Earticle

In this paper, an improved one-against-one support vector machine algorithm is used to classify multiple power quality disturbances. To solve the problem of parameter selection, an improved particle swarm optimization algorithm is proposed to optimize the parameters of the support vector machine. By proposing a new inertia weight expression, the particle swarm optimization algorithm can effectively conduct a global search at the outset and effectively search locally later in a study, which improves the overall classification accuracy. The experimental results show that the improved particle swarm optimization method is more accurate than a grid search algorithm optimization and other improved particle swarm optimizations with regard to its classification of multiple power quality disturbances. Furthermore, the number of support vectors is reduced.

The goal of pattern mining is to identify novel patterns in a database. High utility itemset mining (HUIM) is a research direction for pattern mining. This is different from frequent itemset mining (FIM), which additionally considers the quantity and profit of the commodity. Several algorithms have been used to mine high utility itemsets (HUIs). The original BPSO algorithm lacks local search capabilities in the subsequent stage, resulting in insufficient HUIs to be mined. Compared to the transfer function used in the original PSO algorithm, the V-shaped transfer function more sufficiently reflects the probability between the velocity and position change of the particles. Considering the influence of the acceleration factor on the particle motion mode and trajectory, a nonlinear acceleration strategy was used to enhance the search ability of the particles. Experiments show that the number of mined HUIs is 73% higher than that of the original BPSO algorithm, which indicates better performance of the proposed algorithm.

In the case of hard problems to find solutions or complx combination problems, there are various optimization algorithms that are used to solve the problem. Among these optimization algorithms, the representative of the optimization algorithm created by imitating the behavior patterns of the organism is the PSO (Particle Swarm Optimization) algorithm. Since the PSO algorithm is easily implemented, and has superior performance, the PSO algorithm has been used in many fields, and has been applied. In particular, PSO-SAPARB (PSO with Swarm Arrangement, Parameter Adjustment and Reflective Boundary) algorithm is an advanced PSO algorithm created to complement the shortcomings of PSO algorithm. In this paper, this PSO-SAPARB algorithm was applied to the longitudinal controller design of a VTOL (Vertical Take-Off and Landing) aircraft that has the advantages of fixed-wing aircraft and rotorcraft among drones which has attracted attention in the field of UAVs. Also, through the introduction and performance of the Korean SBAS (Satellite Based Augmentation System) named KASS (Korea Augmentation Satellite System) which is being developed currently, this paper deals with the availability of algorithm such as the PSO-SAPARB.

The object of research is based on 1.5 MW wind turbine blade. This paper has carried out the aerodynamic shape optimization design of wind turbine blade. Based on the aerodynamic basic theory of wind turbine blade design and combined with particle swarm optimization algorithm(PSO), the design optimization model of the aerodynamic shape of blade is established. Through this study, the optimization results of the angle inducing a′ and tangential inducing  were obtained. The calculation programs are written and calculated chord length and torsion angle of the blade used by a′ and a. The calculation result for the optimized wind turbine was 1.38 MW when the wind speed was 16 m/s. The 8 % error could be considered as an engineering acceptable error and the calculated values can be proved the correctness of the design value.

The object of research in Based on 1.5MW wind turbine blade. This paper has carried out the aerodynamic shape optimization design of wind turbine blade. Based on the aerodynamic basic theory of wind turbine blade design and combined with particle swarm optimization algorithm, the design optimization model of the aerodynamic shape of blade is established. The calculation programs are written by use of MATLAB and calculate chord length and torsion angle of the blade. Then the shape of wind turbine blade is obtained. As research we can know that the chord length is decreased after optimization design of wind turbine blade, The optimized blade not only meets the actual manufacturing requirement, but also has the largest wind energy utilization coefficient.

최근 인공지능 알고리즘을 활용한 교통 신호 제어에 관한 관심 증대와 함께, 관련 모델구축 연구가 활발히 진행되고 있다. 그러나 대부분의 연구는 독립 교차로를 대상으로, 교통량 변화 에 연동되는 신호 주기 산정을 위한 이론 전개가 주를 이루고 있다. 본 연구에서는 신호제어 알고리즘 구축을 위한 실증 분석을 통해, 신호운영과 회전교차 방식의 실제 교차로를 대상으 로 분석을 진행하였다. 기존 연구에서 많이 활용되는 GA와 PSO 알고리즘을 개선한 PSO-BFO 알고리즘을 제시하여 두 교차로의 운영 효과 증진을 위한 신호제어 방안을 강구 하였다. 그 결과, 158초의 신호 주기하에 신호 교차로의 경우, 용량 증대 3.4%, 지체도 및 정지횟수 감소는 각각 8.2%, 8.3%의 효과가 발생하고, 회전교차로에서는 용량증대 9.2%, 지체도 및 정지횟수 감 소가 각각 7.1%, 27.2%에 이르는 효과가 발생하는 것으로 나타났다.

