Evolutionary algorithms for the design of grid-connected PV-systems

The sale of electric energy generated by photovoltaic (PV) plants has attracted much attention in recent years. The installation of PV plants aims to obtain the maximum benefit of captured solar energy. The current methodologies for planning the design of the different components of a PV plant are not completely efficient. This paper addresses the optimization of the design of PV plants with solar tracking, which consists of the optimization of the variables that make up the PV plant to obtain the minimum electric (Joule) losses possible. These variables are the size and distribution of solar modules in the solar tracker, the distribution of the solar trackers in the field and the choice of inverter. Evolutionary algorithms (EAs) are adaptive methods based on natural evolution that may be used for searching and optimization. Four different EAs have been used for optimizing the design of PV plants: steady-state genetic algorithm, generational genetic algorithm, CHC algorithm and DE algorithm. In order to test the performance of these algorithms we have used different proposed fields to mount PV plants. The results obtained show that EAs, and specifically DE with rand mutation schemes, are promising techniques to optimize design of PV plants. Furthermore, the results are contrasted with nonparametric statistical tests to support our conclusions.     

一种太阳能集热系统集热量实时预测的混合建模方法

太阳能集热器的集热量受光照度、环境温度、风速等多种因素的影响,其预测模型很难从预测精度和实时性上同时满足用户需求。本文提出一种实时预测太阳能集热系统集热量的混合建模方法。该方法首先从能量守恒出发,根据热管式太阳能集热系统传热机理推导出集热量的理论模型,并把理论模型中的散热系数、透射率、吸收率等经验参数以及采光面积、散热面积等几何参数集总为模型的未知参数,进而提出混合模型的结构。然后,利用TRNSYS仿真软件搭建太阳能集热器模拟仿真系统,对仿真系统不同的运行工况进行仿真实验,获取用于辨识混合模型未知参数的稳态数据。最后,选用粒子群优化算法（PSO）作为模型参数的辨识方法,利用所获得的稳态数据辨识模型的未知参数。模型预测值与仿真实验结果的比较表明,预测模型简单而精确,能够在各种工况下实时地、高精度地预测太阳能集热器的集热量,其平均相对误差可达到2.02%。该模型在太阳能热泵、太阳能热水器等系统的优化控制领域得以广泛应用。     

Intelligent control of photovoltaic system using BPSO-GSA-optimized neural network and fuzzy-based PID for maximum power point tracking

The maximum power point tracking (MPPT) technique is applied in the photovoltaic (PV) systems to achieve the maximum power from a PV panel in different atmospheric conditions and to optimize the efficiency of a panel. A proportional-integral-derivative (PID) controller was used in this study for tracking the maximum power point (MPP). A fuzzy gain scheduling system with optimized rules by subtractive clustering algorithm was employed for tuning the PID controller parameters based on error and error-difference in an online mode. In addition, an Elman-type recurrent neural network (RNN) was used for inverse identification of the PV system and for estimating the solar radiation intensity to determine the MPP voltage. The optimum number of neurons in the single hidden-layer of the RNN was determined by binary particle swarm optimization algorithm. The weights of this RNN were also optimized by using a hybrid method based on the Levenberg-Marquardt algorithm and gravitational search algorithm (GSA). In the proposed fitness function for optimization, both the RNN size and its convergence accuracy were considered. Thus, the algorithm for RNN optimization attempts to minimize both the structural complexity and the mean square error. Simulation results revealed superior performance of GSA in comparison with particle swarm, cuckoo, and grey wolf optimization algorithms. The performance of the proposed MPPT method was evaluated under four different ambient conditions. Our experimental results show that the proposed MPPT method is more efficient than the three competitive methods presented in recent years.     

Bond graph modeling and optimization of photovoltaic pumping system: Simulation and experimental results

Bond graphs are a promising possibility for modeling complex physical systems. This paper explores its potential by undertaking the analysis, modeling and design of a water pumping photovoltaic system. The effectiveness of photovoltaic water pumping systems depends on the sufficiency between the generated energy and the volume of pumped water. Another point developed in this paper presents the optimization of a photovoltaic (PV) water pumping system using maximum power point tracking technique (MPPT). The optimization is based on the detection of the optimal power. This optimization technique is developed to optimize the usage of power. The presented MPPT technique is used in photovoltaic water pumping system in order to increasing its efficiency. A buck–boost chopper allows an adaptation interface between the panel and the battery checked by a tracking mechanism known as the MPPT (Maximum Power Point Tracking). A new algorithm is presented to control a maximum power point tracker MPPT through a bond graph. From the chemical reactions in the batteries to the control laws of the power electronics structures, a bond graph model is proposed for every single part of the system. The model is used in simulations and the results compared to actual measurements. The model is used in simulations and the results compared to actual measurements, showing an accuracy of nearly 99%.     

