Nature-inspired meta-heuristics approaches for charging plug-in hybrid electric vehicle

Currently, there is a remarkable focus on green technologies for taking steps towards more use of renewable energy sources within the sector of transportation and also decreasing pollution. At this point, employment of plug-in hybrid electric vehicles (PHEVs) needs sufficient charging allocation strategy, by running smart charging infrastructures and smart grid systems. In order to daily usage of PHEVs, daytime charging stations are required and at this point, only an appropriate charging control and a management of the infrastructure can lead to wider employment of PHEVs. In this study, four swarm intelligence based optimization techniques: particle swarm optimization (PSO), gravitational search algorithm (GSA), accelerated particle swarm optimization, and hybrid version of PSO and GSA (PSOGSA) have been applied for the state-of-charge optimization of PHEVs. In this research, hybrid PSOGSA has performed very well in producing better results than other stand-alone optimization techniques.

     

粒子群优化算法在网格工作流调度中的应用

为了提高网格工作流管理系统的性能,将粒子群优化算法（PSO）引入到网格工作流的调度策略中．分析算法的基本原理,根据网格工作流调度的问题对其进行变形,提出基于粒子群优化算法的网格工作流调度策略,并与基于Dijkstra的网格工作流调度算法进行对比实验．实验数据表明,粒子群优化算法在网格工作流调度中的性能较好．     

An Optimal Power Scheduling Method Applied in Home Energy Management System Based on Demand Response

In this paper, we first introduce a general architecture of an energy management system in a home area network based on a smart grid. Then, we propose an efficient scheduling method for home power usage. The home gateway (HG) receives the demand response (DR) information indicating the real‐time electricity price, which is transferred to an energy management controller (EMC). Referring to the DR, the EMC achieves an optimal power scheduling scheme, which is delivered to each electric appliance by the HG. Accordingly, all appliances in the home operate automatically in the most cost‐effective way possible. In our research, to avoid the high peak‐to‐average ratio (PAR) of power, we combine the real‐time pricing model with the inclining block rate model. By adopting this combined pricing model, our proposed power scheduling method effectively reduces both the electricity cost and the PAR, ultimately strengthening the stability of the entire electricity system.     

基于分时电价和用户侧储能的配电网调度优化策略

针对分布式电源接入及负荷波动引起配电网线路损耗增加的问题,文中提出将分时电价机制协同用户侧储能参与配电网的优化运行模型。基于分时电价建立用户负荷响应模型,构建以用户日用电成本、配电网网损最小为目标函数的配电网运行优化模型。采用评价函数法将多目标转化成单目标,并在传统遗传算法中引入模拟退火Metropolis准则对用户侧储能充放电策略寻优。仿真结果证明了文中所提策略能有效降低配电网网损及用户用电成本,所提算法寻优速度较快,收敛性能较好。     

New method of traffic flow forecasting based on quantum particle swarm optimization strategy for intelligent transportation system

Traffic flow forecasting is one of the essential means to realize smart cities and smart transportation. The accurate and effective prediction will provide an important basis for decision‐making in smart transportation systems. This paper proposes a new method of traffic flow forecasting based on quantum particle swarm optimization (QPSO) strategy for intelligent transportation system (ITS). We establish a corresponding model based on the characteristics of the traffic flow data. The genetic simulated annealing algorithm is applied to the quantum particle swarm algorithm to obtain the optimized initial cluster center, and is applied to the parameter optimization of the radial basis neural network prediction model. The function approximation of radial basis neural network is used to obtain the required data. In addition, in order to compare the performance of the algorithms, a comparison study with other related algorithms such as QPSO radial basis function (QPSO‐RBF) is also performed. Simulation results show that compared with other algorithms, the proposed algorithm can reduce prediction errors and get better and more stable prediction results.     

Anomaly detection of smart metering system for power management with battery storage system/electric vehicle

A novel smart metering technique capable of anomaly detection was proposed for real-time home power management system. Smart meter data generated in real-time were obtained from 900 households of single apartments. To detect outliers and missing values in smart meter data, a deep learning model, the autoencoder, consisting of a graph convolutional network and bidirectional long short-term memory network, was applied to the smart metering technique. Power management based on the smart metering technique was executed by multi-objective optimization in the presence of a battery storage system and an electric vehicle. The results of the power management employing the proposed smart metering technique indicate a reduction in electricity cost and amount of power supplied by the grid compared to the results of power management without anomaly detection.     

