A solution to unit commitment problem using fire works algorithm

This paper presents a new approach using swarm intelligence algorithm called Fireworks Algorithm applied to determine Unit Commitment and generation cost (UC) by considering prohibited operating zones. Inspired by the swarm behaviour of fireworks, an algorithm based on the explosion (search) process and the mechanisms of keeping the diversity of sparks has been developed to minimize the total generation cost over a given scheduled time period and to give the most cost-effective combination of generating units to meet forecasted load and reserve requirements, while adhering to generator and transmission constraints. The primary focus is to achieve better optimization while incorporating a large and often complicated set of constraints like generation limits, meeting the load demand, spinning reserves, minimum up/down time and including more realistic constraints, such as considering the restricted/prohibited operating zones of a generator. The generating units have certain ranges where operation is restricted based upon physical limitations of machine components or instability, e.g., due to steam valve or vibration in shaft bearings. Therefore, prohibited operating zones as a prominent constraint must be considered. In this paper the incorporating of complicated constraints of an optimization problem into the objective function is not considered by neglecting the penalty term. Numerical simulations have been carried out on 10 – unit 24 – hour system.     

Generation scheduling in smart grid environment using global best artificial bee colony algorithm

Generation scheduling is an important concern of the current power system which is suffering from many obstacles of limited generation resources, grown energy demand and fuel price, inconsistent load demand and fluctuations of available wind power in case of the thermal–wind system. Smart grid system has a great potential of tumbling existing power system difficulties with intelligent infrastructure and computation technologies. Three different distributed energy resources, namely, distributed generation, demand response and gridable vehicles are used in this paper to overcome the power system hitches. The classical generation scheduling is solved with insertion of the cost of demand response and the cost model pertaining to underestimation and overestimation of fluctuating wind power. The modified optimization problem is solved using an efficient Global best artificial bee colony algorithm for 10 generating units test system. Generation scheduling in the smart grid environment yields a significant reduction in the total cost.     

Cost/environmentally compromised dispatch for cascaded hydrothermal system using artificial bee colony algorithm

This paper evaluates the robustness of the artificial bee colony (ABC) algorithm while allocating optimal power generation in a hydrothermal power system at the level of minimum fuel cost and minimum pollutant emission impacts on the environment subjected to physical and technical constraints. The hydrothermal scheduling (HTS) is devised in a bi‐objective framework so as to optimize both objectives of fuel cost and emission release, individually and simultaneously subjected to a verity of intricate equality and inequality constraints. Initially, all feasible solutions are obtained through random search, and then the ABC algorithm is used for the exploration and exploitation processes together in the search space, thereby discovering the optimal hourly schedule of power generation in the hydrothermal system. Meanwhile, a dependent hydro‐discharge computation handles the equality constraints; especially, the reservoir end volume and slack thermal generating unit for each sub‐interval handle the power balance equality constraint. The performance of the proposed approach is illustrated on a multi‐chain interconnected hydrothermal power system with due consideration of the water transport delay between connected reservoirs and transmission loss of system load. The results obtained from the proposed technique are compared with those of other techniques. The results demonstrate that the ABC algorithm is feasible and efficient for solving the HTS problem. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于人工蜂群优化极限学习机的短期负荷预测*

针对极限学习机(Extreme Learning Machine,ELM)在训练前随机产生输入层权值和隐含层阈值导致输出结果不稳定,影响短期负荷预测精度的缺陷,提出基于人工蜂群(Artificial Bee Colony,ABC)算法改进ELM(ABC-ELM)的短期负荷预测新方法。首先,选用历史负荷、外界气象因素和待预测日星期类型等属性构成ELM输入向量,以负荷值为输出,构建ELM模型;其次,采用ABC对ELM输入层权值和隐含层阈值进行优化;最后,根据优化参数,建立基于ABC-ELM的负荷预测模型,并以该模型开展负荷预测。根据国内某大型城市实测负荷数据开展实验,验证方法有效性。实验结果证明ABC-ELM较ELM和BP神经网络具有更高的稳定性和预测精度。     

Economic dispatch with prohibited operating zones using fast computation evolutionary programming algorithm

