Guaranteed Convergence Particle Swarm Optimization Research Articles

Novel reference condition independent method for estimating performance for PV modules based on double-diode model

The traditional methods for performance estimation mainly include two steps: determine the model parameters under reference condition and calculate the model parameters at varying operating conditions through transformation equations. These methods have the disadvantages of being influenced by the selection of reference condition. A novel reference condition independent method is proposed based on double-diode model (DDM) for parameter calculation and performance estimation at varying operating conditions for photovoltaic (PV) modules. In the proposed method, a new set of transformation equations is reconstructed according to the dependence of physical parameters in DDM on irradiance and temperature. All coefficients in the proposed transformation equations are independent of the information under reference condition and applicable to all varying operating conditions, which eliminates the influence of reference condition. The coefficients are optimized by fitting measured I–V data at varying operating conditions using guaranteed convergence particle swarm optimization technology, and used for model parameters calculation at varying operating conditions. Then the output property of PV module under any operating condition can be determined independently, first against the reference condition and then against the model parameters under reference condition. The accuracy and applicability of proposed method is validated by massive experimental data for six different types of PV modules under wide range of operating conditions. Moreover, three traditional methods are selected to compare with the proposed method. The proposed method shows better accuracy in I–V, P–V curve and maximum power point estimation under different irradiance and temperature conditions, which can be further used to predict the output power of PV system.

A novel method for reference parameters identification and electrical property estimation of PV modules under varying operating conditions

The parameters identification of the diode model under reference condition are crucial and have significant impact on output characteristics estimation of photovoltaic (PV) module under varying operating conditions. The traditional methods of extracting model parameters have always focused on solving the parameter optimization problem only under some certain condition, which neglects their effect of performance estimation under other operating condition. In this paper, a novel method is proposed to identify the reference physical parameters and enhance the accuracy of electrical property estimation for PV modules under varying operating conditions. New objective function with penalty function is constructed by considering the estimated performance not only under reference condition but also under multiple real operating conditions. The maximum permissible error (MPE) is proposed to constrain the accuracy for key electrical output indicators and added in penalty function to ensure the accuracy under reference condition. Taking into account the inequality constraints, the guaranteed convergence particle swarm optimization with penalty function (P-GCPSO) is introduced for parameter identification. A set of comparisons between the measured and calculated results of PV modules indicate that the proposed method substantially more accurate than other documented methods for both single and double diode model. For the six different materials tested, the root mean square error (RMSE) was compared. The RMSE of the single-diode model is reduced by at least 57.98% compared to the compared method, with a maximum reduction of 86.57%. Similarly, the RMSE of the double -diode model was reduced by at least 47.24% with a maximum reduction of 88.71% compared to the compared methods. Additionally, the tests with six different types of PV modules at varying environmental conditions for over one year prove that the proposed method is reliable and practical for real-world applications. The relative error of power generation reached a minimum of 2.20%. This proves the reliability and practicability of the proposed method in practical applications. The proposed method is envisaged to be valuable for both offline analysis and online monitoring applications where an accurate, fast and consistent performance estimation tool is required.

An Accurate Metaheuristic Mountain Gazelle Optimizer for Parameter Estimation of Single- and Double-Diode Photovoltaic Cell Models

