Proposed Particle Swarm Optimization Research Articles

Hybridization of CSA and PSO improves the efficacy of MPPT for solar photovoltaic array with partial shading

AbstractOne critical issue in the tracking systems based on photovoltaic (PV) is how to harvest highest power of the photovoltaic array; particularly when the system is operating in partially shaded conditions (PSCs) or varying irradiances. This study proposes particle swarm optimization (PSO) hybridization and cuckoo search algorithm (CSA) methods for maximum power point tracking (MPPT). The effectiveness of the proposed algorithm is validated and examined under various irradiance patterns. A comparison study in performance has been conducted between the proposed hybrid CSA-PSO method with the conventional P&O and PSO techniques. Several tests have been performed based on numerical simulations utilizing the programming software MATLAB/Simulink. The results demonstrated that the suggested hybrid technique yields smaller tracking time, higher power and greater efficiency than those of other traditional algorithms.

An MTPZC for the Integration of RESs using Analysis, Modeling, Control, and Implementation

This article presents a novel approach to enhance the efficiency, control, and power management capabilities of traditional Zeta Converters in renewable energy applications. The proposed particle swarm optimization (PSO)-modified three-port zeta converter (MTPZC) features a multiport structure with dedicated input ports for photovoltaic (PV) and battery sources, along with an output port. The integration of PSO optimization aims to optimize maximum power point tracking to enhance energy extraction. Extensive simulations and experimental validations showcase the MTPZC's superior performance in power extraction from both PV and Battery sources. This innovative design positions the converter as a promising solution for multiport energy conversion systems in renewable energy applications. The article contributes to the advancement of power electronics by offering improved reliability and efficiency. Simulation results, validated in MATLAB and compared with existing methods, demonstrate an impressive efficiency of 97.8%. The MTPZC outperforms existing approaches, indicating lower converter losses and highlighting its potential for practical implementation in diverse renewable energy systems.

Short term load forecasting using evolutionary algorithm for Tajikistan

<p>Load forecasting is a significant element in the energy management system of power systems. Precise load forecasting aids electric utilities to conduct decisions of unit commitment, reduction of spinning reserve capacity, and schedule device maintenance plan. Furthermore, load forecasting contributes to reducing the generation cost, and it is fundamental to the reliability of the power systems. On the other hand, short-term load forecasting is substantial for economic running. The forecasting precision directly affects the reliability, economy running and supplying power quality of the power system. Hence, finding the required load forecasting method to enhance the accuracy is valuable for forecasting precision. This paper proposed particle swarm optimization (PSO) to improve working support vector machine (SVM), SVM regression model is derived; also derived SVM with PSO. Support vector machine (SVM) model is adopted with and without PSO based on the historical load data and meteorological data of Tajikistan country, analysis the various factors affecting the forecast. The historical data and the load forecasting factors to be considered are normalized. The two parameters of SVM significantly influenced the model, and therefore it optimized using evolutionary algorithm.</p>

Multiobjective 3-D UAV Movement Planning in Wireless Sensor Networks Using Bioinspired Swarm Intelligence

The use of unmanned aerial vehicles (UAVs) is a promising solution to efficiently acquire data in large-scale wireless sensor networks (WSNs). In a wide-area WSN environment, UAV path planning is one of the challenging issues in solving the optimization problem to achieve complex and multiple objectives under various constraints related to UAV operation. In this paper, we propose a novel asynchronous UAV path planning mechanism for multi-objective UAV operation. In a three-dimensional sensor field, a grid-based sensor field and information gathering model is introduced. We define a UAV coverage area where line-of-sight communication is possible between a UAV and the sensors and propose a method to quickly find the grid-cells within the coverage area. We define a multi-purpose fitness function that maximizes the value of the acquired sensing information and at the same time minimizes the time and energy required for UAV operation. The value of the sensing information reflects the sensor density for each sensor type within UAV coverage, as well as changes in the sensing information values over time. In the proposed method, time and energy objective functions are learned by considering location-dependent communication link quality, sensor density, and the next UAV locations. The optimum UAV position and the movement schedule of each UAV are asynchronously derived using the proposed particle swarm optimization (PSO) algorithm with several UAV operational constraints. The experiment results demonstrate that the proposed method can maximize the utility of the objective function and achieve fast convergence in finding the optimal solution compared with other methods.

