Optimization PSO Research Articles

Compare between PSO and artificial bee colony optimization algorithm in detecting DoS attacks from network traffic

Our world today relies heavily on informatics and the internet, as computers and communications networks have increased day by day. In fact, the increase is not limited to portable devices such as smartphones and tablets, but also to home appliances such as: televisions, refrigerators, and controllers. It has made them more vulnerable to electronic attacks. The denial of service (DoS) attack is one of the most common attacks that affect the provision of services and commercial sites over the internet. As a result, we decided in this paper to create a smart model that depends on the swarm algorithms to detect the attack of denial of service in internet networks, because the intelligence algorithms have flexibility, elegance and adaptation to different situations. The particle swarm algorithm and the bee colony algorithm were used to detect the packets that had been exposed to the DoS attack, and a comparison was made between the two algorithms to see which of them can accurately characterize the DoS attack.

Data Analysis of Amazon Product Based on LSTM and GPR

<p>In this paper, we propose a method that combines models such as GPR with PSO optimization to predict the time series data. We use LSTM and TOPSIS with entropy weight method modification to process vari-ous types of data from various aspects, taking into account both tabular and textual data, and to mine valuable contents from them. Based on shopping data, we analyze the historical situation and predict the future sales of products. So that we can recommend the most suitable products for customers. At the same time, for merchants, this paper provides directions for product optimization and improvement of advertising and marketing strategies.</p> <p> </p>

Shale oil production prediction and fracturing optimization based on machine learning

With the advancement of horizontal well and hydraulic fracturing technology, the development of unconventional reservoirs such as shale oil has become a hot issue in the energy field. However, production tests have demonstrated that production is non-uniformly between stages due to reservoir heterogeneity and fracturing design limitations. Therefore, it makes sense to improve fracturing design to enhance shale oil development. In this paper, we propose a computational framework for shale oil production prediction and fracturing parameters optimization that couples machine learning and particle swarm optimization (PSO). Firstly, we construct a deep neural network (DNN) model database with 841 numerical simulation data as training set and validation set, and 87 field data as test set. Secondly, the hyperparameter optimized DNN are performed to predict the production performance. And the predictive performance compares to the random forest (RF) and support vector machine (SVM). Thirdly, coupled with DNN, PSO is performed to optimize fracturing parameters. Finally, conducting rapid fracturing design based on PSO optimization results and reservoir sweet spot distribution. The results reveal that DNN exhibit best production prediction accuracy compared to RF and SVM. The generalization ability of DNN is verified by accurate prediction performance of 4 cases with extreme parameters. Optimized fracturing parameters using PSO in an actual well resulted in 2969 m3 increases in cumulative oil and 68*104 USD increases in NPV. According to the optimization results of PSO in four extreme cases, the reasonable fracturing parameters for different reservoir quality are obtained, including the number of fracturing stages and clusters, the volume of single stage fracturing fluid and proppant. Our work guides engineers in rapid fracturing design while improving shale oil development effect.

Fuzzy Neural Network PID Strategy Based on PSO Optimization for pH Control of Water and Fertilizer Integration

In the process of crop cultivation, the application of a fertilizer solution with appropriate pH value is more conducive to the absorption of nutrients by crops. If the pH of the irrigation water and fertilizer solution is too high, it will not only be detrimental to the absorption of nutrients by the crop, but will also damage the structure of the soil. Therefore, the precise regulation of pH in water and fertilizer solutions is very important for agricultural production and saving water and fertilizer. Firstly, the article investigates the hybrid control of fertilizer and water conditioning systems, then builds a fuzzy preprocessing controller and a neural network proportional–integral–differential controller, and optimizes the neural network parameters by means of an improved particle swarm algorithm. The effectiveness of the controller was verified by comparison with the common proportional–integral–differential control and fuzzy algorithm control for fertilizer control and fuzzy preprocessing neural network control. Simulation experiments for this study were designed through the MATLAB/Simulink simulation platform, and the simulation results show that the algorithm has good tracking and regulation capabilities in the system. Finally, the four control algorithms are experimentally validated under different pH regulations using designed field experiments. The results show that, compared with other control algorithms, the control algorithm in this paper has a smaller overshoot and good stability with a shorter rise time, which can achieve the purpose of better regulating the fertilizer application system.