Accurate parameter estimation is crucial and challenging for the design and modeling of PV cells/modules. However, the high degree of non-linearity of the typical I–V characteristic further complicates this task. Consequently, significant research interest has been generated in recent years. Currently, this trend has been marked by a noteworthy acceleration, mainly due to the rise of swarm intelligence and the rapid progress of computer technology. This paper proposes a developed Mountain Gazelle Optimizer (MGO) to generate the best values of the unknown parameters of PV generation units. The MGO mimics the social life and hierarchy of mountain gazelles in the wild. The MGO was compared with well-recognized recent algorithms, which were the Grey Wolf Optimizer (GWO), the Squirrel Search Algorithm (SSA), the Differential Evolution (DE) algorithm, the Bat–Artificial Bee Colony Optimizer (BABCO), the Bat Algorithm (BA), Multiswarm Spiral Leader Particle Swarm Optimization (M-SLPSO), the Guaranteed Convergence Particle Swarm Optimization algorithm (GCPSO), Triple-Phase Teaching–Learning-Based Optimization (TPTLBO), the Criss-Cross-based Nelder–Mead simplex Gradient-Based Optimizer (CCNMGBO), the quasi-Opposition-Based Learning Whale Optimization Algorithm (OBLWOA), and the Fractional Chaotic Ensemble Particle Swarm Optimizer (FC-EPSO). The experimental findings and statistical studies proved that the MGO outperformed the competing techniques in identifying the parameters of the Single-Diode Model (SDM) and the Double-Diode Model (DDM) PV models of Photowatt-PWP201 (polycrystalline) and STM6-40/36 (monocrystalline). The RMSEs of the MGO on the SDM and the DDM of Photowatt-PWP201 and STM6-40/36 were 2.042717 ×10−3, 1.387641 ×10−3, 1.719946 ×10−3, and 1.686104 ×10−3, respectively. Overall, the identified results highlighted that the MGO-based approach featured a fast processing time and steady convergence while retaining a high level of accuracy in the achieved solution.

Improved Model for Genetic Algorithm-Based Accurate Lung Cancer Segmentation and Classification

Lung Cancer is one of the hazardous diseases that have to be detected in earlier stages for providing better treatment and clinical support to patients. For lung cancer diagnosis, the computed tomography (CT) scan images are to be processed with image processing techniques and effective classification process is required for appropriate cancer diagnosis. In present scenario of medical data processing, the cancer detection process is very time consuming and exactitude. For that, this paper develops an improved model for lung cancer segmentation and classification using genetic algorithm. In the model, the input CT images are pre-processed with the filters called adaptive median filter and average filter. The filtered images are enhanced with histogram equalization and the ROI(Regions of Interest) cancer tissues are segmented using Guaranteed Convergence Particle Swarm Optimization technique. For classification of images, Probabilistic Neural Networks (PNN) based classification is used. The experimentation is carried out by simulating the model in MATLAB, with the input CT lung images LIDC-IDRI (Lung Image Database Consortium-Image Database Resource Initiative) benchmark Dataset. The results ensure that the proposed model outperforms existing methods with accurate classification results with minimal processing time.

A Novel Approach for Hybrid Image Segmentation GCPSO: FCM Techniques for MRI Brain Tumour Identification and Classification.

In recent times, the early detection of brain tumour analysis and classification has become a very vital part of the medical field. The MRI scan image is the most significant tool to study brain tissue for proper diagnosis and efficient treatment planning to detect the early stages. In this research study, the two contributions were executed in the preprocessing mode. (a) Using wavelet transform to apply decomposed sub-bands of a low-frequency signal to control and adapt the spatial and intensity parameters in a bilateral filter and (b) to detect texture regions and block boundary to control and adapt the spatial and intensity parameters in a bilateral filter When compared to other image resolution methods, the adaptive bilateral method restores the original image quality and has a higher accuracy rate. Using the hybrid segmentation method of GCPSO (Guaranteed Convergence Particle Swarm Optimization) -FCM (Fuzzy C-Mean) techniques, the results were compared with various segmentation. The proposed segmentation gives a better accuracy rate of 95.32%.

