差分进化算法在梯级水电站短期优化调度中的应用
|
摘要
我国能源形势紧张,优先和大力发展水电是调整能源结构的必然选择,也是实施可持续发展战略的良好途径。梯级水电站作为电力系统的重要组成部分,正确、合理地安排其运行方式,对整个电力系统的安全、稳定、经济运行至关重要。本文以梯级水电站短期优化调度为核心,对机组最优组合问题和梯级水电站日优化运行问题进行了研究,具有一定的参考价值。
本研究依托国家自然科学基金项目“基于CVAR和随机机会约束规划的水电竞价机理与风险分析”(项目编号50779020),并结合“大洑潭水电站自动发电控制”项目的开发,以梯级水电站短期优化调度为研究基础,以动态规划法及基于混沌序列和可行性规则的改进差分进化算法为优化方法,主要解决了水电站厂内经济运行中的机组最优组合问题和梯级水电站短期经济运行中的日优化调度问题,得到了水电站厂内经济运行总表及梯级水电站日优化运行计划。水电站厂内经济运行是梯级水电站短期优化调度的基础,梯级水电站短期优化调度是水电站厂内经济运行的指导,将两者有机地联系起来即可实现梯级水电站短期发电计划优化方案的制定。
机组组合问题是水电站厂内经济运行的重要内容,具有离散、非凸、非线性等特性,是一个复杂的优化问题,很难找到理论最优解。动态规划法具有的多阶段决策过程特性与水电站厂内经济运行连续性、周期性、分阶段调度的问题十分吻合。本文采用动态规划法来解决机组组合的空间最优化问题,在合理选取机组台数、台号之后,再在选定的机组之间用动态规划法进行负荷优化分配。实例计算结果显示,该方法计算快捷,能够迅速得到经济运行总表,实现厂内经济运行,从而为梯级水电站短期优化调度的实现做好铺垫。
梯级水电站之间由于存在水力联系、电力联系,使得梯级水电站短期优化调度具有复杂的约束条件,并表现为大型、动态、有时滞的非线性问题。传统的优化方法对目标函数限制性要求较强,对约束条件的处理也比较复杂,很难从全局找到最优解。为了克服传统优化方法解决此类问题的不足,本文采用差分进化算法对梯级水电站日优化运行问题求解。为了改善算法的求解性能,提出了基于混沌序列自适应确定变异缩放因子和交叉概率因子的改进的差分进化算法;为了克服罚函数在处理约束条件时惩罚因子不易确定的缺点,提出了基于可行性规则的约束条件处理方法,该方法不必增加额外参数,这是罚函数法所不能及的。本文建立了24个时段内梯级水电系统出力与电网给定负荷偏差总和最小为优化目标函数的数学模型,运用改进的差分进化算法及约束条件处理方法求解,与其它算法相比,优化效果显著,为梯级水电站日优化问题提供了一种新的解决思路和方法。
With the intense Energy situation, developing the hydro power firstly and vigorously is our best choice in order to adjust the energy structure in our country,and it is also a good way to implement the sustainable development strategy. As the electrical power system's important component, short-term economic dispatching of the cascaded hydropower plants plays an important role in the security,stability and economic operation of the whole power system. This thesis takes short-term economic dispatching of the cascaded hydropower plants as the core, and studies the inner-plant economical operation and the daily optimal hydro generation scheduling problem (DOHGSB).
This thesis depends on the State Natural Sciences Foundation project named“the tendering mechanism and risk analysis of hydro power based CVAR and stochastic chance constrained programming”(No.50779020) ,combines the project of the Automatic Generation Control of Da Fu Tan hydro plant, takes short-term economic dispatching of the cascaded hydropower plants as the foundation of the research, and applies dynamic programming and differential evolution algorithm to solve the inner-plant economical operation and the daily optimal hydro generation scheduling problem . There is closely relationship between he daily optimal hydro generation scheduling problem and inner-plant economical operation. Generally speaking,The latter can be considered as the foundation of the former in practical application .This thesis obtains the plan of short-term economic dispatching of the cascaded hydropower plants by taking their relationship into account neatly.