A Hydro-Economic Model to Support Water Scarcity

Climate variability is reflected in water affluence that directly impacts the availability and level of water in reservoirs. Economic instruments, such as tariffs, are increasingly being used to promote the rational use of water. This study offers a floating rate model for charging raw water as a function of the reservoir level. The model was designed in the Jaguaribe–Metropolitan System, a place characterized by water-use conflicts during water scarcity. The model was developed as a function of the unit payment capacity (UPC) and drought states of the hydrographic regions. We applied the free software R and PSO optimization package to define the optimal UPC fraction and evaluated the model sensitivity using a synthetic series generated with the Markov chain method. Consequently, we observed that comfortable, alert, and critical situation levels predominated in the sensitivity analysis, and the average collections paid for administration, operation, and maintenance (AO&M) costs. In some cases, a collection surplus that can be managed through a financial fund to finance the system in periods of critical shortage is generated.

Comparative Study and Performance Analysis of PSO, ABC, BFO and Cuckoo Search Optimization Techniques on UPFC Device for Voltage Stability Margin Improvement

Comparative Study and Performance Analysis of PSO, ABC, BFO and Cuckoo Search Optimization Techniques on UPFC Device for Voltage Stability Margin Improvement

PSO Algorithm-Based Design of Intelligent Education Personalization System.

The application of artificial intelligence in the field of education is becoming more and more extensive and in-depth. The intelligent education system can not only solve the limitations of location, time, and resources in the traditional learning field but it can also provide learners with a convenient, real-time, and interactive learning environment and has become one of the important applications in the Internet field. Particle swarm optimization (PSO) is a swarm intelligence-enabled stochastic optimization scheme. It is derived from a model of bird population foraging behavior. Because of its benefits of ease of implementation, high accuracy, and quick convergence, this algorithm has gained the attention of academics, and it has demonstrated its supremacy in addressing real issues. This paper aims to study the optimization of PSO in the field of computational intelligence, improve the matching degree of learning resource recommendation and learning path optimization, and improve the learning efficiency of online learners. This paper suggests intelligent education as the center, takes the PSO algorithm as the main research object, and expounds the related concepts of intelligent education and PSO algorithm. It uses swarm intelligence algorithms for intelligent education personalized services. He focuses on PSO algorithm and its work in intelligent education recommendation and learning path planning. Experiments show that the average value of the difference between the two obtained by the NBPSO algorithm is 1.13E + 02 and the variance 1.88E + 02 is the smallest. Therefore, PSO aids in improving the quality and consistency of online course resource development. In conclusion, the research results of this paper further demonstrate the advantages of PSO algorithm in solving the problem of personalized service in intelligent education. It can promote the in-depth application of swarm intelligence optimization algorithms in intelligent online learning systems. This effectively enhances the intelligent service level of the online learning system and increases the efficiency of online learning.

Design of Drug Sales Forecasting Model Using Particle Swarm Optimization Neural Networks Model.

The establishment of enterprise target inventory is directly related to the forecast of drug sales volume. Accurate sales forecasting can help businesses not only set accurate target inventory but also avoid inventory backlogs and shortages. In this paper, NN technology is used to forecast sales and is optimized using the PSO algorithm, resulting in the creation of a drug sale forecast model. The model optimizes the weights and thresholds of NN using the improved PSO optimization algorithm and predicts the periodic components based on time correlation characteristics, effectively describing the trend growth and seasonal fluctuations of sales forecast data. Furthermore, the model in this paper has been creatively improved according to the needs of practical application, which has improved the shortcomings of traditional NN, such as long training time, slow convergence speed, and ease to fall into local minima, to improve performance and quality, and has received positive results in application. The experimental results show that this model has a prediction accuracy of 96.14 percent, which is 12.78 percent higher than the traditional BP model. The optimized model can be used to forecast drug sales in a practical and feasible way.

