Discrete Binary Particle Swarm Optimization Research Articles

Multi-Objective Dynamic Reconstruction of Distributed Energy Distribution Networks Based on Stochastic Probability Models and Optimized Beetle Antennae Search

In the dynamic optimization problem of the distribution network, a dynamic reconstruction method based on a stochastic probability model and optimized beetle antennae search is proposed. By implementing dynamic reconstruction of distributed energy distribution networks, the dynamic regulation and optimization capabilities of the distribution network can be improved. In this study, a random probability model is used to describe the uncertainty in the power grid. The beetle antennae search is used for dynamic multi-objective optimization. The performance of the beetle antennae search is improved by combining it with the simulated annealing algorithm. According to the results, the optimization success rate of the model was 98.7%. Compared with the discrete binary particle swarm optimization algorithm and bacterial foraging optimization algorithm, it was 9.3% and 26.1% faster, respectively. For practical applications, this model could effectively reduce power grid transmission losses, with a reduction range of 16.7–18.6%. Meanwhile, the charging and discharging loads were effectively reduced, with a reduction range of 16.2–19.7%. Therefore, this method has significant optimization effects on actual power grid operation. This research achievement contributes to the further development of dynamic reconstruction technology for distribution networks, improving the operational efficiency and stability of the power grid. This has important practical significance for achieving green and intelligent operation of the power system.

Research on EEG Signal Emotion Recognition Based on BPSO

The discrete binary particle swarm optimization algorithm proposed in this work can address the difficulty of imprecise emotion-related typical features and localization of emotion recognition. Eighteen classes of features in the time domain, frequency domain and time-frequency domain and differential entropy features are used as features for holistic emotion recognition accuracy using linear and nonlinear methods. Then, the next particle position, velocity and fitness are updated according to the recognition rate accuracy, so as to obtain the optimal feature combination by the emotion recognition accuracy, and lastly the subjects were identified using SVM to get the emotion recognition outcome. The initial experiments reveal that the percentage of correctness was 88.95% and 76.12% for BPSO and PSO, respectively. and the highest correct rate of happy among the four categories of emotions is 91.78%, which is improved by up to 12.83% using the BPSO algorithm.

Research on classification method of multimodal magnetic resonance images of Alzheimer's disease based on generalized convolutional neural networks

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.

A Sampling-Based Distributed Exploration Method for UAV Cluster in Unknown Environments

Rapidly completing the exploration and construction of unknown environments is an important task of a UAV cluster. However, the formulation of an online autonomous exploration strategy based on a real-time detection map is still a problem that needs to be discussed and optimized. In this paper, we propose a distributed unknown environment exploration framework for a UAV cluster that comprehensively considers the path and terminal state gain, which is called the Distributed Next-Best-Path and Terminal (DNBPT) method. This method calculates the gain by comprehensively calculating the new exploration grid brought by the exploration path and the guidance of the terminal state to the unexplored area to guide the UAV’s next decision. We propose a suitable multistep selective sampling method and an improved Discrete Binary Particle Swarm Optimization algorithm for path optimization. The simulation results show that the DNBPT can realize rapid exploration under high coverage conditions in multiple scenes.

Conditional Joint Distribution-Based Test Selection for Fault Detection and Isolation.

Data-driven fault detection and isolation (FDI) depends on complete, comprehensive, and accurate fault information. Optimal test selection can substantially improve information achievement for FDI and reduce the detecting cost and the maintenance cost of the engineering systems. Considerable efforts have been worked to model the test selection problem (TSP), but few of them considered the impact of the measurement uncertainty and the fault occurrence. In this article, a conditional joint distribution (CJD)-based test selection method is proposed to construct an accurate TSP model. In addition, we propose a deep copula function which can describe the dependency among the tests. Afterward, an improved discrete binary particle swarm optimization (IBPSO) algorithm is proposed to deal with TSP. Then, application to an electrical circuit is used to illustrate the efficiency of the proposed method over two available methods: 1) joint distribution-based IBPSO and 2) Bernoulli distribution-based IBPSO.

Grid-friendly energy prosumers based on the energy router with load switching functionality

Huge numbers of residential energy prosumers (EPs) will be widely deployed in the next generation power system which is dominated by renewable energies. The intermittent and non-dispatchable natures of the renewable energies will inevitably bring sporadic and unpredictable disturbances to the power system, making “grid friendliness” an essential requirement for the EPs. To tackle this problem, this paper focuses on the hardware implementation of the energy router (ER) and corresponsive coordinated energy management strategy for grid friendly EPs. The coordinated energy management strategy, combined with a fuzzy logic controller (FLC) for energy storage (ES) unit control and an improved discrete binary particle swarm optimization (DBPSO) algorithm for load scheduling, is elaborated for embedded control of the ER by maintaining balance of the accuracy, efficiency and cost considerations. Built as the energy interface between the EP and the power system, the ER is facilitated with plug-and-play source/load/ES connections, intelligent monitor and control interfaces as well as a load switching module, enabling the functionalities of the coordinated energy management strategy to be implemented. Experimental verification shows that, the developed ER enhances the energy management flexibilities for the EP, and the presented FLC + DBPSO algorithm enables coordinated operation of the EP and potential benefits in renewable DG utilization by improving the performances of PV self-use ratio, load rate and energy cost of the EP system by about 20 %, 50 % and 20 %, respectively, while at the same time maintaining the EP system reliability and consumer comfort, as well as meeting the grid friendly requirements.