Recently, research on traffic signal control using artificial intelligence algorithms has been receiving attention, and many traffic signal control models are being studied. However, most studies either focused on independent intersections or are theoretical studies that calculate signal cycle length according to changes in traffic volume. Therefore, this study was conducted on a signalized intersection – roundabout in Gajwa-ro. The Particle Swarm Optimization – Bacterial Foraging Optimization (PSO-BFO) algorithm was proposed, which is developed from the GA and PSO algorithms for minimizing congestion at two intersections. As a result, optimum cycle length was determined to be 158 seconds. The Verkehr In Stadten – SIMulationsmodell (VISSIM) results showed that there was 3.4% increased capacity, 8.2% reduced delay and 8.3% reduced number of stops at the Gajwa-ro signalized intersection. Additionally, at the roundabout, a 9.2% increase in capacity, a 7.1% reduction in delay, and a 27.2% decrease in the number of stops was observed.

In recent years, the problem of network security has been more and more people's attention, as one of the most important technology of network security, intrusion detection technology has gone through nearly thirty years of development, but it still exists some deficiency factors. Aiming at the defects of the traditional BP neural network intrusion detection model in the detection rate and the convergence speed, the improved PSO-BP neural network is applied to intrusion detection system model in this paper. Experimental and simulation, verifying the improved effect of system in the false negative rate, false positives rate and convergence speed of. Detailed analysis of the standard BP neural network algorithm and improved way of common, including gradient descent algorithm and additional momentum algorithm. Local search capability of BP neural network and the global search ability of particle swarm optimization , we have a detailed description of the PSO algorithm is applied to the case of BP neural network and discusses the improved PSO-BP neural network algorithm flow.

Connected dominating set (CDS) problem is a promising approach for backbone formation in wireless sensor networks. Selecting proper nodes to construct the CDS in order to prolong the network lifetime is an important issue when designing connected dominating set algorithms in wireless sensor networks. In this paper, we propose an energy efficient connected dominating set (CDS) scheme in wireless sensor networks which prolongs the network lifetime. In proposed algorithm, we use an optimal weight based on the minimum residual energy and maximum effective degree of nodes for backbone formation to prolong the network lifetime. The optimal weight coefficients are determined using particle swarm optimization (PSO) algorithm. Then, when selecting nodes for dominating set (DS) formation, these coefficients will be used. If the degree of a node is more than coefficient of degree constraint and energy of a node is less than coefficient of energy constraint, the node won't be selected for DS formation. The message and time complexity of the proposed algorithm is O(n). Simulation results show that proposed algorithm outperforms the other methods in terms of network lifetime.

Due to the slow convergent speed of particle and easily get trapped in the local optima, a novel simple PSO algorithm with opposition-based learning average elite strategy is proposed. In this algorithm, a particle updating formula of the simplified swarm optimization (sPSO) algorithm is adopted. Moreover, the opposition-based learning elite strategy and Gaussian disturbance are exerted on the personal best particles and then replace personal best particle of sPSO with the average of elite opposite solutions with Gaussian disturbance of personal best particles. The adjustment of inertia weight is based on setting a threshold and then the inertia weight selects each mode adaptively according to its current state. A set of experimental results on benchmark functions demonstrate that the proposed PSO algorithm is an effective and efficient approach for optimization problems. Furthermore, the T-test analysis shows that the proposed algorithm is able to achieve better results.

A novel approach based θ-Particle Swarm Optimization (θ-PSO) is proposed for optimal selection of the output feedback damping controller parameters for unified power flow controller (UPFC) in order to improve the damping of power system oscillations. The selection of the output feedback gains for the damping controllers is converted to an optimization problem with the time domain-based objective function which is solved by the θ-PSO algorithm. For designing, only local and available state variables are selected as the input stabilizing signals of each controller. Thus, structure of the proposed output feedback controller is simple and easy to implement. To ensure the robustness of the designed controllers, the design process takes into account a wide range of operating conditions and system configurations. Simulation results demonstrate that UPFC with the proposed output feedback controller can more effectively improve the dynamic stability, damp the oscillations, and enhance the transient stability of power system compared to the classical PSO and phase compensation based damping controllers. Moreover, the system performance analysis under different operating conditions shows that the δE based controller is superior to the mB based controller.