A TDOA/AOA Hybrid Positioning Based on Improved Sparrow Search Algorithm for Mobile Position Estimation

To address the difficulty in calculating the nonlinear equation of time difference of arrival (TDOA) positioning, as well as the problem of measurement error in the hybrid time difference of arrival/angle of arrival (TDOA/AOA) positioning algorithm, an improved sparrow search algorithm is proposed to optimize positioning, and the optimization mechanism is retained on the basis of improving the performance of the original algorithm. The maximum likelihood estimation method is used to calculate the objective function, and then, the estimated function of the mobile station is used as the fitness function to generate the initial population of sparrows. Then, using particle swarm optimization, optimize the sparrow search algorithm and obtain the population’s optimal solution in order to obtain the optimal position. The simulation results show that, when compared to the existing algorithm, increasing the number of base stations increases the average accuracy of the sparrow search algorithm (SSA) positioning method by 18.54% and 4.5%, respectively, and, when compared to the proposed particle swarm optimization (PSO) positioning method, by 13.79% and 11.6% as the radius increases. The SSA hybrid positioning algorithm performs better in terms of positioning accuracy, convergence speed, and robustness.

Particle Swarm Optimization-Based Convolutional Neural Network for Handwritten Chinese Character Recognition

Recently, handwritten Chinese character recognition has become an important research field in computer vision. With the development of deep learning, convolutional neural networks (CNNs) have demonstrated excellent performance in computer vision. However, CNNs are typically designed manually, which requires extensive experience and may lead to redundant computations. To solve these problems, in this study, the particle swarm optimization approach is incorporated into the design of a CNN for handwritten Chinese character recognition, reducing redundant computations in the network. In this approach, each network architecture is represented by a particle, and the optimal network architecture is determined by continuously updating the particles until a global particle is identified. The experimental validation resulted in a network accuracy of 97.24% with only 1.43 million network parameters. Therefore, it is demonstrated that the proposed particle swarm optimization method can quickly and accurately find the optimal network architecture.

Task Scheduling Optimization in Cloud Computing by Coronavirus Herd Immunity Optimizer Algorithm

Cloud computing is now dominant in high-performance distributed computing, offering resource polling and ondemand services over the web. So, the task scheduling problem in a cloud computing environment becomes a significant analysis space due to the dynamic demand for user services. The primary goal of scheduling tasks is to allocate tasks to processors to achieve the shortest possible makespan while respecting priority restrictions. In heterogeneous multiprocessor systems, task and schedule assignments significantly impact the system's operation. Therefore, the different processes within the heuristic-based scheduling task algorithm will lead to a different makespan on a heterogeneous computing system. Thus, a suitable algorithm for scheduling should set precedence efficiently for every subtask based on the resources required to reduce its makespan. This paper proposes a novel efficient scheduling task algorithm based on the coronavirus herd immunity optimizer algorithm to solve task scheduling problems in a cloud computing environment. The basic idea of this method is to use the advantages of meta-heuristic algorithms to get the optimal solution. We evaluate the performance of our algorithm by applying it to three cases. The collected findings suggest that the proposed strategy successfully achieved the best solution in terms of makespan, speedup, efficiency, and throughput compared to others. Furthermore, the results demonstrate that the suggested technique beats existing methods new genetic algorithm (NGA), proposed particle swarm optimization (PPSO), whale optimization algorithm (WOA), enhanced genetic algorithm for task scheduling (EGA-TS), gravitational search algorithm (GSA), genetic algorithm (GA), and hybrid heuristic and genetic (HHG) by 22.8%, 12.3%, 8.8%, 7.3%, 7.3%, 3.4%, and 3.4% respectively according to makespan.

A Particle Swarm Optimization and Deep Learning Approach for Intrusion Detection System in Internet of Medical Things

Integrating the internet of things (IoT) in medical applications has significantly improved healthcare operations and patient treatment activities. Real-time patient monitoring and remote diagnostics allow the physician to serve more patients and save human lives using internet of medical things (IoMT) technology. However, IoMT devices are prone to cyber attacks, and security and privacy have been a concern. The IoMT devices operate on low computing and low memory, and implementing security technology on IoMT devices is not feasible. In this article, we propose particle swarm optimization deep neural network (PSO-DNN) for implementing an effective and accurate intrusion detection system in IoMT. Our approach outperforms the state of the art with an accuracy of 96% to detect network intrusions using the combined network traffic and patient’s sensing dataset. We also present an extensive analysis of using various Machine Learning(ML) and Deep Learning (DL) techniques for network intrusion detection in IoMT and confirm that DL models perform slightly better than ML models.