Application of sliding mode control for maximum power point tracking of solar photovoltaic systems: A comprehensive review

A robust maximum power point tracking (MPPT) control is of paramount importance in the performance enhancement and the optimization of photovoltaic systems (PVSs). Solar panel exhibits nonlinear behavior under real climatic conditions and output power fluctuates with the variation in solar irradiance and temperature. Therefore, a control strategy is requisite to extract maximum power from solar panels under all operating conditions. Sliding mode control (SMC) is extensively used in non-linear control systems and has been implemented in PVSs to track maximum power point (MPP). The objective of this work is to classify, scrutinize and review the SMC techniques used to extract maximum power from PVSs in both off-grid and grid connected applications. The first order, perturb and observe, incremental conductance, linear expression based sliding mode control algorithms and their adaptive forms are discussed in detail. The advanced form of SMC, terminal sliding mode control (TSMC), super twisting theorem (STT) and artificial intelligent (AI) algorithm based are also presented with the focused application of MPPT of PVSs. A tabular comparison is provided at the end of each category to help the users to choose the most appropriate method for their PV application. It is anticipated that this work will serve as a reference and provides important insight into MPPT control of the PV systems.     

Evaluation of Grid-Connected Photovoltaic Plants Based on Clustering Methods

Photovoltaic (PV) systems are electric power systems designed to supply usable solar power by means of photovoltaics, which is the conversion of light into electricity using semiconducting materials. PV systems have gained much attention and are a very attractive energy resource nowadays. The substantial advantage of PV systems is the usage of the most abundant and free energy from the sun. PV systems play an important role in reducing feeder losses, improving voltage profiles and providing ancillary services to local loads. However, large PV grid-connected systems may have a destructive impact on the stability of the electric grid. This is due to the fluctuations of the output AC power generated from the PV systems according to the variations in the solar energy levels. Thus, the electrical distribution system with high penetration of PV systems is subject to performance degradation and instabilities. For that, this project attempts to enhance the integration process of PV systems into electrical grids by analyzing the impact of installing grid-connected PV plants. To accomplish this, an indicative representation of solar irradiation datasets is used for planning and power flow studies of the electric network prior to PV systems installation. Those datasets contain lengthy historical observations of solar energy data, that requires extensive analysis and simulations. To overcome that the lengthy historical datasets are reduced and clustered while preserving the original data characteristics. The resultant clusters can be utilized in the planning stage and simulation studies. Accordingly, studies related to PV systems integration into the electric grid are conducted in an efficient manner, avoiding computing resources and processing times with easier and practical implementation.     

基于MSTSO算法的冷水机组负荷分配模型研究

为降低空调系统的运行能耗,优化冷水机组的负荷分配,首先提出了一种多策略改进的金枪鱼优化算法(MSTSO),引入黄金正弦觅食机制和非线性惯性权重来加强算法对最优解的全局定位能力;通过蜜獾随机搜索策略赋予算法更强的性能以跳出局部最优。接着利用双向长短期记忆网络(BiLSTM)搭建能效预测模型并用MSTSO算法对其初始参数进行寻优从而获得最佳训练效果。最后进一步提出BiLSTM-MSTSO负荷分配模型,对多台冷水机组的负荷进行合理分配与优化。实验结果表明,优化后的BiLSTM预测模型拥有更高的预测精度,MSTSO算法相较其他智能优化算法可以减少更多的能耗并最大化提升冷水机组的运行效率。因此BiLSTM-MSTSO智能模型适用于多冷水机组的能耗预测与优化。     

Enhanced Metaheuristics with Trust Aware Route Selection for Wireless Sensor Networks

Recently, a trust system was introduced to enhance security and cooperation between nodes in wireless sensor networks (WSN). In routing, the trust system includes or avoids nodes related to the estimated trust values in the routing function. This article introduces Enhanced Metaheuristics with Trust Aware Secure Route Selection Protocol (EMTA-SRSP) for WSN. The presented EMTA-SRSP technique majorly involves the optimal selection of routes in WSN. To accomplish this, the EMTA-SRSP technique involves the design of an oppositional Aquila optimization algorithm to choose safe routes for data communication. For the clustering process, the nodes with maximum residual energy will be considered cluster heads (CHs). In addition, the OAOA technique gets executed to choose optimal routes based on objective functions with multiple parameters such as energy, distance, and trust degree. The experimental validation of the EMTA-SRSP technique is tested, and the results exhibited a better performance of the EMTA-SRSP technique over other approaches.     

