Greedy Particle Swarm Optimization Research Articles

Industrial defect detection and location based on greedy particle swarm optimization algorithm

ABSTRACT Particle swarm optimization algorithm is a branch of evolutionary computing and can search for a better solution in a given feature space. This paper introduces the particle swarm optimization algorithm and greedy strategy for the defect detection and location of industrial components and then proposes a greedy particle swarm optimization algorithm. This paper employs sparse random projection to map the vast high-dimensional information to the low-dimensional space while maintaining the relative distance between the data. This employment helps to accelerate the training and prediction speed of the model and remove some unimportant features or noise. This algorithm first adopts particle swarm optimization (PSO) to initialize the cluster centers in an effort to minimize the maximum distance between all unlabeled data points and these centers. The algorithm then utilizes the greedy strategy to select a batch of data points to represent the corresponding features of the normal image, thereby improving the coverage of the model to the data. Experiments have shown that the results of most categories of data sets are close to or better than the current existing methods, especially in defect detection. In terms of defect localization for object categories, our method achieves a pixel-level anomaly localization index (AUROC) of 98.3% on the MVTec AD dataset.

Improvement of Energy Performance Index for Domestic Prosumers Based on Newly Proposed Dynamic Tariff and Rule-Based Strategy

A smart and intelligent energy management system (SIEMS) can make the existing system more reliable, robust, and cost-effective to deal with the present power scenario. This also initiates the necessity to develop a new dynamic tariff system and integrate renewable energy sources (RES) along with the conventional grid which in turn reduces carbon emission. Many countries have adopted different strategies for energy conservation based on energy conservation code, the main aim of which is to enforce design and development of household appliances for efficient power consumption. From data provided by utility sectors, it has been found that even in few countries 25% to 28% of the total energy is consumed by domestic sector and 45% of other residential loads also contribute a major part of the total domestic load consumed in any country. As a whole, residences, which consist of light electrical loads and home appliances constitute prosumers. The total energy consumed by prosumers is also intended by Bureau of energy efficiency, to make them fall under these codes (Energy Conservation Building Code) so that they can be treated on a scale of 1 star to 5 stars. This in turn will help in improving the energy performance index (EPI). In this paper, the optimal scheduling model of household appliances and energy storage system (ESS) has been designed based on the availability of renewable energy sources and newly proposed dynamic tariff system. To validate the efficiency of the model, we have comparatively evaluated the performance of the model with different feature selection methods and optimization techniques. A case study has been done and it has been found that the weighted K nearest neighbor method for feature selection and hybrid greedy particle swarm optimization (HGPSO) technique for optimization are performing better than other existing methods. The proposed model reflects the cost-effectiveness and improvement in EPI for prosumers.

Renewable energy based dynamic tariff system for domestic load management

To deal with the present power-scenario, this paper proposes a model of an advanced energy management system, which tries to achieve peak clipping, peak to average ratio reduction and cost reduction based on effective utilization of distributed generations. This helps to manage conventional loads based on flexible tariff system. The main contribution of this work is the development of three-part dynamic tariff system on the basis of time of utilizing power, available renewable energy sources (RES) and consumers’ load profile. This incorporates consumers’ choice to suitably select for either consuming power from conventional energy sources and/or renewable energy sources during peak or off-peak hours. To validate the efficiency of the proposed model we have comparatively evaluated the model performance with existing optimization techniques using genetic algorithm and particle swarm optimization. A new optimization technique, hybrid greedy particle swarm optimization has been proposed which is based on the two aforementioned techniques. It is found that the proposed model is superior with the improved tariff scheme when subjected to load management and consumers’ financial benefit. This work leads to maintain a healthy relationship between the utility sectors and the consumers, thereby making the existing grid more reliable, robust, flexible yet cost effective.