Unit commitment is one of the most important problems in the inner-plant economical operation. Unit commitment is a discrete,non-linear and non-convex complex problem. It is very difficult to find the theoretic optimum solution .Dynamic programming has the characteristic of multistage decision processes and has advantages in dealing with the inner-plant economical operation. This thesis solves the space optimization problems of unit commitment by using dynamic programming. As the example show, this method can obtain the optimum solution and solve the inner-plant economical operation quickly.
The daily optimal hydro generation scheduling problem is categorized as a class of large-scale, dynamic, non-line and non-convex constrained optimization problem. The traditional optimized method has Strict request to the objective function,and it is also very complex to process the constraints. Therefore, a new improved chaotic hybrid differential evolution algorithm is proposed to solve the DOHGSB in this thesis. In order to overcome the difficulty of choosing suitable mutation factor and crossover factor, a chaotic sequences based on a logistic map is applied into determining the parameter values in this thesis. Penalty functions require a careful fine tuning of the penalty factors during handling constraints. In fact, it is very difficult to estimate the degree of penalization accurately. In order to overcome the drawback of choice penalty factors, an effective method with three simple comparison mechanisms based on feasibility to guide the search toward the optimum is adopted, and the method does not requires us to set any additional parameters. With taking maximizing the summation of the power generation as optimized criterion , this thesis establish the mathematical model by minimize the summation of the deviation between the hourly load demand and hydro system total power generation throughout 24 hours, and the load balance constraint is not treated explicitly but rather implicitly in the mathematical model. The optimal result is obtained with the improved differential evolution algorithm and the constraint handling method and the proposed method is better than other method by solving the same problem. In brief, the adopted method has the feasibility and effectiveness for solving the daily optimal hydro generation scheduling problem.
本研究依托国家自然科学基金项目“基于CVAR和随机机会约束规划的水电竞价机理与风险分析”(项目编号50779020),并结合“大洑潭水电站自动发电控制”项目的开发,以梯级水电站短期优化调度为研究基础,以动态规划法及基于混沌序列和可行性规则的改进差分进化算法为优化方法,主要解决了水电站厂内经济运行中的机组最优组合问题和梯级水电站短期经济运行中的日优化调度问题,得到了水电站厂内经济运行总表及梯级水电站日优化运行计划。水电站厂内经济运行是梯级水电站短期优化调度的基础,梯级水电站短期优化调度是水电站厂内经济运行的指导,将两者有机地联系起来即可实现梯级水电站短期发电计划优化方案的制定。
机组组合问题是水电站厂内经济运行的重要内容,具有离散、非凸、非线性等特性,是一个复杂的优化问题,很难找到理论最优解。动态规划法具有的多阶段决策过程特性与水电站厂内经济运行连续性、周期性、分阶段调度的问题十分吻合。本文采用动态规划法来解决机组组合的空间最优化问题,在合理选取机组台数、台号之后,再在选定的机组之间用动态规划法进行负荷优化分配。实例计算结果显示,该方法计算快捷,能够迅速得到经济运行总表,实现厂内经济运行,从而为梯级水电站短期优化调度的实现做好铺垫。
梯级水电站之间由于存在水力联系、电力联系,使得梯级水电站短期优化调度具有复杂的约束条件,并表现为大型、动态、有时滞的非线性问题。传统的优化方法对目标函数限制性要求较强,对约束条件的处理也比较复杂,很难从全局找到最优解。为了克服传统优化方法解决此类问题的不足,本文采用差分进化算法对梯级水电站日优化运行问题求解。为了改善算法的求解性能,提出了基于混沌序列自适应确定变异缩放因子和交叉概率因子的改进的差分进化算法;为了克服罚函数在处理约束条件时惩罚因子不易确定的缺点,提出了基于可行性规则的约束条件处理方法,该方法不必增加额外参数,这是罚函数法所不能及的。本文建立了24个时段内梯级水电系统出力与电网给定负荷偏差总和最小为优化目标函数的数学模型,运用改进的差分进化算法及约束条件处理方法求解,与其它算法相比,优化效果显著,为梯级水电站日优化问题提供了一种新的解决思路和方法。
With the intense Energy situation, developing the hydro power firstly and vigorously is our best choice in order to adjust the energy structure in our country,and it is also a good way to implement the sustainable development strategy. As the electrical power system's important component, short-term economic dispatching of the cascaded hydropower plants plays an important role in the security,stability and economic operation of the whole power system. This thesis takes short-term economic dispatching of the cascaded hydropower plants as the core, and studies the inner-plant economical operation and the daily optimal hydro generation scheduling problem (DOHGSB).