Deep Learning-Based BoVW–CRNN Model for Lung Tumor Detection in Nano-Segmented CT Images

One of the most common oncologies analyzed among people worldwide is lung malignancy. Early detection of lung malignancy helps find a suitable treatment for saving human lives. Due to its high resolution, greater transparency, and low noise and distortions, Computed Tomography (CT) images are most commonly used for processing. In this context, this research work mainly focused on the multifaceted nature of lung cancer diagnosis, a quintessential, fascinating, and risky subject of oncology. The input used here has been nano-image, enhanced with a Gabor filter and modified color-based histogram equalization. Then, the image of lung cancer was segmented by using the Guaranteed Convergence Particle Swarm Optimization (GCPSO) algorithm. A graphical user interface nano-measuring tool was designed to classify the tumor region. The Bag of Visual Words (BoVW) and a Convolutional Recurrent Neural Network (CRNN) were employed for image classification and feature extraction processes. In terms of findings, we achieved the average precision of 96.5%, accuracy of 99.35%, sensitivity of 97%, specificity of 99% and F1 score of 95.5%. With the proposed solution, the overall time required for the segmentation of images was much smaller than the existing solutions. It is also remarkable that biocompatible-based nanotechnology was developed to distinguish the malignancy region on a nanometer scale and has to be evaluated automatically. That novel method succeeds in producing a proficient, robust, and precise segmentation of lesions in nano-CT images.

Modelling and estimating performance for PV module under varying operating conditions independent of reference condition

Existing methods for parameter identification and performance estimation under varying operating conditions are accomplished in two steps: first, the model parameters are extracted under the prescribed reference condition; second, the model parameters under varying operating conditions are calculated based on the dependence of parameters on environmental conditions. There are two disadvantages for existing methods: the results are affected by the selection of reference condition, and the irradiance and temperature dependence of parameters are non-uniform for different types PV modules. This paper studies the effect of the reference condition selection and proposes a novel method for parameter identification and performance estimation under varying operating conditions. In the proposed method, a set of improved transformation equations are modified by considering both irradiance and temperature dependence for all parameters in single-diode model (SDM). Since the improved transformation equations are independent of reference condition, the effect of the selection of reference condition is eliminated. The coefficients of the improved transformation equations are extracted through guaranteed convergence particle swarm optimization technology from measured I-V curves under different operating conditions. The efficiency and accuracy of proposed method is validated by amount of experimental data under different irradiance and temperature conditions for different types of PV modules. The variations of SDM’s parameters by the proposed method have been investigated thoroughly and shown to be in accordance with the physical behavior of the PV devices. The proposed method can be further employed to simulate the performance of a PV module under real operating conditions and exhibits great accuracy and suitability.

Detection of Lung Tumor Using ASPP-Unet with Whale Optimization Algorithm

The unstructured growth of abnormal cells in the lung tissue creates tumor. The early detection of lung tumor helps the patients avoiding the death rate and gives better treatment. Various medical image modalities can help the physicians in the diagnosis of disease. Many research works have been proposed for the early detection of lung tumor. High computation time and misidentification of tumor are the prevailing issues. In order to overcome these issues, this paper has proposed a hybrid classifier of Atrous Spatial Pyramid Pooling (ASPP)-Unet architecture with Whale Optimization Algorithm (ASPP-Unet -WOA). To get a fine tuning detection of tumor in the Computed Tomography (CT) of lung image, this model needs pre-processing using Gabor filter. Secondly, feature segmentation is done using Guaranteed Convergence Particle Swarm Optimization. Thirdly, feature selection is done using Binary Grasshopper Optimization Algorithm. This proposed (ASPP-Unet -WOA) is implemented in the dataset of National Cancer Institute (NCI) Lung Cancer Database Consortium. Various performance metric measures are evaluated and compared to the existing classifiers. The accuracy of Deep Convolutional Neural Network (DCNN) is 93.45%, Convolutional Neural Network (CNN) is 91.67%, UNet obtains 95.75% and ASPP-UNet-WOA obtains 98.68%. compared to the other techniques.