This paper presents an efficient and simple approach for solving the economic dispatch (ED) problem with units having prohibited operating zones. The operating region of the units having prohibited zones is broken into isolated feasible sub-regions which results in multiple decision spaces for the economic dispatch problem. The optimal solution will lie in one of the feasible decision spaces and can be found using the conventional λ–δ iterative method in each of the feasible decision spaces. But, this elaborate search procedure is time consuming and not acceptable for on-line application. In this paper, a simple and novel approach is proposed. In this approach, the optimal solution and the corresponding optimum system lambda are determined using an efficient fast computation evolutionary programming algorithm (FCEPA) without considering the prohibited operating zones. Then, a small set of advantageous decision spaces is formed by combining the feasible sub-regions of the fuel cost curve intervening the prohibited zones in the neighbourhood of the optimal system lambda. A penalty cost for each advantageous decision space is judiciously computed using participation factor. The most advantageous decision space is found out by comparing the penalty cost of the decision spaces. The optimal solution in the most advantageous decision space is obtained using the FCEPA. The proposed algorithm is tested on a number of sample systems with units possessing prohibited zones. The study results reveal that the proposed approach is computationally efficient and would be a competent method for solving economic dispatch problem with units having prohibited operating zones.     

基于人工蜂群算法的多目标最优潮流问题的研究

以污染气体排放量、网损最小为目标,建立多目标电力系统最优潮流数学模型,并提出一种基于人工蜂群的多目标算法对其进行求解。该算法利用外部存档技术来保存进化过程中已经找到的Pareto最优解,并在每次迭代后更新。最后根据模糊集理论从Pareto最优解集中选取最优折衷解,为决策者提供科学的决策依据。通过IEEE-30节点系统及IEEE-57节点系统的仿真,验证了该算法在求解大规模电力系统多目标问题上的有效性,相比其他多目标算法能有效避免局部收敛。     

A solution to the ramp rate and prohibited operating zone constrained unit commitment by GHS-JGT evolutionary algorithm

Unit commitment (UC) problem on a large scale with the ramp rate and prohibited zone constraints is a very complicated nonlinear optimization problem with huge number of constraints. This paper presents a new hybrid approach of ’Gaussian Harmony Search’ (GHS) and ’Jumping Gene Transposition’ (JGT) algorithm (GHS-JGT) for UC problem. In this proposed hybrid GHS-JGT for UC problem, scheduling variables are handled in binary form and other constants directly through optimum conditions in decimal form. The efficiency of this method is tested on ten units, forty units and hundred units test system. Simulation results obtained by GHS-JGT algorithm for each case show a better generation cost in less time interval, in comparison to the other existing results.     

基于改进人工蜂群算法的配电网多点故障应急抢修优化调度

为提高配电网故障应急抢修调度在电网应急管理的辅助决策作用,建立了综合考虑抢修资源分配、多小组协作、抢修顺序的配电网多点故障应急抢修优化模型。引入多种群协同进化机制对传统人工蜂群算法进行改进,通过多蜂群智能体增强算法解决高维度复杂优化问题的能力。结合改进人工蜂群算法提出了应急抢修优化模型的统一调度方法。PGE69节点算例仿真研究表明,所提方法可在配电网发生多处故障后快速给出应急抢修预案,减少了停电经济损失。     

基于改进人工鱼群算法的大规模多目标机组组合优化

大型电力系统包含众多发电机组,且运行时需要考虑诸多方面的因素,其机组组合优化是一个多目标多约束的非线性大规模优化问题,现有方法存在诸多不足。人工鱼群算法在解决非线性优化问题时性能良好,但存在寻优效率低、可能陷入局部极值等缺点。针对这些不足,提出了改进的人工鱼群算法。该算法引入了可变视野,对人工鱼移动策略做出了调整并与遗传算法中的变异操作相结合。构建了兼顾经济性与环保性的多目标优化模型。为了解决机组规模扩大导致的计算时间过长问题,采用了分阶段的优化方法,将改进后的算法应用于启停安排阶段,确定机组启停状态后采用混合整数规划法进行负荷分配。针对最高包含1000台机组的大电网机组优化算例进行了模拟实验,实验结果表明:改进后的优化算法的收敛性和全局搜索能力均得到了提高,大规模机组组合的计算时间大大缩短。多目标条件下也取得了理想结果,验证了该方法的有效性。     

基于蜂群算法的低压电力线高频RLCG 模型参数辨识

电力线是通用的电力网络间的连接载体,同时也是传导电磁干扰和载波通信信号的主要传播介质.建立准确的电力线电参数模型是研究传导电磁干扰和载波信号传输特性的基础.采用一种考虑集肤效应和介质损耗的高频信号传输的RLCG模型对普通的三线低压电力线进行建模,并利用人工蜂群算法对模型参数进行辨识,该模型考虑了高频条件下电力线的趋肤效应以及电介损耗对信号传输特性的影响.利用网络分析仪测量实际电力线的阻抗特性作为标准数据,与传统的基于遗传算法的辨识方法的仿真结果进行对比,证明了所提出的电力线高频RLCG模型可以准确地反映电力线的高频传输特性,为低压电力线载波通信和电磁兼容分析奠定基础.     