This thesis depends on the State Natural Sciences Foundation project named“the tendering mechanism and risk analysis of hydro power based CVAR and stochastic chance constrained programming”(No.50779020) ,combines the project of the Automatic Generation Control of Da Fu Tan hydro plant, takes short-term economic dispatching of the cascaded hydropower plants as the foundation of the research, and applies dynamic programming and differential evolution algorithm to solve the inner-plant economical operation and the daily optimal hydro generation scheduling problem . There is closely relationship between he daily optimal hydro generation scheduling problem and inner-plant economical operation. Generally speaking,The latter can be considered as the foundation of the former in practical application .This thesis obtains the plan of short-term economic dispatching of the cascaded hydropower plants by taking their relationship into account neatly.
Unit commitment is one of the most important problems in the inner-plant economical operation. Unit commitment is a discrete,non-linear and non-convex complex problem. It is very difficult to find the theoretic optimum solution .Dynamic programming has the characteristic of multistage decision processes and has advantages in dealing with the inner-plant economical operation. This thesis solves the space optimization problems of unit commitment by using dynamic programming. As the example show, this method can obtain the optimum solution and solve the inner-plant economical operation quickly.
The daily optimal hydro generation scheduling problem is categorized as a class of large-scale, dynamic, non-line and non-convex constrained optimization problem. The traditional optimized method has Strict request to the objective function,and it is also very complex to process the constraints. Therefore, a new improved chaotic hybrid differential evolution algorithm is proposed to solve the DOHGSB in this thesis. In order to overcome the difficulty of choosing suitable mutation factor and crossover factor, a chaotic sequences based on a logistic map is applied into determining the parameter values in this thesis. Penalty functions require a careful fine tuning of the penalty factors during handling constraints. In fact, it is very difficult to estimate the degree of penalization accurately. In order to overcome the drawback of choice penalty factors, an effective method with three simple comparison mechanisms based on feasibility to guide the search toward the optimum is adopted, and the method does not requires us to set any additional parameters. With taking maximizing the summation of the power generation as optimized criterion , this thesis establish the mathematical model by minimize the summation of the deviation between the hourly load demand and hydro system total power generation throughout 24 hours, and the load balance constraint is not treated explicitly but rather implicitly in the mathematical model. The optimal result is obtained with the improved differential evolution algorithm and the constraint handling method and the proposed method is better than other method by solving the same problem. In brief, the adopted method has the feasibility and effectiveness for solving the daily optimal hydro generation scheduling problem.
引文
[1]张勇传.水电站经济运行原理.北京:中国水利水电出版社,1998.
[2]国务院办公厅.关于转发发展改革委等部门节能发电调度办法(试行)的通知.http://www.gov.cn/gongbao/content/2007/content-744115.htm,2007.
[3]徐荣荣.梯级水电站短期经济优化调度算法与软件设计.[硕士论文].电子科技大学,2005.
[4]李占英.梯级水电站群径流随机模拟及中长期优化调度.[硕士论文].大连理工大学,2007.