Reliability-driven distribution power network dynamic reconfiguration in presence of distributed generation by the deep reinforcement learning method

The reliability of the distribution network increasingly common by high penetration of distributed generations. To address the reliability, this paper propose a new approach based on the dynamic reconfiguration to improve the reliability of the distribution network in presence of distributed generation by Reinforcement Learning algorithm. In this research, the deep reinforcement learning approach find the optimal switches to change the power flow when the network reliability is reduced. The objective function as a reward in reinforcement learning algorithm included active power loss, voltage deviation, and reliability. Furthermore, the failure-rate reduction strategy was computed as a reliability indices of the load points in the distribution network. To calculate the probabilistic load flow, the 2m Point Estimate Method (PEM) has been proposed. The proposed approach is evaluated using the IEEE 33-bus and the IEEE118-bus. The suggested structure has been implemented by deep Q-learning method. The Guaranteed Convergence Particle Swarm Optimization (GCPSO) and Honeybee-Graph (HG) algorithms has been implemented to comparison with presented approach. The results illustrate the usefulness of the methodology. By comparison, near to 5, 10 and 4, 14 percentage improvement by DQL method than the HG, GCPSO methods in total reactive and active power loss, respectively, in the IEEE 118 bus test system (for all scenarios). Furthermore the computing time for presented method is less than the GCPSO and HG.

A novel method for performance estimation of photovoltaic module without setting reference condition

In traditional methods, the process of performance estimation of a photovoltaic (PV) module is achieved through two steps. First, the model parameters are determined under some reference condition, and then, the model parameters are determined under varying operating conditions based on the reference values and the dependence of the model parameters on environmental conditions. This paper presents a novel method for the performance estimation of PV modules under varying operating conditions without setting a reference condition. In the proposed method, the dependence of the model parameters on environmental conditions is modeled and modified without setting a reference condition or using reference values. The model parameters are determined from experimental data using guaranteed convergence particle swarm optimization technology, and are suitable for all operating conditions. Thus, the performance of PV modules can be directly determined under varying operating conditions, which simplifies the process and improves the accuracy. The effectiveness and accuracy of the proposed method are validated by large amounts of experimental data for different types of PV modules at different locations. In comparison with the traditional methods, the proposed method exhibits better accuracy in terms of the I-V and P-V curve and maximum power point estimation under different irradiance and temperature conditions. It can be further used to estimate the output power of PV system under varying operating conditions.

Suitable mathematical model for the electrical characterization of different photovoltaic technologies: Experimental validation

Different photovoltaic technologies have achieved notable improvements in efficiency in recent years, allowing photovoltaic cells to convert a higher percentage of incident solar radiation into electrical energy. However, the search for new, more efficient technologies as well as the improvement of existing ones, remains the aim of researchers and manufacturers. New materials have been considered, requiring the development of more accurate mathematical models to simulate their behavior. This study focusses on the validation of a modified multidimension diode model to determine a suitable model for different photovoltaic technologies. This model includes m-diodes connected in series and u-strings of diodes in parallel, providing a reconfigurable diode network, which allows the determination of the optimal number of diodes in the equivalent electrical circuit based on manufacturer or experimental data. The guaranteed convergence particle swarm optimization algorithm was used to estimate the photovoltaic parameters of the modified multidimension diode model. The validation was carried out with six different photovoltaic technologies, namely polycrystalline silicon, monocrystalline silicon, amorphous silicon, copper indium selenide, heterojunction with intrinsic thin-layer, and cadmium sulfide/cadmium telluride. The results revealed that the modified multidimension diode model accurately reflects the behavior of different photovoltaic technologies with high performance, providing a good compromise between accuracy and computational cost. Specifically, the modified multidimension diode model, when compared to the single-diode model (most commonly used in literature), achieved up to 14% more accuracy for the photovoltaic technologies considered under this study. Furthermore, the mathematical models identified as most suitable for the photovoltaic technologies under study are suggested as references for future works.