Optimal power flow solution of power system incorporating stochastic wind power using Gbest guided artificial bee colony algorithm

This paper focuses primarily on implementation of optimal power flow (OPF) problem considering wind power. The stochastic nature of wind speed is modeled using two parameter Weibull probability density function. The economic aspect is examined in view of the system wide social cost, which includes additional costs like expected penalty cost and expected reserves cost to account for wind power generation imbalance. The optimization problem is solved using Gbest guided artificial bee colony optimization algorithm (GABC) and tested on IEEE 30 bus system. The simulation results obtained using proposed method are compared with other methods available in the literature for a case of conventional OPF as well as OPF incorporating stochastic wind. Subsequently an extensive simulation study is conducted to investigate the effect of wind power and different cost components on optimal dispatch and emission. Numerical simulations indicate that the operation cost of system and emission depends upon the transmission system bottlenecks and the intermittency of wind power generation.     

基于改进人工蜂群算法的家庭储能容量优化配置*

家庭能源系统中的储能设备初始投资成本高,限制其实际应用。针对此问题,文章对混合储能的容量配置进行了研究。分别构建了刚性负荷、柔性负荷和储能类设备负荷模型;在此基础上搭建以用户每天用电费用最低为目标的家庭能源管理系统模型;提出一种改进的人工蜂群算法对模型求解。实验结果表明,通过和单储能的系统相比,在满足用户用电需求的同时,配置混合储能的家庭能源系统能有效减小用户每天用电费用。对文中算法与人工蜂群算法和粒子群算法优化结果进行比对,证实所提算法优化时长短、收敛速度快且不易于陷入局部最优。     

基于改进ABC算法的中长期电力负荷组合预测

将人工蜂群(ABC)算法应用到中长期电力负荷预测中,通过与组合预测模型相结合,对组合预测目标函数进行优化权重求解。另外针对该算法的早期收敛速度慢、后期容易陷入局部最优的缺点,通过引入扰动项,并进行最坏蜜源替代予以解决。实例分析证明该改进算法收敛速度快,全局寻优能力强。利用它求得的组合预测值,相对于单一模型的预测结果,精度有较大的提高,说明该改进算法应用到中长期电力负荷预测中是可行的。     

基于人工蜂群算法优化支持向量机的接地网腐蚀速率预测模型

为了提高接地网腐蚀速率预测的精确度,在建立预测模型的过程中,首先对接地网进行了基于电网络理论的腐蚀诊断过程,并以经过诊断之后确定的腐蚀支路位置为采样点。考虑到仅以土壤理化性质反映接地网腐蚀速率的局限性,在接地网腐蚀诊断结果的基础上,提出接地网电阻平均增长速率作为预测模型的输入特征量之一。建立了基于人工蜂群优化支持向量机的接地网腐蚀速率预测模型,测试结果显示相对BP神经网络模型和广义回归神经网络模型,所提模型的预测结果精确度和稳定性更高,表明了对于解决接地网腐蚀速率预测问题,所提模型具有良好的适用性。     

Determination of optimal output power and location for multiple distributed generation sources simultaneously by using artificial bee colony

Transformation of a distribution network into an intelligent and efficient system meets with many difficulties. One of most important challenges for engineers is to achieve a more economical distribution network. In addition, fluctuation in the price of oil and gas makes this task more complex. Therefore, the introduction of distributed generation (DG) in the system promises to be a good solution to reduce the dependency on oil and gas sources. However, the location and output power of DG are still an issue that needs to be solved by the utility. In previous studies, determination of DG output power and DG location are executed separately, which means a different technique is applied to each of them. Thus, it will lead the solution getting trapped in a local minimum because the calculation of optimal DG output power does not depend on the optimal DG location. This paper presents a solution to determine the location and output power of DGs simultaneously by using simultaneous artificial bee colony (SABC) to reduce the total power losses. The performance of SABC is compared with that of separate analysis, which is a combination of a single DG placement algorithm and artificial bee colony (ABC). The analysis shows that determining simultaneously the DG's location and the output gives lower total power losses and better voltage profile compared to separately analyzing the two. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Single trial estimation of event-related potential components using spatiotemporal filtering and artificial bee colony optimized Gaussian kernel mixture model