One of the most important and effort intensive activity of the entire software development process is software testing. The effort involved chiefly increases because of the need to obtain optimal test data out of the entire search space of the problem under testing. Software test data generation is one area that has seen tremendous research in terms of automation and optimization. Generating or identifying an optimal test set that satisfies a more robust adequacy criteria, like data flow testing, is still a challenging task. A number of heuristic and meta-heuristics like genetic algorithm (GA), Particle Swarm Optimization (PSO) have been applied to optimize the test data generation problem. GA, although more popular, has its own difficulties such as complex to implement and slow convergence rate. In this paper an Adaptive Particle Swarm Optimization (APSO) algorithm is applied to generate test data for data-flow dependencies of a program guided by a novel fitness function. Adaptive PSO is used because of its capability of balancing in exploration and exploitation. A new fitness function is designed based on the concepts of dominance relations, weighted branch distance for APSO to guide the search direction. A set of benchmark programs and four modules of Krishna Institute of Engineering and Technology (KIET), Enterprise resource planning (ERP) system were taken for the experimental analysis. The experimental results show that the proposed adaptive PSO based approach performed significantly better than random search, Genetic Algorithm and PSO in enhancing the convergence speed.

Hadoop uses a reliable, efficient and scalable way to process data. It provides a good solution for dealing with big data. The task scheduler is the core component of Hadoop, and it is responsible for the managing and allocating the cluster resources. Therefore, scheduling algorithm directly affects the overall performance of Hadoop platform and utilization of cluster resource. Based on this, the improved accelerate particle swarm algorithm (IAPSO) is introduced to the cloud environment, and to solve the cloud task scheduling problem in this article. When we use particle swarm algorithm for task scheduling, the tasks are considered as particles, the resource pool is seen as the search space, and the process of finding the optimal solution is considered as a process of task scheduling. If all the sub tasks find the appropriate resources, then stop the iteration and allocate sub asks to the resource nodes. Finally, we simulate the experiment by using CloudSim software. When a single type of task is committed, our algorithm and the other three algorithms can also be used to complete the task scheduling process, and our algorithm is more efficient. But in practice, the cloud computing environment is facing multiuser, and the types of tasks are also varied. With the increase in the number of tasks, the advantage of the other three algorithms decreases gradually, but algorithm in this paper has been exhibited higher efficiency. In addition, with the increase of the number of nodes, task completed time of the algorithm in this paper is significantly less than the other three algorithms, and it has a steady downward trend. Therefore, IAPSO algorithm which is proposed in this paper is applied to solve task scheduling problem in the cloud environment, and it can effectively improve the efficiency of task scheduling.

Aiming at the division roughness of topic classification existing in the most online social networks community, the improved particle swarm optimization algorithm is applied to refine community topics and concepts of community seeds and community topic are also introduced. In this paper, first of all, the explicit links existing in the community are mined, and the basic community structure is constructed, then the community content is deeply analyzed, according to implicit feature between nodes under online community, community topic categories are elaborately refined until structure is stable. Experiments show that this proposed algorithm can accelerate the convergence of the node and greatly improves the topic mining accuracy of online social network compared with the state-of-art CR2NDAS model and PLSA model.

Due to the low computational precision, local optimal solution and slow convergence speed of particle swarm optimization (PSO) algorithm, an improved PSO (SAQPSO) algorithm based on simulated annealing (SA) and quantum theory is proposed in this paper. The first, quantum theory is used to change the updating mode of the particles in order to improve the search speed and the convergence precision, and guarantee the simplification and effectiveness. Then the SA with probability and local search ability is introduced into quantum PSO (QPSO) in order to keep the diversity of the population, avoid falling into local optimum and enhance the global search ability. The SAQPSO algorithm keeps the characteristics of the simple and easy implementation, improves the global optimization ability and the convergence speed and the accuracy. Finally, some benchmark functions are used to prove the validity of the proposed SAQPSO algorithm. The computational results show that the proposed SAQPSO algorithm takes on the fast convergence speed, the better robustness and global search ability.

Particle swarm optimization (PSO) algorithm is simple stochastic global optimization technique, but it exists unbalanced global and local search ability, slow convergence speed and solving accuracy. An improved simulated annealing (ISAM) algorithm is introduced into the PSO algorithm with crossover and Gauss mutation to propose an improved PSO (ISAMPSO) algorithm based on the mutation operator and simulated annealing in this paper. In the ISAMPSO algorithm, the mutation operator of genetic algorithm is introduced into the SA algorithm as a generation mechanism of new solution in order to propose an improved simulated annealing algorithm with mutation (ISAM). Then the ISAM algorithm is introduced into the PSO algorithm to jump out the local optimum, effectively achieve the global optimum adjust and optimize the population, maintain the diversity of the population, improve the local search ability and convergence speed. Six classical functions are selected to test the performance of the proposed ISAMPSO algorithm. The simulation experiments results show that the proposed ISAMPSO algorithm can effectively overcomes the stagnation phenomenon and enhance the global search ability. The convergence speed and accuracy were better than the PSO algorithm.