[5]韩冰,张粒子,舒隽.梯级水电站优化调度方法综述.现代电力,2000,24,(1):78-83.
[6]华振兴.梯级水电站群短期优化调度. [硕士论文].华中科技大学,2006.
[7]刘学海.梯级水电站群优化调度与运营策略研究.[博士论文].天津大学,2005.
[8]刘涌,侯志俭,蒋传文.求解机组组合的改进粒子群算法.电力系统自动化,2006,30(4):35-39.
[9]袁桂丽,何修年,史国青等.一种机组优化组合问题的遗传算法.电站系统工程,2006,22(1):27-29.
[10]袁晓辉,王乘,张勇传等.粒子群优化算法在电力系统中的应用.电网技术,2004,28(19):14-19.
[11] Gaing Zwe-Lee. Discrete Particle Swarm Optimization ALgorithnm for Unit Commitment. Proceedings of IEEE Power Engineering Society General Meeting,2003,1:418-424.
[12]袁晓辉,王乘,袁艳斌等.一种求解机组组合问题的新型改进粒子群方法.电力系统自动化,2005,29(1):34-38.
[13] Lingfeng Wang, Chanan Singh. Unit commitment considering generator outages through a mixed-integer particle swarm optimization algorithm.Applied Soft Computing, 2009, 9(3):947-953.
[14] Xiaohui Yuan,Hao Nie, Anjun Su etal. An improved binary particle swarmoptimization for unit commitment problem.Expert Systems with Applications,2009,36(4):8049-8055.
[15]李建华.水电站短期优化调度研究与应用.[硕士论文].武汉大学,2005.
[16]袁晓辉,袁艳斌,权先璋等.基于混沌进化算法的梯级水电系统短期发电计划.电力系统自动化,2001,25(16):34-38.
[17]胡国强.梯级水电站优化调度模型与算法研究.[博士论文].华北电力大学,2007.
[18] P.K. Hota, A.K. Barisal, R. Chakrabarti. An improved PSO technique for short-term optimal hydrothermal scheduling. Electric Power Systems Research, 2009,79(7):1047-1053.
[19] Jiang Chuanwen, Etorre Bompard.A self-adaptive chaotic particle swarm algorithm for short term hydroelectric system scheduling in deregulated environment.Energy Conversion and Management,2005,46 (17):2689-2696.
[20]张志刚,蒋勤.基于差分进化算法的水电站短期经济运行研究.电网与清洁能源,2009,25(2):50-54.
[21] X Yuan,C Zhang, L Wang etal. An enhanced differential evolution algorithm for daily optimal hydro generation scheduling. Computers and Mathematics with Applications,2008,55(11):2458-2468.
[22] L Lakshminarasimman,S Subramanian. Short-term scheduling of hydrothermal power system with cascaded reservoirs by using modified differential evolution. IEE Proc-Gener Transm. Distrib,2006, 153(6): 693-700.
[23] Storn R, Price K. Differential Evolution-a Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. Technical Report, International Computer Science Institute, 1995,8: 22-25.
[24]刘波,王凌,金以慧.差分进化算法研究进展.控制与决策,2007,22(7):21-29.
[25]李凯斌.智能进化优化算法的研究与应用.[硕士论文].浙江大学,2008.
[26]袁晓辉,苏安俊、聂浩等.差分进化算法在电力系统中的应用研究进展.华东电力,2009,37(2):0243-0248.
[27]周艳萍,顾幸生.差分进化算法研究进展.化工自动化及仪表,2007,34(3):1-5.
[28]吴亮红.差分进化算法及应用研究.[硕士论文].湖南大学,2007.
[29]胡中波.差分演化算法在函数优化中的应用研究.[硕士论文].武汉理工大学,2006.
[30]谢晓峰,张文俊,张国瑞等.差异演化的实验研究.控制与决策,2004,19(1):49-52.