Optimal Path and Timetable Planning Method for Multi-Robot Optimal Trajectory

In an environment with limited space and dense goal configuration, the path of robot team is forced to coincide without much adjustment space, which is a challenge for multi-robot collaborative path planning. In this work, a novel Optimal Path and Timetable Planning (OPTP) method is proposed. The OPTP firstly generates the near-shortest paths for each robot by an RRT*-based planner. Then the timetables for each robot in the path-time space are created by the improved Particle Swarm Optimization (PSO) method. A heuristic bias is added to the PSO optimizer to efficiently mediate the conflict near the goal configuration. The OPTP achieves the near-shortest moving distance of the multi-robot team, as well as the near-optimal navigation makespan in face of complex obstacles, narrow channels, and dense goal configurations. The compared simulations and real-world experiments verify the effectiveness of the OPTP method.

Intelligent voltage and frequency control of islanded micro-grids based on power fluctuations and communication system uncertainty

Control of critical micro-grid factors such as voltage/frequency is complex and challenging in power distribution networks that include micro-grids. Therefore, providing an efficient and optimal control framework to maintain stability and control the critical factors of the network significantly affects the development of micro-grids goals. The present study proposed the intelligent voltage/frequency control scheme in primary and secondary micro-grids. Micro-grid voltage/frequency restoration was planned based on the PSO-Fuzzy control algorithm in the primary control. In addition to optimizing the members of the fuzzy controller, the PSO optimization algorithm was also used to calculate the voltage/ frequency deviation based on the voltage error factors and the violation of the deviation from the frequency reference. The PSO-Fuzzy structure was provided to optimize hybrid energy storage units' charge and discharge thresholds. Moreover, an intelligent artificial neural network algorithm was presented based on Lyapunov stability equations and a communication system platform to compensate for the voltage/frequency deviation in the secondary control. The proposed algorithm had optimal and efficient performance in different scenarios, such as the effect of load dynamic and its type, power fluctuations, and communication system delays.

Optimization of terahertz fingerprint and identification capabilities by using PSO algorithm

In the terahertz range, materials are often characterized by a specific spectral response that contains unique resonant frequencies, which allows to detect and identify them very precisely. In this work, we have developed a new efficient calculating model that can be applied to identify the resonance frequencies of the material using terahertz time-domaine spectroscopy measurements in transmission mode. Furthermore, the PSO optimization algorithm is an extremely powerful tool that, once associated with our model, allowed us to quickly and accurately extract the optical characteristics of the material such as the absorption and the refractive index of the material. The performances of the proposed technique are very relevant particularly in the case of important noise.

Metaheurystic optimization of CFD–multiphase population balance and biokinetics aeration stirrer tank bioreactor of sludge flocs for scale-up study with bio(de/re)flocculation

In this paper, dynamic behavior and optimization of aerated sludge flocs stirrer tank bioreactors in scale-up study have been investigated. Three-dimensional CFD multiphysics model of bioreactor with multiphase population balance and biokinetics with metaheurystic process optimization has been developed. Simulation of hydrodynamics-PBM-kinetic relation on biomass growth have been investigated in full transient CFD analysis. De(re)flocculation event was induced to impact of bioflocculation phenomena, which has an important impact of aeration bioprocess efficiency. In this paper it is evidenced that population balance and bio(de/re)flocculation is a crucial factor affecting on process efficiency. Selected metaheurystic algorithm (genetic GA, ant colony optimization ACO, particle swarm optimization PSO) has been used to bioprocess parameter optimization. The results showed that the best value is achieved by ACO, but PSO and GA also perform satisfactory results of parameter optimization process model.

