改进遗传算法及其在水库群优化调度中的应用

根据梯级水电站优化调度特点,建立遗传算法(GA)求解多阶段最优化问题的数学模型.针对标准遗传算法(sGA)局部寻优能力较差、易早熟等不足之处,从编码方法、遗传算子和混合算法方面对其进行改进,提出了采用超立方体浮点数编码自适应遗传算法(AGA)和超立方体浮点数编码遗传模拟退火算法(SA-GA).通过16种不同策略的GA在雅砻江梯级优化调度中的应用,其结果表明了改进策略在解决水库群优化问题方面的有效性和优越性.最后将GA与动态规划(DP)算法的性能进行比较分析,充分体现了GA的优点.     

遗传算法在水库调度中的应用综述

简要回顾了遗传算法在水库调度中的应用概况,对遗传算法用于水库调度优化时的编码、约束条件处理、早熟与全局收敛性、参数设置、混合遗传算法、多目标遗传算法以及效率评定准则等问题进行了综述。分析遗传算法耗时与全局收敛之间的矛盾后认为,遗传算法适用于传统方法难以求解的优化问题,以及对计算时效性要求不高或者目标函数计算复杂度不高的实时水库调度问题,特别是水库中长期调度以及水资源规划问题。     

水电站水库优化调度的改进混沌遗传算法

针对水电站水库优化调度问题,提出了将改进遗传算法和混沌优化相耦合的改进混沌遗传算法。该算法将混沌变量映射到优化变量的取值范围中,对混沌变量进行编码,表示成染色体,然后对其进行选择、交叉和变异,通过增加混沌扰动,不断进化收敛得到最优解。实例计算并与其他方法比较表明,该算法在求解水电站优化调度这样的复杂非线性优化问题时,搜索效率高,收敛性能好,能以较快的速度收敛于全局最优解,为水电站水库优化调度模型求解提供了一种新方法。     

Optimization of Hydropower Reservoir Using Evolutionary Algorithms Coupled with Chaos

Over the past decade, several conventional optimization techniques had been developed for the optimization of complex water resources system. To overcome some of the drawbacks of conventional techniques, soft computing techniques were developed based on the principles of natural evolution. The major difference between the conventional optimization techniques and soft computing is that in the former case, the optimal solution is derived where as in the soft computing techniques, it is searched from a randomly generated population of possible solutions. The results of the evolutionary algorithm mainly depend on the randomly generated initial population that is arrived based on the probabilistic theory. Recent research findings proved that most of the water resources variables exhibit chaotic behavior, which is a projection depends upon the initial condition. In the present study, the chaos algorithm is coupled with evolutionary optimization algorithms such as genetic algorithm (GA) and differential evolution (DE) algorithm for generating the initial population and applied for maximizing the hydropower production from a reservoir. The results are then compared with conventional genetic algorithm and differential evolution algorithm. The results show that the chaotic differential evolution (CDE) algorithm performs better than other techniques in terms of total annual power production. This study also shows that the chaos algorithm has enriched the search of general optimization algorithm and thus may be used for optimizing complex non-linear water resources systems.     

基于试验遗传算法的平原圩区除涝排水系统最优规划

平原圩区除涝排水系统最优规划是一个多维、非线性复杂系统优化问题。本文提出基于试验优化设计思想的试验遗传算法，即在标准遗传操作中增加了均匀设计、正态随机和摄动调优等试验操作技术。某圩区排水系统最优规划实例表明，与可分规划法及简单遗传算法相比，试验遗传算法能严格满足系统约束条件，且操作简单，计算效率更高。由于该算法兼顾了整体空间的种群多样性和局部空间极小值的搜索效率，同时能根据需要自动调整计算精度，因此较易获得复杂问题的全局最优解。     

鲸鱼优化算法在水库优化调度中的应用

为验证鲸鱼优化算法在水库优化调度求解中的可行性和有效性,采用4个典型测试函数对鲸鱼优化算法进行仿真验证,并与布谷鸟搜索算法、差分进化算法、混合蛙跳算法、粒子群优化算法、萤火虫算法和SCE-UA算法共6种算法的仿真结果进行对比分析;将鲸鱼优化算法与6种对比算法应用于某单一水库和某梯级水库中长期优化调度求解。结果表明:鲸鱼优化算法寻优精度高于其他6种算法8个数量级以上,具有收敛速度快、收敛精度高和极值寻优能力强等特点;鲸鱼优化算法单一水库和梯级水库优化调度结果均优于其他6种算法;鲸鱼优化算法应用于水库优化调度求解是可行和有效的。     