Melting mechanism of Pt–Pd–Rh–Co high entropy alloy nanoparticle: An insight from molecular dynamics simulation

The temperature elevation process by the molecular dynamics (MD) simulation was used to investigate the melting mechanism of PtPdRhCo and Pt41Pd18Rh5Co32 high-entropy alloy nanoparticles (HEA-NPs) with diameters of 5, 10, and 15 nm in the FCC arrangement. The second-nearest neighbor modified embedded-atom method (2NN MEAM) potential was used and the cross-element parameters were parametrized by the guaranteed convergence particle swarm optimization (GCPSO) based on the reference data prepared by the density functional theory (DFT) calculation. According to the MD results, three characteristic temperatures during the heating process are found, which include the surface local shear resistance temperature Tslsr, surface pre-melting temperature Tsm, and melting point Tm. By observing the distribution of atomic local shear strain ηiMises with the increasing temperature, the definition of Tslsr is first proposed, below which atoms with high local shear strains are blocked at the surface of HEA-NPs. As the system temperature is above Tslsr, the interior atoms near the surface begin to possess higher local shear strains and this influence continuously spread toward the core of HEA-NPs at higher temperatures. At Tsm, a certain amount of atoms within the thin surface shell are melted, leading to the first discontinuity of binding energy-temperature profile. At Tm, the HEA-NPs structure completely becomes liquid phase and the second discontinuity of binding energy-temperature profile can be found. Although the binding energies of these two HEA-NPs types of the same size are almost identical, the Tslsr, Tsm, and Tm values of PtPdRhCo are relatively higher than those of Pt41Pd18Rh5Co32. Each element type of PtPdRhCo shows a collective behavior during the heating process, resulting in a similar local structural evolution at different temperatures. For Pt41Pd18Rh5Co32, Co and Pd atoms tend to be distorted more easily than Pt and Rh atoms during the heating process, which can be regarded as a kind of defect. This is the main reason for relatively lower Tslsr, Tsm, and Tm values of Pt41Pd18Rh5Co32.

Parameter extraction of photovoltaic single-diode model using integrated current–voltage error criterion

An error criterion is essential in the process of parameter extraction of photovoltaic (PV) modules by fitting I–V curves, which exerts a huge influence on the accuracy of the extracted parameters. This paper proposes a new integrated current–voltage error criterion, named EC-I&V(x), which takes into account the intrinsic I–V properties of the PV module. The deviation in both current and voltage is considered by combining the mean squared error of the current and voltage in different data regions. Four optimization methods are used to validate the proposed error criterion, including guaranteed convergence particle swarm optimization, differential evolution, shuffled complex evolution, and an artificial bee colony algorithm. Different methods with the proposed error criterion are applied to synthetic I–V curves with variable error levels and measured I–V data under different operating conditions. Comparing with the traditional current based error criterion, more accurate results are obtained by using the proposed EC-I&V(x) at different error levels for different optimization methods. The proposed EC-I&V(x) not only improves the accuracy of each extracted parameter but also improves the accuracy of the estimated I–V property near maximum power points.

Effects of Strontium incorporation to Mg-Zn-Ca biodegradable bulk metallic glass investigated by molecular dynamics simulation and density functional theory calculation