[31]颜学峰,余娟,钱锋等.基于改进差分进化算法的超临界水氧化动力学参数估计.华东理工大学学报,2006,32(1):94-97.
[32] Das S,Konar A.An Improved Differential Evolution Scheme for Noisy Optimization Problems//PReMI2005,2005: 417-421.
[33]许小健,黄小平,钱德玲.自适应加速差分进化算法.复杂系统与复杂性科学,2008,5(1):87-91.
[34] Jun hong Liu, JouniLampinen. A Fuzzy Adaptive Differential Evolution Algorithm. IEEE Region 10 Conf on Computers,Communications, Control and Power Enginner. Beijing,2002: 606-611.
[35]李凯斌,卢建刚,吴燕玲等.改进的差分进化算法及应用.组合机床与自动化加工技术,2008,10:16-18.
[36]邓泽喜,曹敦虔,刘晓冀.一种新的差分进化算法.计算机工程与应用,2008,44(24):40-42.
[37] C Thitithamrogchai,B Eua-Arporn.Economic Load Dispatch for Piecewise Quadratic Cost Function using Hybrid Self-adaptive Differential Evolution with Augmented Lagrange Multiplier Method. 2006 International Conference on Power System Technology:1-8.
[38]王刚,高阳,夏洁.基于差异进化算法的人工神经网络快速训练研究.管理学报,2005,2(4): 450-454.
[39]郑小霞,钱锋.一种改进的微粒群优化算法.计算机工程,2006,32(15):25-27.
[40]贺安坤,苗良.差分进化微粒群优化算法-DEPSO.微计算机信息,2006,22(12):84-86.
[41] Beygey P, Ragsdale C.Modied Dierential Evolution: A Greedyrandom Strategyfor Genetic Recombination.Omega,2005,33:255-265.
[42] Shiy J,Tengh F,LIZ.Cooperative Co-evolutionary Differential Evolution for Function Optimization.//Proceedings of 2005 International Conference on Natural Compu- -tation.Berlin,Springer-Verlag,2005:1080-1088.
[43] Liu B,Wang L, Jin Y H et al. Designing neural networks using hybrid particle swarm optimization.Lecture Notes in Computer Science. Berlin,2005:391-397.
[44] Abbass H A. An evolutionary artificial neural networks approach for breast cancer diagnosis .Artificial Intelligence in Medicine,2002, 25(3): 265-281.
[45]方强.基于优进策略的差分进化算法及其化工应用.[硕士论文].浙江大学,2004.
[46] Kaelo P, Alim M. A Numerical Study of Some Modified Differential Evolution Algorithms. European Journal of Operational Research,2006, 169:1176-1184.
[47] R.Naresh,J.Sharma.Short term hydro scheduling using two-phase neural net-wo rk.Electrical Power Energy System,2002(24):583-590.
[48] Yang PC,Yang HT,Huang CL. Scheduling short term hydrothermal generation using evolutionary programming techniques.IEE Proc PtC 1996:143(4):65-72.
[49]蒋传文,候志俭,李承军.求取混沌时间序列嵌入维数的一种神经元网络方法.水电能源科学,2000,18(4):12-13.
[50]唐巍,李殿璞.电力系统经济负荷分配的混沌优化方法.中国电机工程学报,2000,20(10):36-40.
[51]雷德明,严新平,吴智铭.多目标混沌进化算法.电子学报,2006,34(6):1142-1145.
[52]王凌,刘波.微粒群优化与调度算法.北京:清华大学出版社,2008.
[53] Carlos A,Coello Coello.Theeoretical and numerical constraint handling techniques used with evolutionary algorithms:a survey of the state of art.Computer methods in applied mechanics and engineering. 2002,191:1245-1287.
[2]国务院办公厅.关于转发发展改革委等部门节能发电调度办法(试行)的通知.http://www.gov.cn/gongbao/content/2007/content-744115.htm,2007.