粒子群算法在水库(群)优化调度研究中的应用综述

简要介绍粒子群算法的工作原理和水库(群)优化调度模型,然后较全面地阐述粒子群算法在水库(群)优化调度中的应用及存在的问题,最后总结了算法的各种改进,并对粒子群算法在水库(群)中的研究进行了展望。     

Water pollution control in the river basin by fuzzy genetic algorithm-based multiobjective programming modeling

Designing water quality management strategies is often complicated by the difficulty in simultaneously considering large amounts of relevant data, applicable submodels, competing objectives, unquantifiable factors, nonlinear characteristics, and uncertainty during parameterization. Mathematical optimization techniques offer promise in identifying optimal or satisfactory strategies that may be used as benchmarks for decision making. Newer optimization techniques such as genetic algorithm (GA) and fuzzy mathematical programming make the search for optimal control strategies in an uncertain environment more feasible. Using a probabilistic search procedure that emulates Darwinian natural selection, GAs allow multicriteria decision making with respect to both nonlinear feature and fuzzy characteristics to be incorporated directly into the optimization process and generate trade-off curves between cost and environmental quality while identifying good control strategies. This paper verifies such a discovery by a case study of water quality control in the Tseng-Wen river basin in Taiwan.     

Flood Control Operation of Reservoir Group Using Yin-Yang Firefly Algorithm

Flood control operation (FCO) of a reservoir is a complex optimization problem with a large number of constraints. With the rapid development of optimization techniques in recent years, more and more research efforts have been devoted to optimizing FCO problems. However, for solving large-scale reservoir group optimization problem, this is still a challenging task. In this work, a reservoir group FCO model is established with minimum flood volume stored in each reservoir and minimum peak flow of downstream control point during the dispatch process. At the same time, a flood forecast model for FCO of a reservoir group is developed by coupling Yin-Yang firefly algorithm (YYFA) with ε constrained method. As a case study, the proposed model is applied to a three-reservoir flood control system in Luanhe River Basin consisting of reservoirs, river channels, and downstream control points. Results show that optimal operation of three reservoirs systems can efficiently reduce the occupied storage capacity for flood control and flood peaks at downstream control point of the basin. The proposed method can be extended to FCO of other reservoir groups with similar conditions.

     

Fuzzy Systems Tuned By Swarm Based Optimization Algorithms for Predicting Stream flow

River flow prediction is an important phenomenon in water resources for which different methods and perspective have been used. Using fuzzy system with black box perspective is one of them. Fuzzy systems have some parameters and properties that have to be determined. This is an optimization problem that can be solved by swarm optimization techniques among several techniques. Swarm optimization are developed by inspiring from the behavior of the animals living as swarm. The study presents two achievements fuzzy system that tuned by swarm optimization algorithms can be used for prediction of monthly mean streamflow and which swarm optimization algorithm is better than the others for tuning fuzzy systems. Three swarm optimization algorithms, hunter search, firefly, artificial bee colony are used in this study. These algorithms are compared with mean performance values and convergence speed. Monthly streamflow data of three stream gauging stations in Susurluk Basin are used for the case study. The results show, swarm optimization algorithms can be used for prediction of monthly mean streamflow and ABC algorithm has better performance values than other optimization algorithms.     