Optimization of baseline configuration in a GNSS network (Nile Delta network, Egypt) – A case study

Abstract When starting any GNSS measurements, there is a need to establish a survey plan with the required optimal baselines. The optimal GNSS baselines can be chosen by solving the geodetic second-order design (SOD). The particle swarm optimization PSO is used widely to solve geodetic design issues. This work employed the particle swarm optimization (PSO) algorithm, a stochastic global optimization method, to select the optimal GNSS baselines. The optimal baselines satisfy the set criterion matrix at a reasonable cost. The fundamentals of the algorithm are presented. The effectiveness and usefulness of the technique are then demonstrated using a Nile Delta GNSS network as an example. In some cases, we have to observe many GNSS benchmarks with limited instrumentations. PSO represents a powerful tool for optimizing baseline to get the required accuracy with limited capabilities (like limited receivers). The PSO algorithm, a stochastic global optimization approach, was used in this paper to find the best observation weights to measure in the field that will match the predetermined criterion matrix with a fair degree of precision. The method’s fundamentals are presented with an actual geodetic network over the Nile delta in Egypt. In the current work, two survey strategies were applied. One represents a case with 9 GNSS receivers (high capability), and another one represents the tested survey plan with limited GNSS receivers (3 receivers, low capability) after applying PSO. By comparing two survey strategies, applying the PSO algorithm to a real Nile delta geodetic network shows its effectiveness on the obtained coordinate accuracy. This obtained accuracy ranged from 2 mm to 3 mm in X, Y, Z, and 3 mm in height. Also, the linear closure error between known and estimated coordinates improved to be 1.4 cm after applying PSO.

Research on control strategy of asymmetric electro-hydraulic servo system based on improved PSO algorithm

In the electro-hydraulic servo control system, there are some problems, such as low position control accuracy, uncontrollable speed, speed impact, and asymmetric control due to the asymmetry of hydraulic cylinder. To solve the above problems, this paper proposes a Fuzzy PID control algorithm with load force compensation based on improved PSO optimization. This improved particle swarm optimization algorithm introduces crossover and mutation operations in genetic algorithm to improve the optimization performance of traditional particle swarm optimization algorithm. The mathematical model of valve controlled asymmetric cylinder is established, and the Amesim linearization analysis function is used to identify the system, establish the transfer function, and build the control system. The joint simulation and test results of Amesim and MATLAB show that the proposed control strategy can realize the simultaneous control of speed and position. Under different loads, different speeds, and different input follow signals, it does not need to adjust any parameters. Regardless of forward or reverse operation, the optimal dynamic performance and minimum steady-state error are obtained, which greatly improves the response speed of the system. The effectiveness and superiority of the improved PSO compound control strategy are verified.

Quality Evaluation for Physical Education Teaching in Colleges with Joint Neural Network

A new teaching curriculum for physical education in colleges has been proposed as part of the teaching reform. New developments in content, goals, and teaching methods have also occurred, and these have gradually become the focus of current physical education researchers. By developing a model for objectively, truly, comprehensively, and accurately evaluating college physical education teaching, it will be possible not only to improve the quality of physical education instruction and the effectiveness of faculty in achieving their goals but also to improve the quality of programs. This research work proposes a Joint Neural Network (JNN) composed of an Improved Support Vector Machine (ISVM) and improved Back Propagation (BP) network for evaluating physical education quality in colleges. When using a standard SVM to classify feature data, the parameters used have an impact on the SVM’s classification. This study introduces an improved SVM with hybrid optimization of PSO and GA algorithms, combining the properties of genetic algorithms and particle swarm optimization. As the existing BP network is trapped with a local optimum, this work proposes an optimized BP network algorithm using the bat algorithm. The improved SVM and improved BP are then combined to form a joint neural network for evaluating the quality of physical education in colleges. Comprehensive and systematic experiments validate the correctness and effectiveness of the algorithm proposed in this paper.