Single trial estimation of event-related potential (ERP) components is an open research topic in neuroscience. In this article, we have proposed a method to improve the performance of spatiotemporal filtering by decreasing its dependency to prior estimates of ERP components. For this purpose, we have used a mixture of Gaussian kernels instead of a raw prior signal, and the parameters of the Gaussian kernel are estimated using artificial bee colony algorithm. The algorithm starts with one Gaussian kernel, and after optimizing its parameters, another Gaussian kernel is added. This procedure goes on until the stopping criterion is reached. The efficiency of the algorithm is tested for one single uncorrelated component and two correlated components for synthesized electroencephalogram (EEG) signal. Also, the efficiency of the proposed method is presented on real data for extraction of N170 component in real EEG data.     

基于差分进化人工蜂群算法的光伏最大功率跟踪策略研究

带有旁路二极管的光伏阵列在局部阴影时其P-U特性曲线会出现多个极值点,此时常规MPPT方法在多峰值寻优时可能会失效。对光伏阵列输出特性功率极值点的个数进行了研究,在此基础上将基于差分进化的人工蜂群算法应用于最大功率点跟踪。首先对蜜蜂的初始位置进行预定义初始化,避免遗漏极值点。将差分进化算法中的变异策略与人工蜂群算法相结合,实现时变条件下全局最大功率点跟踪控制。并且在上述算法中加入迭代终止策略,从而有效避免系统稳态时的功率振荡现象。在Matlab中搭建S-Function仿真模型,验证了该算法的有效性。     

基于改进人工蜂群算法的直流配电网典型应用场景拓扑结构研究

为了解决直流配电网规划中场景针对性不强的问题,给出了不同场景下直流配电网的网络拓扑结构规划方案。将直流配电网应用场景分为居民住宅区、工业园区和新能源集结区,考虑不同应用场景的特点,利用层次分析法提出一种新的可靠性指标计算方法。结合变权的思想,综合考虑电网的经济性和可靠性,给出了直流配电网的规划模型。利用由最大最小积改进的人工蜂群算法,以IEEE标准14节点电路为对象,对三种场景下的规划模型进行寻优,并利用griewank函数对比了改进前后算法的性能。仿真结果表明,所得线路规划方案满足各场景要求,改进后的蜂群算法收敛速度和精度均有提升。所提方法可为直流配电网规划提供参考。     

基于混合蜂群算法特征参数同步优化支持向量机的水电机组轴心轨迹识别方法研究

在水电机组轴心轨迹识别研究中,为解决传统支持向量机方法中特征参数无法自适应选择而导致分类性能不高、计算时间过长等问题,提出混合人工蜜蜂群算法特征参数同步优化支持向量机（HABC-SVM）的轴心轨迹识别方法。将人工蜜蜂群算法引入到支持向量机识别优化模型的求解中,对人工蜜蜂群从搜索策略、蜜源编码、更新策略等方面进行了改进。通过仿真试验获取水电机组的四类典型轴心轨迹样本,对轴心轨迹中提取的19种特征参数和支持向量机参数进行了同步优化,将改进HABC算法与PSO-SVM算法和GA-SVM算法进行了对比。研究结果表     

Modelling and control of six‐phase induction motor servo‐driven continuously variable transmission system using blend modified recurrent Gegenbauer orthogonal polynomial neural network control system and amended artificial bee colony optimization

Because the nonlinear and time‐varying characteristics of the continuously variable transmission system operated using a six‐phase copper rotor induction motor are unknown, improving the control performance of the linear control design is time‐consuming. To capture the nonlinear and dynamic behaviour of the six‐phase copper rotor induction motor servo‐driven continuously variable transmission system, a blend modified recurrent Gegenbauer orthogonal polynomial neural network (NN) control system, which has the online learning capability to return to the nonlinear time‐varying system, was developed. The blend modified recurrent Gegenbauer orthogonal polynomial NN control system can perform overseer control, modified recurrent Gegenbauer orthogonal polynomial NN control, and recompensed control. Moreover, the adaptation law of online parameters in the modified recurrent Gegenbauer orthogonal polynomial NN is based on the Lyapunov stability theorem. The use of amended artificial bee colony optimization yielded two optimal learning rates for the parameters, which helped improve convergence. Finally, comparison of the experimental results of the present study with those of previous studies demonstrated the high control performance of the proposed control scheme. Copyright © 2016 John Wiley & Sons, Ltd.