Metaheuristic Secure Clustering Scheme for Energy Harvesting Wireless Sensor Networks

Recently, energy harvesting wireless sensor networks (EHWSN) have increased significant attention among research communities. By harvesting energy from the neighboring environment, the sensors in EHWSN resolve the energy constraint problem and offers lengthened network lifetime. Clustering is one of the proficient ways for accomplishing even improved lifetime in EHWSN. The clustering process intends to appropriately elect the cluster heads (CHs) and construct clusters. Though several models are available in the literature, it is still needed to accomplish energy efficiency and security in EHWSN. In this view, this study develops a novel Chaotic Rider Optimization Based Clustering Protocol for Secure Energy Harvesting Wireless Sensor Networks (CROC-SEHWSN) model. The presented CROC-SEHWSN model aims to accomplish energy efficiency by clustering the node in EHWSN. The CROC-SEHWSN model is based on the integration of chaotic concepts with traditional rider optimization (RO) algorithm. Besides, the CROC-SEHWSN model derives a fitness function (FF) involving seven distinct parameters connected to WSN. To accomplish security, trust factor and link quality metrics are considered in the FF. The design of RO algorithm for secure clustering process shows the novelty of the work. In order to demonstrate the enhanced performance of the CROC-SEHWSN approach, a wide range of simulations are carried out and the outcomes are inspected in distinct aspects. The experimental outcome demonstrated the superior performance of the CROC-SEHWSN technique on the recent approaches with maximum network lifetime of 387.40 and 393.30 s under two scenarios.     

Optimal design of truss structures for size and shape with frequency constraints using a collaborative optimization strategy

A new metaheuristic strategy is proposed for size and shape optimization problems with frequency constraints. These optimization problems are considered to be highly non-linear and non-convex. The proposed strategy extends the idea of using a single optimization process to a series of collaborative optimization processes. In this study, a modified teaching-learning-based optimization (TLBO), which is a relatively simple algorithm with no intrinsic parameters controlling its performance, is utilized in a collaborative framework and introduced as a higher-level TLBO algorithm called school-based optimization (SBO). SBO considers a school with multiple independent classrooms and multiple teachers with inter-classroom collaboration where teachers are reassigned to classrooms based on their fitness. SBO significantly improves the both exploration and exploitation capabilities of TLBO without increasing the algorithm's complexity. In addition, since the SBO algorithm uses multiple independent classrooms with interchanging teachers, the algorithm is less likely to be influenced by local optima. A parametric study is conducted to investigate the effects of the number of classes and the class size, which are the only parameters of SBO. The SBO algorithm is applied to five benchmark truss optimization problems with frequency constraints and the statistical results are compared to other optimization techniques in the literature. The quality and robustness of the results indicate the efficiency of the proposed SBO algorithm.     

Size optimization for hybrid photovoltaic–wind energy system using ant colony optimization for continuous domains based integer programming

In this paper, ant colony optimization for continuous domains (ACO_R) based integer programming is employed for size optimization in a hybrid photovoltaic (PV)–wind energy system. ACO_R is a direct extension of ant colony optimization (ACO). Also, it is the significant ant-based algorithm for continuous optimization. In this setting, the variables are first considered as real then rounded in each step of iteration. The number of solar panels, wind turbines and batteries are selected as decision variables of integer programming problem. The objective function of the PV–wind system design is the total design cost which is the sum of total capital cost and total maintenance cost that should be minimized. The optimization is separately performed for three renewable energy systems including hybrid systems, solar stand alone and wind stand alone. A complete data set, a regular optimization formulation and ACO_R based integer programming are the main features of this paper. The optimization results showed that this method gives the best results just in few seconds. Also, the results are compared with other artificial intelligent (AI) approaches and a conventional optimization method. Moreover, the results are very promising and prove that the authors’ proposed approach outperforms them in terms of reaching an optimal solution and speed.     