[3]徐荣荣.梯级水电站短期经济优化调度算法与软件设计.[硕士论文].电子科技大学,2005.
[4]李占英.梯级水电站群径流随机模拟及中长期优化调度.[硕士论文].大连理工大学,2007.
[5]韩冰,张粒子,舒隽.梯级水电站优化调度方法综述.现代电力,2000,24,(1):78-83.
[6]华振兴.梯级水电站群短期优化调度. [硕士论文].华中科技大学,2006.
[7]刘学海.梯级水电站群优化调度与运营策略研究.[博士论文].天津大学,2005.
[8]刘涌,侯志俭,蒋传文.求解机组组合的改进粒子群算法.电力系统自动化,2006,30(4):35-39.
[9]袁桂丽,何修年,史国青等.一种机组优化组合问题的遗传算法.电站系统工程,2006,22(1):27-29.
[10]袁晓辉,王乘,张勇传等.粒子群优化算法在电力系统中的应用.电网技术,2004,28(19):14-19.
[11] Gaing Zwe-Lee. Discrete Particle Swarm Optimization ALgorithnm for Unit Commitment. Proceedings of IEEE Power Engineering Society General Meeting,2003,1:418-424.
[12]袁晓辉,王乘,袁艳斌等.一种求解机组组合问题的新型改进粒子群方法.电力系统自动化,2005,29(1):34-38.
[13] Lingfeng Wang, Chanan Singh. Unit commitment considering generator outages through a mixed-integer particle swarm optimization algorithm.Applied Soft Computing, 2009, 9(3):947-953.
[14] Xiaohui Yuan,Hao Nie, Anjun Su etal. An improved binary particle swarmoptimization for unit commitment problem.Expert Systems with Applications,2009,36(4):8049-8055.
[15]李建华.水电站短期优化调度研究与应用.[硕士论文].武汉大学,2005.
[16]袁晓辉,袁艳斌,权先璋等.基于混沌进化算法的梯级水电系统短期发电计划.电力系统自动化,2001,25(16):34-38.
[17]胡国强.梯级水电站优化调度模型与算法研究.[博士论文].华北电力大学,2007.
[18] P.K. Hota, A.K. Barisal, R. Chakrabarti. An improved PSO technique for short-term optimal hydrothermal scheduling. Electric Power Systems Research, 2009,79(7):1047-1053.
[19] Jiang Chuanwen, Etorre Bompard.A self-adaptive chaotic particle swarm algorithm for short term hydroelectric system scheduling in deregulated environment.Energy Conversion and Management,2005,46 (17):2689-2696.
[20]张志刚,蒋勤.基于差分进化算法的水电站短期经济运行研究.电网与清洁能源,2009,25(2):50-54.
[21] X Yuan,C Zhang, L Wang etal. An enhanced differential evolution algorithm for daily optimal hydro generation scheduling. Computers and Mathematics with Applications,2008,55(11):2458-2468.
[22] L Lakshminarasimman,S Subramanian. Short-term scheduling of hydrothermal power system with cascaded reservoirs by using modified differential evolution. IEE Proc-Gener Transm. Distrib,2006, 153(6): 693-700.
[23] Storn R, Price K. Differential Evolution-a Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. Technical Report, International Computer Science Institute, 1995,8: 22-25.
[24]刘波,王凌,金以慧.差分进化算法研究进展.控制与决策,2007,22(7):21-29.
[25]李凯斌.智能进化优化算法的研究与应用.[硕士论文].浙江大学,2008.
[26]袁晓辉,苏安俊、聂浩等.差分进化算法在电力系统中的应用研究进展.华东电力,2009,37(2):0243-0248.
[27]周艳萍,顾幸生.差分进化算法研究进展.化工自动化及仪表,2007,34(3):1-5.
[28]吴亮红.差分进化算法及应用研究.[硕士论文].湖南大学,2007.