Comparative Study Of P&O and PSO Particle Swarm Optimization MPPT Controllers Under Partial Shading

Maximum power point tracking (MPPT) is a vital and essential requirement for photovoltaic (PV) systems under normal irradiance and partial shading conditions (PSCs). Although, perturb and observe (P&O) algorithm does not map the global maximum power point (GMPP), whereas the algorithm for particle swarm optimization (PSO) tracks it efficiently. This paper explores the rapid determination of GMPP under PSCs using a proposed particle swarm optimization MPPT technique which operates in conjunction with a boost converter. To achieve this analysis, MATLAB/SIMIULINK is used. The results of the simulation illustrate the high tracking performance of the proposed technique under various irradiance patterns.

Resource-Efficient VM Placement in the Cloud Environment Using Improved Particle Swarm Optimization

Fundamentally, a strategy considering the effective utilization of resources results in the better energy efficiency of the system. The aroused interest of users in cloud computing has led to an increased power consumption making the network operation costly. The frequent requests from the users asking for computing resources can lead to instability in the load of the computing system. To perform the load balancing in the host, migration of the virtual machines from the overloaded and underloaded hosts needs to be done, which is considered an important facet concerning energy consumption. The proposed Particle Swarm Optimization based Resource Aware VM Placement (RAPSO_VMP) scheme aims to place the migrated virtual machines. RAPSO_VMP takes into consideration multiple resources like CPU, storage, and memory while trying to optimize the overall resource utilization of the system. According to the simulation analysis, the proposed RAPSO_VMP scheme shows an improvement of 5.51% in energy consumption, reduced the number of migrations by 9.12%, and the number of hosts shutdowns 22.74%.

Fitting of TC model according to key parameters affecting Parkinson's state based on improved particle swarm optimization algorithm

Biophysical models contain a large number of parameters, while the spiking characteristics of neurons are related to a few key parameters. For thalamic neurons, relay reliability is an important characteristic that affects Parkinson's state. This paper proposes a method to fit key parameters of the model based on the spiking characteristics of neurons, and improves the traditional particle swarm optimization algorithm. That is, a nonlinear concave function and a Logistic chaotic mapping are combined to adjust the inertia weight of particles to avoid the particle falling into a local optimum in the search process or appearing premature convergence. In this paper, three parameters that play an important role in Parkinson's state of the thalamic cell model are selected and fitted by the improved particle swarm optimization algorithm. Using the fitted parameters to reconstruct the neuron model can predict the spiking trajectories well, which verifies the effectiveness of the fitting method. By comparing the fitting results with other particle swarm optimization algorithms, it is shown that the proposed particle swarm optimization algorithm can better avoid local optima and converge to the optimal values quickly.

Reconfiguration and Analysis of PV Array based on Particle Swarm Optimization of Solar Plant

Abstract The major shortcoming in the extraction of electrical energy occurs due to partial shading over a limited area of vast spread solar panels underpinning reduction of efficiency. A number of panels are interconnected in series and parallel to form a photovoltaic (PV) array for large power plants and a shadow over a single cell deteriorates overall performance. As a consequence, several peaks are added to the P-V curve causing hotspots in PV panels, degradation of the PV system, and collapse of tracking algorithms. In order to minimize such issues in PV panels, an effective optimization technique is developed by reconfiguring the panels which are capable of reaching the full global power point in a PV system under partial shading conditions. The study proposes particle swarm optimization (PSO) using PV characteristics of Quaid-e-Azam Solar Plant (QASP) in Punjab, Pakistan1. In PSO, electrical connections of PV modules are changed keeping their physical locations unaltered aiming to improve the performance of the PV system. After reconfiguration, the algorithm finds the best combination of PV modules by equalizing the row currents followed by the comparison of row current, voltages, and power of panels. The proposed PSO is proved to be an efficient method for reconfiguring PV modules in very less computational time by increasing the output power of shaded modules.

A cooperative image object recognition framework and task offloading optimization in edge computing