高斯-柯西变异算子优化的LSSVM模型研究

论文针对标准量子粒子群算法易陷入局部极值的问题,提出一种改进的量子粒子优化最小二乘支持向量机的方法。利用高斯变异数的局部开发能力以及柯西变异数的全局搜索能力,在量子粒子群优化算法中,引入高斯-柯西变异算子,帮助算法跳出局部极值。并利用该优化模型进行光伏发电量预测实验,对优化的最小二乘支持向量机模型的预测结果与其他模型预测结果进行比较,结果表明:基于高斯-柯西变异算子的量子粒子群优化的最小二乘支持向量机对光伏发电量的预测具备较好的收敛速度和跳出局部收敛困境的能力。     

An improved power conditioning system for grid integration of solar power using ANFIS based FOPID controller

Power loss become common while integrating with common grid and in specific when power produced through Solar. This is the very lacking area which this proposal implements an Adaptive Neuro Fuzzy Inference System (ANFIS) based controller of Fractional Order Proportional Integral Derivative (FOPID) used for Tracking of Maximum PP of Grid Integrated Solar Power Conditioning System. The proposed work advances with different ambient light conditions for maximum power point traction. In this work a clear-cut Photo Voltaic (PV Cell) model has been developed and an intensive and operative training data have been extracted from the developed controller. This produced dataset have been the feeder input for the ANFIS structure in turn to locate the Tracking of Maximum PP (MPPT). Traction of MPPT is done, the FOPID controller is enforced by matching the voltage from the array of Photo Voltaic cell with attained or reference voltage produced by the ANFIS structure. In the meantime driving this PV array, DC to DC converter's duty cycle is controlled for producing maximum power from the structure. The duty cycle in FOPID controller is generated through calculating the error within the reference voltage and PV voltage. Those values are then simulated through Math Lab and the Simulation results show that this proposed work efficiency is better than the regularly employed controllers in the solar power production and conditioning system     

Balanced energy allocation scheme for a solar-powered sensor system and its effects on network-wide performance

Solar power can extend the lifetime of wireless sensor networks (WSNs), but it is a very variable energy source. In many applications for WSNs, however, it is often preferred to operate at a constant quality level rather than to change application behavior frequently. Therefore, a solar-powered node is required adaptation to a highly varying energy supply. Reconciling a varying supply with a fixed demand requires a good prediction of that supply, so that demand can be regulated accordingly. We describe two energy allocation schemes, based on time-slots, which aim at optimum use of the periodically harvested solar energy, while minimizing the variability in energy allocation. The simpler scheme is designed for resource-constrained sensors; and a more accurate approach is designed for sensors with a larger energy budget. Each of these schemes uses a probabilistic model based on previous observation of harvested solar energy. This model takes account of long-term trends as well as temporary fluctuations of right levels. Finally, this node-level energy optimization naturally leads to the improvement of the network-wide performance such as latency and throughput. The experimental results on our testbeds and simulations show it clearly.     

Hybrid simulation and optimization-based design and operation of integrated photovoltaic generation,storage units,and grid

Unlike fossil-fueled generation, solar energy resources are geographically distributed and highly intermittent, which makes their direct control extremely difficult and requires storage units as an additional concern. The goal of this research is to design and develop a flexible tool, which will allow us to obtain (1) an optimal capacity of an integrated photovoltaic (PV) system and storage units and (2) an optimal operational decision policy considering the current and future market prices of the electricity. The proposed tool is based on hybrid (system dynamics model and agent-based model) simulation and meta-heuristic optimization. In particular, this tool has been developed for three different scenarios (involving different geographical scales), where PV-based solar generators, storage units (compressed-air-energy-storage (CAES) and super-capacitors), and grid are used in an integrated manner to supply energy demands. Required data has been gathered from various sources, including NASA and TEP (utility company), US Energy Information Administration, National Renewable Energy Laboratory, commercial PV panel manufacturers, and publicly available reports. The constructed tool has been demonstrated to (1) test impacts of several factors (e.g. demand growth, efficiencies in PV panel and CAES system) on the total cost of the integrated generation and storage system and an optimal mixture of PV generation and storage capacity, and to (2) demonstrate an optimal operational policy.     

A surrogate-based optimization algorithm for network design problems

Network design problems (NDPs) have long been regarded as one of the most challenging problems in the field of transportation planning due to the intrinsic non-convexity of their bi-level programming form. Furthermore, a mixture of continuous/discrete decision variables makes the mixed network design problem (MNDP) more complicated and difficult to solve. We adopt a surrogate-based optimization (SBO) framework to solve three featured categories of NDPs (continuous, discrete, and mixed-integer). We prove that the method is asymptotically completely convergent when solving continuous NDPs, guaranteeing a global optimum with probability one through an indefinitely long run. To demonstrate the practical performance of the proposed framework, numerical examples are provided to compare SBO with some existing solving algorithms and other heuristics in the literature for NDP. The results show that SBO is one of the best algorithms in terms of both accuracy and efficiency, and it is efficient for solving large-scale problems with more than 20 decision variables. The SBO approach presented in this paper is a general algorithm of solving other optimization problems in the transportation field.     