[29]胡中波.差分演化算法在函数优化中的应用研究.[硕士论文].武汉理工大学,2006.
[30]谢晓峰,张文俊,张国瑞等.差异演化的实验研究.控制与决策,2004,19(1):49-52.
[31]颜学峰,余娟,钱锋等.基于改进差分进化算法的超临界水氧化动力学参数估计.华东理工大学学报,2006,32(1):94-97.
[32] Das S,Konar A.An Improved Differential Evolution Scheme for Noisy Optimization Problems//PReMI2005,2005: 417-421.
[33]许小健,黄小平,钱德玲.自适应加速差分进化算法.复杂系统与复杂性科学,2008,5(1):87-91.
[34] Jun hong Liu, JouniLampinen. A Fuzzy Adaptive Differential Evolution Algorithm. IEEE Region 10 Conf on Computers,Communications, Control and Power Enginner. Beijing,2002: 606-611.
[35]李凯斌,卢建刚,吴燕玲等.改进的差分进化算法及应用.组合机床与自动化加工技术,2008,10:16-18.
[36]邓泽喜,曹敦虔,刘晓冀.一种新的差分进化算法.计算机工程与应用,2008,44(24):40-42.
[37] C Thitithamrogchai,B Eua-Arporn.Economic Load Dispatch for Piecewise Quadratic Cost Function using Hybrid Self-adaptive Differential Evolution with Augmented Lagrange Multiplier Method. 2006 International Conference on Power System Technology:1-8.
[38]王刚,高阳,夏洁.基于差异进化算法的人工神经网络快速训练研究.管理学报,2005,2(4): 450-454.
[39]郑小霞,钱锋.一种改进的微粒群优化算法.计算机工程,2006,32(15):25-27.
[40]贺安坤,苗良.差分进化微粒群优化算法-DEPSO.微计算机信息,2006,22(12):84-86.
[41] Beygey P, Ragsdale C.Modied Dierential Evolution: A Greedyrandom Strategyfor Genetic Recombination.Omega,2005,33:255-265.
[42] Shiy J,Tengh F,LIZ.Cooperative Co-evolutionary Differential Evolution for Function Optimization.//Proceedings of 2005 International Conference on Natural Compu- -tation.Berlin,Springer-Verlag,2005:1080-1088.
[43] Liu B,Wang L, Jin Y H et al. Designing neural networks using hybrid particle swarm optimization.Lecture Notes in Computer Science. Berlin,2005:391-397.
[44] Abbass H A. An evolutionary artificial neural networks approach for breast cancer diagnosis .Artificial Intelligence in Medicine,2002, 25(3): 265-281.
[45]方强.基于优进策略的差分进化算法及其化工应用.[硕士论文].浙江大学,2004.
[46] Kaelo P, Alim M. A Numerical Study of Some Modified Differential Evolution Algorithms. European Journal of Operational Research,2006, 169:1176-1184.
[47] R.Naresh,J.Sharma.Short term hydro scheduling using two-phase neural net-wo rk.Electrical Power Energy System,2002(24):583-590.
[48] Yang PC,Yang HT,Huang CL. Scheduling short term hydrothermal generation using evolutionary programming techniques.IEE Proc PtC 1996:143(4):65-72.
[49]蒋传文,候志俭,李承军.求取混沌时间序列嵌入维数的一种神经元网络方法.水电能源科学,2000,18(4):12-13.
[50]唐巍,李殿璞.电力系统经济负荷分配的混沌优化方法.中国电机工程学报,2000,20(10):36-40.
[51]雷德明,严新平,吴智铭.多目标混沌进化算法.电子学报,2006,34(6):1142-1145.
[52]王凌,刘波.微粒群优化与调度算法.北京:清华大学出版社,2008.
[53] Carlos A,Coello Coello.Theeoretical and numerical constraint handling techniques used with evolutionary algorithms:a survey of the state of art.Computer methods in applied mechanics and engineering. 2002,191:1245-1287.