Data-Driven Optimal Test Selection Design for Fault Detection and Isolation Based on CCVKL Method and PSO

Accurate fault detection and isolation (FDI) relies on the information collection. This can be done by the optimal test selection which can also reduce the life cost of engineering systems. In recent years, some researchers have made lots of achievement on solving the test selection design (TSD) problem. However, few of them concerned a method to deal with the ambiguity problem caused by the multiple fault modes. In this article, a data-driven-based method for test selection is proposed to build an accurate TSD model. Then, we propose a copula function on cross validation-based Kullback–Leibler divergence (CCVKL) method to construct an accurate constraint model. An improved discrete binary particle swarm optimization (IBPSO) algorithm is used to obtain the optimal test design solution. The proposed method also in comparison to three other existing methods are performed in an electrical circuit.

Two-stage optimal allocation of charging stations based on spatiotemporal complementarity and demand response: A framework based on MCS and DBPSO

This paper studies a two-stage model for the optimization of charging scheduling and charging station construction planning based on the spatial-temporal complementarity of charging demand, in order to improve the overall satisfaction of the whole society. In the first stage, starting from the probability of trip starting point and other characteristics, the simulation of load demand is realized based on Monte Carlo simulation, and the charging plan regulation method is created combined with the principle of Dijkstra algorithm. In the second stage, a solution path based on discrete binary particle swarm optimization is proposed. The experimental results of 14 scenarios show that no matter disorderly charging or orderly charging, the annual social comprehensive cost of the scenario with five charging stations is the lowest. Compared with disordered charging, the total construction capacity of charging station is reduced by 51.61%, and the annual social comprehensive cost is reduced by 29.35%. Therefore, this study provides a framework for the optimal configuration of charging stations, which is applicable when considering or not considering demand response, and provides a solution for the future green development planning of urban charging infrastructure.

WSN Node Optimal Deployment Algorithm Based on Adaptive Binary Particle Swarm Optimization

In order to optimize the deployment of wireless sensor network nodes, and avoid network energy consumption increase due to node redundancy and uneven coverage, the multi-objective mathematical optimization problem of area coverage is transformed into a function problem. Aiming at network coverage rate, node dormancy rate and network coverage uniformity, the idea of genetic algorithm mutation is introduced based on the discrete binary particle swarm optimization and the global optimal speed is mutated to avoid the algorithm falling into the local optimal solution. In order to further improve the optimization ability of the algorithm, the adaptive learning factor and inertia weight are introduced to obtain the optimal deployment algorithm of wireless sensor network nodes. The experimental results show that the algorithm can reduce the number of active nodes efficiently, improve coverage uniformity, reduce network energy consumption and prolong network lifetime under the premise that the coverage rate is greater than 90%, and compared with an algorithm called coverage configuration protocol, an algorithm called finding the minimum working sets in wireless sensor networks, and an algorithm called binary particle swarm optimization-g in literature, the number of active nodes in this algorithm is reduced by about 36%, 30% and 23% respectively.

An integrated method for hiding sensitive association rules of the supply chains

Sensitive association rule hiding is an important issue of data sharing for supply chains, which can ensure mutual benefits and avoid information leakages among different enterprises. An integrated method is proposed by using Apriori and the discrete binary particle swarm optimization (BPSO) algorithm, aiming to improve the rule hiding efficiency and effectiveness. The Apriori algorithm is used to extract the association rules from sharing data. The selected sensitive association rules can be hidden using BPSO based on constructing discrete binary space and multi-objective fitness functions. The proposed method is verified through a case study. The results show that the proposed method can effectively hide sensitive information and protect enterprises' business benefits.