Molecular dynamics (MD) simulation and density functional theory (DFT) calculations were used to predict the material properties and explore the improvement on the surface corrosion resistance for the Mg66Zn30Ca3Sr1 bulk metallic glass (BMG). The Mg66Zn30Ca4 BMG was also investigated to realize the influence of the addition of Sr element on the material behaviors of Mg66Zn30Ca4. The Mg-Zn-Ca-Sr parameters of the next nearest-neighbor modified embedded atom method (2NN MEAM) potential were first determined by the guaranteed convergence particle swarm optimization (GCPSO) method based on the reference data from the density functional theory (DFT) calculation. Besides, using the 2NN MEAM parameters of the Mg-Zn-Ca-Sr system, the structures of Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1 were predicted by the simulated-annealing basin-hopping (SABH) method. The local atomic arrangements of the predicted BMG structures are almost the same as those measured in some related experiments from a comparison with the calculated and experimental X-ray diffraction (XRD) profiles. Furthermore, the HA index analysis shows that the fractions of icosahedra-like local structures are about 72.20% and 72.73% for Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1, respectively, indicating that these two BMG structures are entirely amorphous. The uniaxial tensile MD simulation was conducted to obtain the stress-strain relationship as well as the related mechanical properties of Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1. Consequently, the predicted Young’s moduli of both BMGs are about 46.4 GPa, which are very close to the experimental values of 48.8 ± 0.2 and 49.1 ± 0.1 GPa for Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1, respectively. However, the predicted strengths of Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1 are about 850 and 900 MPa, both are slightly higher than the measured experimental values about 747 ± 22 and 848 ± 21 MPa for Mg66Zn30Ca4 and Mg66Zn30Ca3Sr1. Regarding the thermal properties, the predicted melting temperature of Mg66Zn30Ca3Sr1 by the square displacement (SD) profile is about 620 K, which is very close to the experimental melting temperature of about 613 K. The self-diffusion coefficients of Mg, Zn, Ca, and Sr elements were also calculated for temperatures near their melting points by means of the Einstein equation. The methodology can determine the diffusion barriers for different elements by utilizing these diffusion coefficients resulting in a fact that the diffusion barriers of Ca and Sr elements of Mg66Zn30Ca3Sr1 are relatively high. For the electronic properties predicted by the DFT calculation, the projected density of states (PDOS) profiles of surface Mg, Zn, Ca, and Sr elements clearly show that the addition of Sr into Mg66Zn30Ca4 effectively reduces the s and p orbital states of surface Mg and Zn elements near the Fermi level, particularly the p orbits, which suppresses the electron transfer as well as increases the surface corrosion resistance of Mg66Zn30Ca4. Consequently, this study has provided excellent 2NN MEAM parameters for the Mg, Zn, Ca, and Sr system by the GCPSO method to predict real BMG structures as well as by means of the DFT calculation to explore the electronic properties. Eventually, through our developed numerical processes the material properties of BMGs with different compositions can be predicted accurately for the new BMG design.

A new high performance method for determining the parameters of PV cells and modules based on guaranteed convergence particle swarm optimization

Determining the mathematical model parameters of photovoltaic (PV) cells and modules represents a great challenge. In the last few years, several analytical, numerical and hybrid methods have been proposed for extracting the PV model parameters from datasheets provided by the manufacturers or from experimental data, although it is difficult to determine highly reliable solutions quickly and accurately. In this paper, we propose a new method for determining the PV parameters of both the single-diode and the double-diode models, based on the guaranteed convergence particle swarm optimization (GCPSO), using experimental data under different operating conditions. The main advantage of this method is its ability to avoid premature convergence in the optimization of complex and multimodal objective functions, such as the function that determines PV parameters. To validate performance, the GCPSO method was compared with several analytical, numerical and hybrid methods found in the literature. This validation considered three different case studies. The first two are important reference case studies in the literature and have been widely used by researchers. The third was performed in an experimental environment, in order to test the proposed method under a real implementation. The proposed methodology can find highly accurate solutions while demanding a reduced computational cost. Comparisons with other published methods demonstrate that the proposed method produces very good results in the extraction of the PV model parameters.

Arithmetic and parent-centric headless chicken crossover operators for dynamic particle swarm optimization algorithms

This paper conducts an analysis of various strategies for incorporating the headless chicken macromutation operator into a dynamic particle swarm optimization algorithm. Seven variations of the dynamic headless chicken guaranteed convergence particle swarm optimization algorithm are proposed and evaluated on a diverse set of single-objective dynamic benchmark problems. Competitive performance was demonstrated by the headless chicken PSO algorithms when compared to, amongst others, a quantum particle swarm optimization algorithm.