QUAntum Particle Swarm Optimization: an auto-adaptive PSO for local and global optimization

QUAntum Particle Swarm Optimization: an auto-adaptive PSO for local and global optimization

Particle Swarm Optimization Based Optimal Design of Six-Phase Induction Motor for Electric Propulsion of Submarines

Recent research reveals that multi-phase motors in electric propulsion systems are highly recommended due to their improved reliability and efficiency over traditional three phase motors. This research presented a comparison of optimal model design of a six phase squirrel cage induction motor (IM) for electric propulsion by using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). A six phase squirrel cage induction motor is designed and simulated by ANSYS Motor-CAD. In order to find the best fit method, simulation results are compared and applied to the motors for electric propulsion, considering the influence of design upon the motor performance. The six-phase squirrel cage induction motor is more energy efficient, reliable and cost effective for the electric propulsion compared to the conventional three phase motor. In this study, first the initial parameters of the six phase squirrel cage induction motor have been determined and then these parameters have been compared with optimized values by Genetic Algorithm (GA) and PSO optimization. The motor designed is optimized using efficiency and power losses as the fitness function. The six phase squirrel cage induction motor is designed using ANSYS Motor-CAD and the simulation results were also presented along with two-dimensional and three-dimensional geometry. The result shows that the weight and power loss are reduced to 161 kg and 0.9359 Kw respectively, while the efficiency and power factor are increased to 0.95 and 0.87 respectively when PSO is used. This shows that the result is promising.

Comparative Analysis of Electric Traction System with PI Controller and PSO Optimization Algorithm

Electrical traction refers to a system that uses electrical power for traction, such as railways, trams, trolleys, and other vehicles. The term "track electrification" refers to the type of power source that used power electric locomotive systems. It could be AC, DC, or a hybrid supply. This paper provides the comparative analysis of electric traction system with PI controller and PSO Optimization Algorithm

Adaptive Gaussian Quantum based PSO and TSA optimization for parametric Optimizaiton of Toughned glass on Toughening machine

Usually, toughened glasses are used for safer road transport and general purposes. This is because toughened glasses are difficult to break since these types of glasses are four to five times stronger than ordinary glasses. Meanwhile, the compressive strength of the glass needs to be enhanced and tensile strength needs to be minimized to enhance the toughening glass quality. In addition to this, both cutting and machining parameters need to be optimized and validate with the production rate and the company product thus optimizing the production cost. In this paper, the machining and cutting parameters as well as the production cost are optimized using a novel technique named Adaptive Gaussian Quantum behaved Particle Swarm Optimization algorithm and Tunicate Swarm algorithm (AGQPSOA-TS) approach. Here, two different algorithms namely Adaptive Gaussian Quantum behaved Particle Swarm Optimization algorithm and Tunicate Swarm algorithm are integrated and proposed a novel technique named AGQPSOA-TS algorithm. Finally, the experiments are carried out with the aim of enhancing the compressive strength and minimizing the tensile strength of the toughened glass. According to the Indian standards, the thickness and dimensions of the glass workpiece are taken as 5 mm and 200mmx200mm respectively. The comparative evaluations are conducted for compressive strength, tensile strength as well as production cost to depict the efficiency of the proposed system.

Performance Comparison of Particle Swarm Optimization and Genetic Algorithm Combined with A* Search for Solving Facility Layout Problem

Optimization metaheuristics have become necessary due to the growing demand for better and more realistic designs. This paper proposes a metaheuristic-based approach for solving design problems in a reasonable time while browsing large spaces of solutions. The objective of this article is to compare the performance of two methods Genetic Algorithm GA and Particle swarm optimization PSO, combined with A* algorithm, in solving a constrained facility layout problem. The two chosen metaheuristics have been successfully applied in many search problems. We consider their speed and performance. The performance of the obtained solutions is measured in terms of the total distance traveled by products in the workshop. In order to determine the shortest path in a realistic way between workstations in a given irregular area (with aisle structure, or material storage areas, lunchrooms and offices), the A* algorithm was integrated with them. The comparison therefore concerns <GA, A*> and <PSO, A*>. GA and PSO algorithms generate configurations for which the shortest path for any couple of machines is identified through the A* search algorithm taking into account of obstacles. The mathematical model used and the parameters of the genetic algorithm are those developed in (Besbes et al. 2019). The numerical results show the feasibility and effectiveness of both approaches. Our results demonstrate that GA yields a better solution than Particle Swarm Optimization in total distance travelled while PSO is faster.