An Improved Mathematical Model for Green Lock Scheduling Problem of the Three Gorges Dam

In recent years, the environmental pollutions at the Three Gorges Dam have become an increasingly concerning issue of the Chinese government. One of the most significant environmental problems is the carbon emissions from the lockage operations at the two ship locks of the Three Gorges Dam. Currently, due to the large amount of vessels passing through the dam, there is always a long queue of vessels on both sides and the average waiting time is long. This has further lead to an increased amount of fuel consumption and carbon emissions. Therefore, it is of great importance to develop a decision-support model for a better navigation scheduling and planning of the lockage operations at the Three Gorges Dam. This paper proposed an improved mixed integer non-linear programming model for the green lock scheduling problem at the Three Gorges Dam. The model aims at minimizing the carbon emissions and the waiting time in the lockage process through scheduling the vessels in a fairer and more efficient manner. Moreover, a greedy particle swarm optimization (G-PSO) algorithm is developed to solve the complex optimization problem. The proposed mathematical model and algorithm are validated through a numerical experiment. The result shows that it may lead to a significant reduction on carbon emissions by giving a specified speed to each vessel with a pre-optimized sequence. Meanwhile, the fairness and efficiency of the lockage process may also be improved.

A greedy particle swarm optimization (GPSO) algorithm for testing real-world smart card applications

Software testing continues to be regarded as a necessary and critical step in the software development life cycle. Among the multitudes of existing techniques, particle swarm optimization (PSO) algorithm, in particular, has shown superior merits for automatically generating software test cases for its easy implementation and for relying on fewer parameters that require tuning. Hence, several state-of-the-art PSO-based algorithms have been successfully used as a test data generator. On the other hand, greedy-based algorithms, which are commonly used to solve complex and multi-step combinatorial problems, are starting to gain momentum as a solution for the complexity problem of software testing. Greedy algorithms favored over other techniques when the solution of the problem is guaranteed to be near-optimal. As a result, the utilization of both greedy and PSO algorithms in a single solution for automatically generating test data represents a strong candidate if designed carefully. In this paper, we propose a novel hybrid greedy and PSO algorithm (GPSO) that jointly guarantees the effectiveness and close to optimality results for generating a minimum number of test data. Compared with the widely employed genetic algorithm (GA), our proposed GPSO outperforms the GA in terms of the average number of iterations, execution time, and coverage percentage. Experimental trials with six different typical Java card applications show that the use of the proposed GPSO as a test data generator results in an outstanding performance.

Virtual machine-based task scheduling algorithm in a cloud computing environment

Virtualization technology has been widely used to virtualize single server into multiple servers, which not only creates an operating environment for a virtual machine-based cloud computing platform but also potentially improves its efficiency. Currently, most task scheduling-based algorithms used in cloud computing environments are slow to convergence or easily fall into a local optimum. This paper introduces a Greedy Particle Swarm Optimization (G&PSO) based algorithm to solve the task scheduling problem. It uses a greedy algorithm to quickly solve the initial particle value of a particle swarm optimization algorithm derived from a virtual machine-based cloud platform. The archived experimental results show that the algorithm exhibits better performance such as a faster convergence rate, stronger local and global search capabilities, and a more balanced workload on each virtual machine. Therefore, the G&PSO algorithm demonstrates improved virtual machine efficiency and resource utilization compared with the traditional particle swarm optimization algorithm.

Optimum Resource Allocation of Database in Cloud Computing

Cloud computing is a new generation of computing based on virtualization technology. An important application on the cloud is the Database Management Systems (DBMSs). The work in this paper concerns about the Virtual Design Advisor (VDA). The VDA is considered a solution for the problem of optimizing the performance of DBMS instances running on virtual machines that share a common physical machine pool. It needs to calibrate the tuning parameters of the DBMS’s query optimizer in order to operate in a what-if mode to accurately and quickly estimate the cost of database workloads running in virtual machines with varying resource allocation.The calibration process in the VDA had been done manually. This manual calibration process is considered a complex, time-consuming task because each time a DBMS has to run on a different server infrastructure or to replace with another on the same server, the calibration process potentially has to be repeated. According to the work in this paper, an Automatic Calibration Tool (ACT) has been introduced to automate the calibration process.Also, a Greedy Particle Swarm Optimization (GPSO) search algorithm has been proposed and implemented in the VDA instead of the existed greedy algorithm to prevent the local optimum states from trapping the search process from reaching global optima. The main function of this algorithm is to minimize the estimated cost and enhance the VMs configurations.The ACT tool and the GPSO search algorithm have been implemented and evaluated using TPC-H benchmark queries against PostgreSQL instances hosted in Virtual Machines (VMs) on the Xen virtualization environment.

A Greedy Particle Swarm Optimization Strategy for T-way Software Testing

A Greedy Particle Swarm Optimization Strategy for T-way Software Testing