基于引水限制调度线的并联水库系统供水优化算法及应用

以实现梯级水库群或者水源连通工程水量补偿式调节为目标,针对并联水库的联合供水特征,采用引水限制调度线控制引水水库可引水量,引入粒子群算法构建了并联水库优化调度模型。通过优化引水调度线提出可以改进并联水库系统的调度规则和调度方法,将优化和常规调度有机结合,并根据并联水库系统实际运行条件设置模型的目标函数、约束条件和参数设置方法。以X市S水库和L水库组成的并联水库系统为实例,采用该模型进行优化模拟。结果表明:并联水库系统经优化年均弃水量比两库单独供水的弃水量减少5 496万m~3,末库容比两库单独供水时提高203万m~3。在95%供水保证率时,并联水库系统供水系统的年供水能力比双库单独供水能力之和提高了5 556万m~3。优化形成的引水限制调度线分布形态合理,并联供水系统经过优化大幅度提高了水库系统的供水能力,证明了基于引水限制调度线的并联水库系统供水优化算法的可行性,该方法对并联水库联合调度具有重要参考价值。     

基于逐次逼近遗传算法的梯级水库优化调度

利用传统遗传算法求解水库优化调度问题时,经过遗传操作产生的新个体可能是不可行解,因此需要对其进行修正.但在梯级水库调度中,由于各时段间、水库间存在的水力电力联系,使这种修正变得复杂困难.鉴于此,提出了逐次逼近遗传算法(GASA),它可在包含不可行解的空间中寻优,并通过搜索空间的不断改变,逐渐逼近最优解.最后通过一个算例,并与离散微分动态规划法(DDDP)和逐步优化法(POA)的优化结果进行比较,说明了该方法的可行性与有效性.     

滑坡体力学参数反分析研究

除室内试验和现场试验之外,反演分析是一种可以利用现有变形监测数据获取滑坡体等效力学参数的方法.以清江杨家槽滑坡体为例进行研究,提出了将均匀设计、遗传算法与BP神经网络结合起来应用于滑坡体反分析的新方法.先将具有很好全局寻优能力的改进遗传算法作为BP神经网络的学习算法,形成遗传神经网络;然后利用均匀设计方法设计网络学习样本,训练遗传神经网络映射滑坡体变形与滑坡体力学参数的非线性关系;最后将实测位移值作为网络输入,网络输出即为参数的反演值.该方法克服了优化反分析方法反演时间过长,解不易收敛等缺陷,实现了多参数的同时反演.通过对反分析结果进行检验与评价,证明其结果符合实际工程要求.     

改进差分进化算法在水库优化调度中的应用研究

差分进化算法在求解水库优化调度时,进化后期种群多样性急剧下降,导致算法无法跳出局部最优解而出现“早熟”收敛。针对该问题,该文对算法的贪婪选择策略进行改进,使其以一定的概率动态接受稍差解作为子代个体,从而提高算法的种群多样性;同时,提出种群基因重生策略,进一步改善种群进化的基因信息结构。将改进的差分进化算法应用于清江梯级发电调度问题,并与差分进化算法、模拟退火算法求解结果进行对比。模拟结果表明,改进算法具有更强的全局搜索能力,求解梯级水库优化调度问题更具有优势。     

蜂群遗传算法及在水库群优化调度中的应用

介绍了一种基于蜂群繁殖原理的改进遗传算法--蜂群遗传算法(BSGA),采用改进的遗传算子解决了传统遗传算法中"选择压力"和"种群多样性"之间的矛盾.将该算法应用于梯级水库优化调度的研究中,通过对清江梯级水库群优化调度的实例计算,得到了合理的全局最优解,验证了BSGA的可靠性和实用性.     

A Multi-Objective Optimization Model for Coordinated Regulation of Flow and Sediment in Cascade Reservoirs

This paper presents a multi-objective optimization model for the coordinated regulation of flow and sediment in cascade reservoirs. The model was developed to address two contradicting issues: sediment trapping and flow regulation. The benefits of flood control, hydropower generation and navigation, and sedimentation in cascade reservoirs were considered as the target functions; then the corresponding submodels for reservoir operation and sediment computation were established. The model was implemented by reducing it to a single objective nonlinear model using the constraint method. Non-inferior solutions were obtained by solving the model with catfish effect particle swarm optimization algorithm. The model was applied to the cascade system of Xiluodu and Xiangjiaba reservoirs in the lower Jinsha River in the flood recession period. Under the safety of flood control and navigation, a non-inferior set for impounding time, power generation, and siltation-loss rate of capacity was obtained and optimal solutions with different weights were derived. The results demonstrate that the model is a useful tool in coordinated operations of cascade reservoirs.     

