at downstream sites and the loss of hydropower generation. The developed model is used to determine optimal operating strategies for Karkheh multi-reservoir system in southwestern Iran. For this purpose, the model is executed in two scenarios based on “two-reservoir” and “six-reservoir” systems and for floods with return periods of 25 and 50 years. The results show that in two-reservoir system, flood damage is at least about 114 million dollars and cannot be mitigated any further no matter how hydropower generation is managed. But, in the case of developing all six reservoirs, optimal strategies of coordinated operation can mitigate and even fully prevent flood damage.     

Artificial intelligence technologies in surface water quality monitoring

Abstract:

Water quality monitoring networks are designed to detect, evaluate, arid quantify past, present, and emerging water quality problems and trends. A review of strategies to design monitoring networks suggests that a structured and consistent design methodology is for the most part missing. Monitoring network design is a complex task that requires an optimal configuration to ensure the maximum information extraction from the water quality data collected. In order to attain an optimal, and ultimately cost‐effective, network design, complementary design techniques or tools are needed. An overview of potentially applicable artificial intelligence technologies, as well as a literature review of promising research undertaken in the water resources area with respect to artificial intelligence techniques are presented. The artificial intelligence technologies examined include expert systems, artificial neural networks, genetic algorithms, and fuzzy logic systems.     

基于并行混沌量子粒子群算法的梯级水库群防洪优化调度研究

梯级水库群防洪优化调度问题规模庞大、结构复杂,涉及大量的决策变量和复杂的约束条件,各水库、各时段之间的水位、流量存在复杂的耦合关系,呈现出高维度、非线性、强约束特性,传统的优化方法难以直接求解或者计算效率低,存在早熟收敛问题。研究工作试图将量子粒子群算法(QPSO)引入到水库群防洪优化调度问题中,为了提高算法的全局搜索能力和收敛性能,对标准QPSO做了改进,包括利用混沌思想初始化种群、自适应激活机制和精英粒子混沌局部搜索策略3个方面,并引入多核并行计算技术以降低计算时间,提出了并行混沌量子粒子群算法(PCQPSO),函数测试证明了PCQPSO的可行性、稳定性和高效性。将PCQPSO应用到水库群防洪优化调度问题中,与POA、QPSO进行对比分析,结果表明PCQPSO收敛效率快、求解精度高,为解决梯级水库群防洪优化调度问题提供了一种有效的新思路。     

A Compromise Ratio Method with an Application to Water Resources Management: An Intuitionistic Fuzzy Set

Water resources management can be regarded as an iterative process of general decision making considering the applications and modifications of waters and related lands within a geographic region. This process helps decision makers to balance their diverse requirements and applications of water as an environmental resource, and to recognize how their activities can have impacts on the long-term sustainability. This paper introduces a new compromise ratio method based on Atanassov’s intuitionistic fuzzy sets under multiple criteria in real-life situations. Atanassov’s intuitionistic fuzzy weighted averaging (AIFWA) operator is applied to aggregate individual judgments of the decision makers to rate the relative importance of the selected criteria and potential alternatives. Then a new Atanassov’s intuitionistic fuzzy ranking index is proposed to analyze the potential alternatives. Finally, the performance of the proposed fuzzy decision-making method is illustrated to a real water resources management problem from the recent literature. Computational results demonstrate that the presented method can be utilized in a large-scale multi-level assessment process to assist the decision makers the optimal solution among the potential alternatives with multiple conflicting and compromising criteria.     

基于概率三角模糊数的水资源多属性决策方法研究

水资源优化配置的决策方案的许多指标和权重往往是定性的,因此如何较合理的处理这些指标和权重是解决优化配置的关键所在。针对定性指标和精确指标混合情况下的水资源多属性决策问题,引入三角模糊数相互比较的可能度概念及模糊比率刻度概念,使定性指标及权重在决策中以三角模糊数形式的规范表示,研究各决策指标在非统一概率分布下的三角模糊数决策矩阵的综合评价方法,使决策评价结果更加合理,切合实际。实例计算表明水资源多属性决策方法简单可行,得到的最优方案与专家们对方案的倾向性意见一致。