The Cloud computing has become the fast spread in the field of computing, research and industry in the last few years. As part of the service offered, there are new possibilities to build applications and provide various services to the end user by virtualization through the internet. Task scheduling is the most significant matter in the cloud computing because the user has to pay for resource using on the basis of time, which acts to distribute the load evenly among the system resources by maximizing utilization and reducing task execution Time. Many heuristic algorithms have been existed to resolve the task scheduling problem such as a Particle Swarm Optimization algorithm (PSO), Genetic Algorithm (GA), Ant Colony Optimization (ACO) and Cuckoo search (CS) algorithms, etc. In this paper, a Dynamic Adaptive Particle Swarm Optimization algorithm (DAPSO) has been implemented to enhance the performance of the basic PSO algorithm to optimize the task runtime by minimizing the makespan of a particular task set, and in the same time, maximizing resource utilization. Also, .a task scheduling algorithm has been proposed to schedule the independent task over the Cloud Computing. The proposed algorithm is considered an amalgamation of the Dynamic PSO (DAPSO) algorithm and the Cuckoo search (CS) algorithm; called MDAPSO. According to the experimental results, it is found that MDAPSO and DAPSO algorithms outperform the original PSO algorithm. Also, a comparative study has been done to evaluate the performance of the proposed MDAPSO with respect to the original PSO.

With the development of computer technology, more and more intelligent algorithms in the solution of different problems in many aspects of society are extensively used. Calculation of the minimum values of the function optimization and finding the optimal solution of combinatorial optimization problems in certain space are the two typical problems. In the fields of science and engineering, many optimization problems are constrained with different conditions. Due to the existence of constraints, the optimization problems are more difficult than the unconstrained optimization problem. Therefore, research on how to make the objective function find the optimal solution in the feasible region is of great significance As an important intelligent algorithm, particle swarm optimization (PSO) is widely used in the calculation of the optimal solution of the constraint problems. But due to the disadvantages of the PSO, its search efficiency is quite low when the particle is close to the optimal value. On the other side, it is easy to search the local optimal solution but difficult to get the global optimal solution. So, it is necessary to modify the algorithm to improve the performance. In the paper, we modify the algorithm and propose a modified algorithm (M-PSO). With the simulation, the results show the validity of the algorithm.

Particle swarm optimization(PSO) algorithm has the advantages of simplicity and easy implementation, but it exits the weaknesses of the being easy to fall into local minimum and premature convergence. In order to overcome these weaknesses of PSO algorithm, the inertia weight and learning factor are improved and the PSO algorithm is initialized by using chaotic optimization in order to propose an improved PSO(WLFCPSO) algorithm. In the proposed WLFCPSO algorithm, chaotic optimization strategy is used to initialize the parameters of PSO algorithm in order to obtain the more reasonable initialization parameters. The adaptive inertia weight adjustment strategy is used to control the adjustment ability of inertia weight in order to keep the diversity of the inertia weight. The dynamic linear adjustment strategy for learning factors is used to gradually reduce the cognitive ability of the individual and improve the global search ability of particles. In order to prove the effectiveness of the proposed WLFCPSO algorithm, several benchmark functions are selected. The experiment results show that the proposed WLFCPSO algorithm has the rapider convergence speed and higher solution precision for solving high-dimension function optimization problems.

Particle swarm optimization (PSO) algorithm is a population-based search algorithm by simulating the social behavior of birds within a flock. It is a simple and efficient optimization algorithm. But it exists the low computational speed and easy falling into local optimal solution in solving the complex problem. So the quantum theory, adaptive inertia weight, disturbance factor and diversity mutation strategy are introduced into the PSO algorithm in order to propose an improved PSO(IWDMDQPSO) algorithm in this paper. In the IWDMDQPSO algorithm, the quantum theory is used to change the updating mode of the particles for guaranteeing the simplification and effectiveness of the algorithm. The adaptive inertia weight is used to improve the premature convergence of the algorithm. The disturbance factor is used to avoid the premature of the algorithm. The diversity mutation strategy is used to improve the global searching ability and computation speed. Finally, the famous benchmark functions are selected to prove the performance and effectiveness of the proposed IWDMDQPSO algorithm. The experiment results show that the proposed IWDMDQPSO algorithm takes on better solving accuracy and higher computation speed in solving the complex function. So it has a remarkable optimization performance.