基于PPSO-GRADS算法的盲信号分离

该文将联姻策略应用在粒子群算法中,提出一种并行分阶段的基于粒子群优化算法的盲信号分离方法(PPSO-GRADS)。该算法具有收敛速度快,分离精度高的特点。通过仿真证明该算法比未使用联姻策略的粒子群算法有更好的性能,在收敛速度和分离效果上比传统的梯度算法,遗传算法都有较明显的改善。     

数字调制识别SVM分类器参数优化及仿真

对于基于SVM数字信号调制识别分类器,参数选取过程中如何优化惩罚因子和径向基核函数参数问题,提出了一种改进算法。该算法将自适应惯性权重粒子群算法和k折交叉验证法结合,利用交叉验证法计算粒子适应度值,通过粒子群算法实现最优参数值搜索,最终得到分类器惩罚因子和径向基核函数参数最优值。仿真结果表明,该算法性能明显优于网格搜索法和遗传算法。     

家庭微网储能分组能量管理优化策略

在家庭能量管理系统中,可再生能源的发电功率具有不确定性和间断性,成为影响家庭能量优化调度的因素。储能系统在优化过程中过多充放电次数也会增加储能折旧费用。针对上述问题,文中提出一种储能分组能量管理优化策略。根据可再生能源出力不确定部分和确定部分为储能系统配置充电部分和调度部分。首先建立风力发电系统、光伏发电系统和储能系统模型,然后在此基础上搭建以每日用电费用最小为目标的家庭能量管理优化调度模型。最后以上海市一住宅用电为例,通过改进遗传算法对模型求解。仿真算例分析表明所提策略降低用电费用的同时可以减小可再生能源发电不确定性对能量优化调度的影响,具有一定的有效性和参考价值。     

Electricity Consumption Scheduling with Consumers' Comfort and Preference in Smart Grid

A game theory based scheduling method for household electricity consumption in smart grid is proposed in this paper.A non-cooperative game model is employed during the scheduling.All household consumers compete with each other and control their loads to maximize their payoffs.For solving the scheduling problem,we formulate the Utility optimization (UO) model,in which the electricity cost reduction and the improvement of consumers' comfort and preference are considered simultaneously.The System optimization (SO) model only minimizes the electricity cost when scheduling the consumers' electricity consumption.Then we compare and analyze the two models in numerical simulation.The existence and the uniqueness of Nash equilibrium for proposed game model are proved.Simulation results show that the UO model provides an effective scheduling approach to achieve higher comfort and preference and at the same time decrease the energy cost.     

基于PSO-GA算法的多用户OFDM系统资源分配

为了最小化多用户OFDM系统的总发射功率,提出利用改进的粒子群算法与遗传算法相结合的联合算法(PSO-GA)来搜索最优的子载波和比特分配。该算法首先利用改进粒子群算法对系统的子载波和比特分配进行优化。算法运行过程中,当更新后的粒子速度大于最大粒子速度或小于最小粒子速度时,取最大粒子速度与最小粒子速度区间中的一个随机值作为更新的粒子速度。待PSO-GA算法的改进粒子群算法收敛后,将收敛后的种群作为遗传算法的初始种群,再利用遗传算法进行系统的子载波和比特优化分配,进而得出最优解。仿真结果表明,利用该算法比利用遗传算法、粒子群算法与Zhang算法的分配方案使系统需要的总发射功率降低2~10 dB。     

基于PSO-WaveNet的短期风电功率预测

为了应对风电大规模并网给电力系统带来的严峻挑战,同时提高风力发电的市场竞争力,需要对短期风电功率进行准确预测.文中将小波分析和粒子群优化理论引入神经网络——PSO-WaveNet算法.该算法构建了稳定的风电功率预测网络模型,同时利用灰色关联算法确定网络的输入参量.弥补了神经网络容易陷入局部最优值的缺陷,实验结果表明用算法进行风电功率预测提高了预测精度,验证了该混合算法的可行性.     

基于粒子群优化和支持向量机的电力负荷预测

提出支持向量机的粒子群优化算法的用电量预测方法.其中,采用粒子群优化算法选取较优的支持向量机训练参数组合.以江西省2008年7月～10月的用电量数据以及相关特征数据作为实验数据,实验结果表明该算法电量负荷预测精度高于BP神经网络.     

电力通信技术在智能电网中的运用与相关研究

在社会市场经济背景下,智能网络建设已成为现代化建设事业发展的核心内容,智能电网建设的重要性不断显现.因此,本文作者站在客观的角度,多角度客观分析了电力通信与智能电网,多层次详细探讨了智能电网中电力通信技术的运用,新能源、配电、变电等方面,优化创新电力通信技术的基础上,提高新时期智能电网运营效益.     