Meta-Heuristic Algorithms for Hydrologic Frequency Analysis

Meta-heuristic algorithms, such as the genetic algorithm and ant colony optimization, have received considerable attention in recent years due to their higher ability for solving difficult engineering optimization problems. This paper employs these techniques for estimating parameters of commonly used flood frequency distributions, and compares them with some conventional methods such as maximum likelihood, moments and probability weighted moments using annual maximum discharge data of 14 rivers from East-Azarbaijan, Iran. The results indicate that both the genetic algorithm and ant colony optimization are suitable parameter estimation alternatives. Also, the results of Monte Carlo simulation for various sample sizes, ranging from 20 to 100, demonstrate that the meta-heuristic algorithms yield accurate quantile estimates.     

基于遗传算法的TOPMODEL参数优化

模型参数的确定是模型研制与应用成功与否的关键．一般采用人工经验率定和自动率定两种方法来确定．遗传算法和一般的优化算法不同,它具有全局寻优能力,是一类优秀的非线性函数优化算法．利用遗传算法来进行TOPMODEL参数优化,并和人工率定的计算结果作了简要的对比,明显地显示该方法的优点．采用遗传算法所得到的精度较高,可以类推到其他水文模型的参数优化中去．     

New Approach: Integrated Risk-Stochastic Dynamic Model for Dam and Reservoir Optimization

Multiple studies have developed management models to identify optimal operating policies for reservoirs in the last four decades. In an uncertain environment, in which climatic factors such as stream flow are stochastic, the economic returns from reservoir releases that are based on policy are uncertain. Furthermore, the consequences of reservoir release are not fully realized until it occurs. Rather than explicitly recognizing the full spectrum of consequences that are possible within an uncertain environment, the existing optimization models have focused on addressing these uncertainties by identifying the release policies that optimize the summative metric of the risks that are associated with release decisions. This technique has limitations for representing risks that are associated with release policy decisions. In fact, the approach of these techniques may conflict with the actual attitudes of the decision-makers regarding the risk aspects of release policies. The risk aspects of these decisions affect the design and operation of multi-purpose reservoirs. A method is needed to completely represent and evaluate potential consequences that are associated with release decisions. In this study, these techniques were reviewed from the stochastic model and risk analysis perspectives. Therefore, previously developed optimization models for operating dams and reservoirs were reviewed based on their advantages and disadvantages. Specifically, optimal release decisions that use the stochastic variable impacts and the levels of risk that are associated with decisions were evaluated regarding model performance. In addition, a new approach was introduced to develop an optimization model that is capable of replicating the manner in which reservoir release decision risks are perceived and interpreted. This model is based on the Neural Network (NN) theory and enables a more complete representation of the risk function that occurs from particular reservoir release decisions.     

Conjunctive Operation of Reservoirs and Ponds Using a Simulation-Optimization Model of Irrigation Systems

Water resource management in arid agricultural irrigation regions is a great challenge for managers and decision makers. In some of those regions, many ponds have been built to ensure an adequate water supply for irrigation. Therefore, reservoirs and ponds should be managed conjunctively to minimize shortages of water. In this study, a new integrated mathematical model of conjunctive, or integrated, operation of reservoirs and ponds to maximize the water supply has been proposed for a reservoir-pond irrigation system. This objective has been achieved via the use of two models: an optimal model, which is used to determine the optimal discharge of reservoirs, and a simulation model, which considers the regulatory role of ponds and reservoirs and simulates their water supply to the irrigation system. An adaptive genetic algorithm has been employed in this study to solve the nonlinear and multi-dimensional reservoirs optimization problem. This methodology has been applied to the Yarkant River Basin to demonstrate its applicability, and three scenarios are presented. The main objective of the simulation-optimization model in the Yarkant River Basin is to minimize shortages in meeting irrigation demands for nine sub-irrigation systems subject to the constraint of ecological water transfer to the Tarim River. The optimizing effect of the model was particularly prominent under the third scenario, i.e., the XBD, MMK, and ART Reservoirs and 16 ponds conjunctively operated to meet the water demand of the YKB. The frequency of success (FS) in meeting agricultural water demands reaches up to 75%, and the value for ecological demand is 50.98%. The results demonstrate the importance of the conjunctive combined use approach for management of water resources in irrigation system of arid regions.