基于优化BP神经网络光伏出力短期预测研究

太阳能拥有丰富的资源,而且分布广泛,现已被广泛应用到各种应用中,光伏发电已是一种可靠可行、可扩展的重要可再生能源利用的方式,因此对光伏出力进行精准的预测意义重大;从宁夏市某光伏发电站获得了一年的光伏发电数据与气象等因素,选取四月至五月的数据进行研究预测;针对BP神经网络的收敛时间长,容易陷入局部极小值等缺点;建立单一BP神经网络预测模型,基于遗传算法(GA)优化BP神经网络的GA-BP预测模型与基于狼群算法(WPA)优化的BP神经网络的WPA-BP预测模型;选择平均相对误差作为误差评估指标,结果表明,3种预测模型均能对光伏电站的发电功率进行预测,但是单一的BP神经网络模型误差较大,晴天时,误差为5.1%,经遗传算法改进后的预测误差为4.9%,较单一模型提高了0.2%的精度,而WPA-BP预测模型误差为4.4%,预测精度高于前者;同时多云天和雨天的时候,均为WPA-BP模型的预测误差小,稳定性高,具有一定的研究价值。     

基于IBH-LSSVM的混沌时间序列预测及其在抽油井动液面短期预测中的应用

为了提高预测模型的预测精度,模型参数的选取通常转化为目标参数的组合优化问题,但是预测结果经常会受到优化算法参数设置的影响．针对这个问题,本文提出了一种基于改进黑洞算法和最小二乘支持向量机的预测模型,该模型将嵌入维数、 延迟时间、 正则化参数和核函数参数作为组合优化目标,优化算法不需要额外设定任何主观参数．另外,为了防止模型训练的过拟合,采用基于快速留一法的在线校验方法．通过对寻优机制的改进,该模型具有更好的预测效果．将其应用于抽油井动液面的短期预测中,结果表明所提出的预测模型具有一定的实际应用意义．     

融合MLP和DBN的光伏发电预测算法

精确的光伏发电预测对提高电力系统稳定性、保证电能质量、优化电网运行具有重大意义。为了解决现存光伏预测算法精度较低、性能较差的问题,同时为了综合利用多层感知器（MLP）解决非线性问题的能力以及深度信念网络（DBN）有效处理大量复杂数据的优势,构建了一种融合MLP和DBN的光伏预测算法（MLP-DBN）,其基本思想是先利用MLP模型进行初步预测,再将观测值与预测值的残差输入DBN预测模型进行预测,最后用残差预测值对MLP模型的预测值进行修正。利用光伏发电实测数据仿真,探究了不同学习率下模型的预测性能,并对模型的各参数进行了寻找优化设置。使用均方根误差、平均绝对误差以及决定系数等性能指标评估结果表明,与传统的预测算法支持向量机（SVM）以及具有较高预测精度的深度学习算法长短期记忆网络（LSTM）相比,MLP-DBN算法性能有明显的提升,为光伏发电提供了一种高精度高性能的预测算法,可以有效解决光伏发电预测问题。     

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

Accurate soil prediction is a vital parameter involved to decide appropriate crop, which is commonly carried out by the farmers. Designing an automated soil prediction tool helps to considerably improve the efficacy of the farmers. At the same time, fuzzy logic (FL) approaches can be used for the design of predictive models, particularly, Fuzzy Cognitive Maps (FCMs) have involved the concept of uncertainty representation and cognitive mapping. In other words, the FCM is an integration of the recurrent neural network (RNN) and FL involved in the knowledge engineering phase. In this aspect, this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classification (FCMCSO-ASC) technique. The goal of the FCMCSO-ASC technique is to identify and categorize seven different types of soil. To accomplish this, the FCMCSO-ASC technique incorporates local diagonal extrema pattern (LDEP) as a feature extractor for producing a collection of feature vectors. In addition, the FCMCSO model is applied for soil classification and the weight values of the FCM model are optimally adjusted by the use of CSO algorithm. For examining the enhanced soil classification outcomes of the FCMCSO-ASC technique, a series of simulations were carried out on benchmark dataset and the experimental outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.