The development of AIoT (Artificial Intelligence of Things) and communication technologies has recently brought with it many promising applications. Intelligent surveillance is one of the new models of applications that synthesizes both technologies of IoTs and the object recognition method of artificial intelligence. However, this system suffers from the heavy computation load problem, but the processing devices are generally lightweight with only limited memory and computation power. In this paper, we propose a cooperative image object recognition framework to integrate the process of AIoT devices into the edge computing environment to overcome this problem. The proposed scheme offloads some captured surveillance video frames to nearby GPU equipped edge servers and then integrates the returned results to enhance the overall recognition accuracy of the surveillance system. We also formulate the AIoT Task Offloading scheduling to a mathematical programming Problem (named ATOP) and prove it to be an NP-complete problem. A heuristic Particle Swarm Optimization algorithm is also proposed to determine near optimal offloading scheduling for the ATOP such that the overall object recognition precision is maximized. Although the object recognition precision is enhanced, there still remains a gap to the ground truth, and the cumulative gap might cause significant errors as times goes by. In this research, we also develop a mechanism to help the designer to automatically diagnose when the cumulative errors become significant. Simulation results demonstrate that the proposed framework is feasible and the proposed Particle Swarm Optimization algorithm for the ATOP outperforms the greedy approach and the genetic algorithm. The simulation results also show that the abnormal data diagnosis mechanism can figure out when the cumulative errors happen using a real-world human-flow counting data set.

Comparison of Various Techniques with PSO based Power Allocation Strategy in Cooperative Wireless Networks

Abstract: Now a days, wireless communication using co-operative networks have attracted many attentions due to its suitability of working in different environments with acceptable performances. During the transmission, a major requirement of optimal power allocation strategy is observed and this is the major concern of many researchers. This power allocation technique requires a suitable optimization algorithm while selecting the power allocation factor for power assignment. In the paper various optimization strategies are compared with proposed particle swarm optimization technique. A cooperative communication frame work is used with amplify and forward as relaying technique. The proposed algorithm using the tech-nique is simulated and the comparison results are obtained. Simulation results when compared outperformed with other previous works. Keywords: Cooperative networks; optimal power alloca-tion; Amplify and forward relaying; Particle Swarm Opti-mization (PSO).

AN OPTIMIZED DESIGN MODELLING OF A NEURAL NETWORK BASED GREEN HOUSE MANAGEMENT SYSTEM USING SOLAR AND RECTIFYING ANTENNA

The renewable energy resources are widely used in various real time applications, which utilized the solar, wind, fuel cell, etc. From this, the energy management and controlling strategy improves the results. The conventional approach uses Quantum Tunneling PSO for optimization and it is managed with various utility on power grid system. The work utilized the solar and EM waves for energy management scheme and it utilized the controlling parameter by optimization algorithm. The drawback of conventional method is that, the hybrid system utilization and switching is performed with random selection and it not capable for hybrid resources of multiple array functioning. The proposed research work performed with the solar with MPPT tracking and EM with rectenna are utilized and with the help of neural network model, the PV and RF signal generations are stored as array and based on the switching duty cycle from the function of proposed particle swarm optimization, the boost converter act to provide the supply to grid. Through the inverter control, the model fed with the grid, which uses PI controlling with PWM signal generation. Based on the demand and grid utility the LC compensation improves the boost converter performance. The PV and RF signal generation utilized on the continuous utility and obtains the demand free grid circuit. By comparing with the proposed and existing approach, the proposed greenhouse management model obtains the better result. Overall simulink model is done with MATLAB 2018a. Keywords- PV module; EM waves; Rectenna; Proposed PSO; Feed Forward neural network; PI controller and grid utility;

Multi-objective optimization of hybrid renewable energy system by using novel autonomic soft computing techniques

An increasing demand in electric power consumption has clearly led to an exhaustion of alternating energy resources. Undoubtedly, it has harmful environmental effects. Hybrid energy and Micro grid can solve this kind of problem. The concept of micro grid is quite significant in cases where transmission of electric power is nither feasible nor profitable. An efficient scheduling of micro grid is able to meet load demand without shedding any load and the optimization is required to make it profitable and eco-friendly. In this regard this work implements a twenty four hours based environmental/economic scheduling of distributed generating units with renewable energy sources in a micro grid connected with main grid .This work proposes a framework for optimal scheduling of micro grid which minimize the cost of generating units as well as emission. Particle Swarm Optimization technique has been employed to solve this problem. Weighting factor is used for optimization in multi-objective framework where both cost and emission are minimized simultaneously. In this paper, a comparative study of employing different types of Particle Swarm Optimization has been made where Hierarchical Particle Swarm Optimization (HPSO) performs better incorporating different constraints. The results of proposed Particle Swarm Optimization method are compared and verified with results of others method which is recently employed. Finally, the comparative study indicates that proposed method gives superior solution than previous method in case of operating cost and emission.