基于多智能体深度强化学习的智能电网光网络切片方案

为了提高光网络对大规模、差异化电力业务的资源分配能力,降低大规模业务的算法训练时间,提出了一种基于多智能体深度确定性策略梯度算法的智能电网光网络资源分配方案。该方案考虑大规模和差异化电力业务,将智能电网光网络建模成多智能体系统,以最大化电网公司收益为目标,建立了智能电网光核心网络切片模型,进行网络资源分配优化,并采用条件判断映射,简化了优化问题。同时,把不同业务部署到不同智能体中进行运算,以降低训练时间,满足网络实时性需求。仿真结果表明,该算法具有更大的奖励、更低的成本、时延和训练时间。     

Dynamic adaptive discrete particle swarm optimization algorithm based method on low-power mapping in network-on-chip

Compared to 2D NoC, 3D NoC has better integrated density and system performance, which was a reliable method to solve the problem about low-power mapping. On the basis of the traditional particle swarm optimization algo-rithm (PSOA), a dynamic adaptive discrete particle swarm optimization algorithm (DADPSOA) was proposed . Parame-ter in this algorithm was adjusted dynamically based on the degree of early convergence and the charge of individual adap-tive value to approach the optimal solution. At the same time, the reasonable structure of the particles was made aiming at reducing the time complexity of this algorithm. Experimental results show that comparing with the random mapping, genetic algorithm (GA), PSOA and dynamic ant colony algorithm (DACA), DADPSOA can save the execution time, reduce the communication power consumption of mapping results. The power consumption of the task graph is reduced.     

Investigation on the evolutionary algorithms with their applications in MIMO detecting systems

In this paper, with the purpose of integrating the advantages of both the genetic algorithm and the particle swarm optimization, a new genetic particle swarm optimization (GPSO) algorithm is proposed. Furthermore, these three evolutionary algorithms are successfully applied to address the MIMO detection problem. Simulation results reveal that the GPSO‐based detection algorithm takes much less population size and iteration number when compared with the particle swarm optimization‐based detection method and the genetic algorithm‐based detection method. Besides, when compared with the optimal maximum likelihood detection method, the GPSO‐based detection algorithm can strike a much better balance between the BER performance and the computational complexity. Copyright © 2012 John Wiley & Sons, Ltd.     

Resource Allocation Algorithm Based on PSO-GA for Multi-User OFDM System

In order to minimize the transmitted power in the multi-user orthogonal frequency division multiplexing (OFDM) system, a scheme combining the improved particle swarm optimization (POS) algorithm with genetic algorithm (GA) is proposed to optimize the sub-carriers and bits allocation. In the algorithm, a random velocity between the maximum and minimum particle velocity is used as the updating velocity instead of maximum or minimum velocity when the updated particle velocity is higher than the maximum particle velocity or lower than the minimum particle velocity. Then, the convergence population is used as the initial population of the genetic algorithm to optimize the sub-carriers and bits allocation further. Simulation results show that the transmitted power of the proposed algorithm is about 2 dB to 10 dB lower than that of the genetic algorithm, particle swarm optimization algorithm, and Zhang's algorithm.     

一种基于改进遗传算法的风光互补移动基站智能供电系统设计

针对移动基站面广量大,机房几乎无人值守,系统成本高等问题,以吐鲁番地区实际应用环境为背景,研究并设计了一种基于改进遗传算法的风光互补移动基站智能供电系统。首先,对风光互补移动基站智能供电系统进行了软硬件设计,支持远程智能控制;然后,为了解决成本最优和计算效率问题,将传统遗传算法和粒子群算法相结合,提出了基于粒子群算法的改进遗传算法,对系统优化配置,从而在满足负荷用电的前提下,使系统寿命周期成本显著降低,同时计算效率提高。实验结果表明,所设计的系统工作性能稳定可靠,系统成本降低可在吐鲁番地区及类似地域无人值守的移动通信基站中推广使用。     

DOA and Power Estimation Using Genetic Algorithm and Fuzzy Discrete Particle Swarm Optimization

Aiming to reduce the computational costs and converge to global optimum, a novel method is proposed to solve the optimization of a cost function in the estimation of direction of arrival (DOA). In this method, genetic algorithm (GA) and fuzzy discrete particle swarm optimization (FDPSO) are applied to optimize the direction of arrival and power parameters of the mode simultaneously. Firstly, the GA algorithm is applied to make the solution fall into the global searching. Secondly, the FDPSO method is utilized to narrow down the search field. In FDPSO, chaotic factor and crossover method are added to speed up the convergence. This approach has been demonstrated through some computational simulations. It is shown that the proposed algorithm can estimate both the DOA and the powers accurately. It is more efficient than some present methods, such as Newton-like algorithm, Akaike information critical (AIC), particle swarm optimization (PSO), and genetic algorithm with particle swarm optimization (GA-PSO).