Locating hazardous gas leaks in the atmosphere via modified genetic, MCMC and particle swarm optimization algorithms

Hazardous gas leaks in the atmosphere can cause significant economic losses in addition to environmental hazards, such as fires and explosions. A three-stage hazardous gas leak source localization method was developed that uses movable and stationary gas concentration sensors. The method calculates a preliminary source inversion with a modified genetic algorithm (MGA) and has the potential to crossover with eliminated individuals from the population, following the selection of the best candidate. The method then determines a search zone using Markov Chain Monte Carlo (MCMC) sampling, utilizing a partial evaluation strategy. The leak source is then accurately localized using a modified guaranteed convergence particle swarm optimization algorithm with several bad-performing individuals, following selection of the most successful individual with dynamic updates. The first two stages are based on data collected by motionless sensors, and the last stage is based on data from movable robots with sensors. The measurement error adaptability and the effect of the leak source location were analyzed. The test results showed that this three-stage localization process can localize a leak source within 1.0 m of the source for different leak source locations, with measurement error standard deviation smaller than 2.0.

A novel power flow analysis in an islanded renewable microgrid

In an islanded microgrid mode the use of conventional power flow analysis is not effective as the voltage of slack bus and the frequency of the microgrid are assumed to be constant. Such assumption fails to consider the real characteristics of the island microgrid as all DGs are involved in providing the demand of active and reactive power as well as in maintaining the frequency of the microgrid. In this paper, a novel algorithm, named GPSO-GM (Guaranteed convergence Particle Swarm Optimization with Gaussian Mutation), for the power flow analysis problem in an islanded microgrid is proposed. The problem is modeled without any slack bus by considering steady state frequency as one of the power flow variables. To model different control modes of DGs, such as droop, PV and PQ, in an islanded microgrid, a new formula for power flow equations is developed. PSO is adopted to minimize the mismatch of total active and reactive power. Two operators, mutation and guaranteed convergence, are added to PSO in order to help in finding an optimal solution and to assist in increasing the speed of the proposed algorithm as well as the accuracy of the results. The performance of proposed load flow based on GPSO-GM is compared with the PSO, Newton-trust and time domain methods. The results provide support for the validity of GPSO-GM.

Optimal management of microgrids including renewable energy scources using GPSO-GM algorithm

Environmentally friendly energy sources with high power quality or reliability and low costs are regarded as an effective solution for energy supply problems arising from use of conventional methods. Presented in this paper, gives an optimal management strategy of PV/wind/diesel independent hybrid systems for supplying required energy in autonomous microgrids. A new optimization problem is formulated for minimizing the capital investment and fuel costs of the system. To solve the proposed optimization problem a novel algorithm, named Guaranteed convergence Particle Swarm Optimization with Gaussian Mutation (GPSO-GM), is developed. Two operators, namely mutation and guaranteed convergence, are added to PSO in order to help finding more accurate results and increasing the speed of calculations. The performance of the proposed strategy is evaluated in two case studies.

Multiplicative neuron model artificial neural network based on Gaussian activation function

Multiplicative neuron model-based artificial neural networks are one of the artificial neural network types which have been proposed recently and have produced successful forecasting results. Sigmoid activation function was used in multiplicative neuron model-based artificial neural networks in the previous studies. Although artificial neural networks which involve the use of radial basis activation function produce more successful forecasting results, Gaussian activation function has not been used for multiplicative neuron model yet. In this study, rather than using a sigmoid activation function, Gaussian activation function was used in multiplicative neuron model artificial neural network. The weights of artificial neural network and parameters of activation functions were optimized by guaranteed convergence particle swarm optimization. Two major contributions of this study are as follows: the use of Gaussian activation function in multiplicative neuron model for the first time and the optimizing of central and propagation parameters of activation function with the weights of artificial neural network in a single optimization process. The superior forecasting performance of the proposed Gaussian activation function-based multiplicative neuron model artificial neural network was proved by applying it to real-life time series.