An Improved Energy-Aware Routing Protocol Using Multiobjective Particular Swarm Optimization Algorithm

The energy of sensor nodes in wireless sensor networks is limited, which is one of the most important challenges due to the lack of a fixed power supply. Because data transmission consumes the most energy of nodes, a node that transmits more packets runs out of energy faster than the others. When the energy of a node comes to the end of a network, the process of network operation may be disrupted. In this case, critical information in the network with the desired quality may not reach the hole and eventually the base stations. Therefore, considering the dynamic topology and distributed nature of wireless sensor networks, designing energy-efficient routing protocols is the main challenge. In this paper, an energy-aware routing protocol based on a multiobjective particle swarm optimization algorithm is presented. In the proposed particle swarm optimization algorithm method, the proportionality function for selecting the optimal threaded node is set based on the goals related to service quality including residual energy, link quality, end-to-end delay, and delivery rate. The simulation results show that the proposed method consumes less energy and has a longer lifespan compared with the state-of-the-art methods due to balancing the goals related to service quality criteria.

Evaluation and Implementation of Particle Swarm Optimization Maximumpower Point Tracking Technique for Photo Voltaic System

The power generated from the solar PV panels by photovoltaic effect is varying on the particular day. To extract the peak power from the solar panels maximum power point tracking (MPPT) techniques are developed. The demerits of conventional MPPT techniques are slow tracking of the peak point and inaccurate setting of the peak operating voltage point VMPP. The paper proposes the various MPPT techniques and the particle swarm optimization (PSO) MPPT technique. The proposed PSO-MPPT technique improves the productivityand performance of the system. The comparison of various MPPT algorithms based on the performance characteristics are discussed in the paper. The proposed particle swarm optimization MPPT algorithm is efficient, simple and accurate which increases the panel power, by controlling the duty cycle of the switching pulse in the DC converter section under varying weather conditions. The proposed particle swarm optimization MPPT technique is simulated in MATLAB/SIMULINK.

Study on conical source transient electromagnetic based on AWPSO algorithm

The transient electromagnetic conical field source device can effectively reduce the inductance between the coils and improve the resolution of the small device to detect the shallow underground layer. However, the conventional inversion method requires an initial model and has the disadvantage of low inversion precision. Combined with the results of previous studies, this paper proposed an adaptive weighted particle swarm optimization (AWPSO) algorithm based on Sigmoid function through the analysis and research of PSO, which solved the problem of artificial initial model and low precision of inversion results. By calculating the test function, the algorithm can effectively improve the searching ability of particle swarm optimization algorithm. Several different typical geoelectric models are designed, and the algorithm is applied to data inversion of transient electromagnetic geoelectric model. Combined with the measured data of a hot spring practice area, the inversion calculation and interpretation of the sounding data were carried out, and the inversion calculation results were confirmed by the geological and hydrological data. The results show that the proposed particle swarm optimization algorithm has a high inversion fitting degree to the theoretical model and the measured data, achieves the separation of the apparent resistivity anomalies in the shallow subsurface, and improves the resolution and interpretation accuracy of the measured data in the conical field source transient electromagnetic method.

Multi-modal prediction of breast cancer using particle swarm optimization with non-dominating sorting

Cancer is enlisted as the second leading reason for death across the world wherein almost one person out of six dies of cancer. Breast cancer is one of the most common forms of cancer predominant in women having the second highest mortality rate in the world. Various scientific studies have been conducted to combat this disease, and machine learning approaches have been an extremely popular choice. Particle swarm optimization has been identified as one of the most powerful and efficient technique for the diagnosis of breast cancer guiding physicians towards timely and accurate treatment. It is also pertinent to mention that multi-modal prediction methods are used to make decisions depending upon different scenarios and aspects whereas the non-dominating sorting feature is useful to sort different objects based on differing requirements. The main novelty of this work is multi-modal prediction algorithm for breast cancer prediction is proposed. The work encompasses the use of particle swarm optimization, non-dominating sorting and multi-classifier techniques, namely, k-nearest neighbour method, fast decision tree and kernel density estimation. Finally, Bayes’ theorem is implemented for revising the results to achieve optimum accuracy in the breast cancer prediction. The proposed particle swarm optimization and non-domination sorting with classifier technique model helps to select the most significant features relevant to breast cancer predictions. The selected features design the objective of the problem model. The proposed model is implemented on the WBCD and WDBC breast cancer data sets publicly available from the UCI machine learning data repository. The metrics considered are sensitivity, specificity, accuracy and time complexity. The experimental results of the study using measures such as sensitivity, specificity, accuracy and time complexity. The experimental results of the study are evaluated against the state-of-the-art algorithms, namely, genetic algorithm kernel density estimation and particle swarm optimization kernel density estimation wherein the results justify the superiority of the proposed model.