Joint Distribution-Based Test Selection for Fault Detection and Isolation Under Multiple Faults Condition

Effective and comprehensive fault information can reduce the maintenance cost of a system. The selection of a proper test is important to obtain accurate information for fault detection and isolation (FDI) once a fault occurs. In real systems, the FDI task is made difficult by the correlations in the physical behaviors of the components and the possible coexistence of multiple faults. In this article, a new type of test selection model based on deep joint distribution is proposed, which takes into account the dependence and ambiguity groups. The optimal test can, then, be selected by an improved discrete binary particle swarm optimization (IBPSO) algorithm. The strengths of the proposed optimal test selection strategy are: 1) it can greatly improve the accuracy of test selection; 2) it considers the influence of multiple faults; 3) the dependence problem of the test outcomes can be addressed; and 4) it is computationally efficient and capable of selecting optimal test points meeting the requirements of real-time FDI. The application to a negative feedback circuit demonstrates the performance of the proposed method.

A Nonuniform Delay-Coordinate Embedding-Based Multiscale Predictor for Blast Furnace Systems

Blast furnace is the main equipment in modern ironmaking industry. To achieve hot metal of high quality, the temperature in the blast furnace rector, often indicated by the silicon content in hot metal, should be controlled within a proper range. This brief captures the multiscale features of the blast furnace system and proposes a multiscale predictor based on nonuniform delay-coordinate embedding for silicon prediction. We use the discrete binary particle swarm optimization method to optimize nonuniform embedding parameters, including embedding dimension and time lags. Then, the predictor is trained with the nonuniform embedding features under the framework of the Taylor expansion model. Some experiments on a real blast furnace are conducted to verify the superiority of the proposed method, and the results show that the nonuniform embedding model obtains better performance with lower embedding dimension and higher accuracy than the uniform embedding model, which can be seen as a great improvement of our previous work.

Research on nondestructive measurement solving algorithm based on grid slice volume

In this paper, an improved discrete binary particle swarm optimization (BPSO) for large scale 0-1 integer programming is proposed. Firstly, a large-scale 0-1 integer programming model based on the multi-directional slice volume of the virtual grid element is constructed, and the optimization objective function is constructed to change the problem of solving the equations into the problem of seeking the optimal solution. Secondly, the 0-1 model intelligent solution algorithm based on the improved BPSO algorithm is designed, and the model solution system based on the grid slice volume measurement is designed. Finally, through the analysis of the experimental results, it shows that the improved discrete particle swarm optimization algorithm has a significant improvement on the convergence and calculation efficiency of the fitness function, which shows that the algorithm has a good optimization performance.

Z-Shaped Transfer Functions for Binary Particle Swarm Optimization Algorithm.

Particle swarm optimization (PSO) algorithm is a swarm intelligent searching algorithm based on population that simulates the social behavior of birds, bees, or fish groups. The discrete binary particle swarm optimization (BPSO) algorithm maps the continuous search space to a binary space through a new transfer function, and the update process is designed to switch the position of the particles between 0 and 1 in the binary search space. Aiming at the existed BPSO algorithms which are easy to fall into the local optimum, a new Z-shaped probability transfer function is proposed to map the continuous search space to a binary space. By adopting nine typical benchmark functions, the proposed Z-probability transfer function and the V-shaped and S-shaped transfer functions are used to carry out the performance simulation experiments. The results show that the proposed Z-shaped probability transfer function improves the convergence speed and optimization accuracy of the BPSO algorithm.

Canopy SIF synergize with total spectral reflectance optimized by the MDBPSO algorithm to monitor wheat stripe rust

<p indent=0mm>In order to extract the characteristic parameters sensitive to wheat stripe rust from total spectral reflectance and improve the operation efficiency and estimation accuracy of the wheat stripe rust remote sensing detection model, this paper improved the traditional discrete binary particle swarm optimization (DBPSO) algorithm from two aspects: inertia weight and particle update method. The modified discrete binary particle swarm optimization (MDBPSO) algorithm was used to select the characteristic parameters for the severity of wheat stripe rust from the total spectral reflectance. The selected characteristic variables were combined with canopy solar-induced chlorophyll fluorescence (SIF) data as independent variables to construct wheat stripe rust estimation model. Random forest (RF) algorithm and back propagation (BP) neural network algorithm were used as model construction method to compare and analyze the accuracy of the feature parameter construction model extracted by the correlation coefficient (CC) analysis method and the DBPSO algorithm. The MDBPSO algorithm had faster convergence speed and higher optimization accuracy than the DBPSO algorithm. The number of iterations before and after the improvement was reduced from 395 to 156. The optimal fitness function (OFV) value decreased from 0.145 to 0.127. When the MDBPSO algorithm was used to select feature variables, the accuracy of the models constructed by the two methods of RF and BP neural networks was higher than that by CC analysis and DBPSO. The validation set determination coefficient (<italic>R</italic>²_V) between the predicted disease index (DI) value and the measured DI value of the RF algorithm was 9% and 3% higher than that of the CC analysis method and the DBPSO algorithm, the validation set root mean square error (RMSE_V) was reduced by 28% and 11%, respectively. The <italic>R</italic>²_V between the predicted disease index (DI) value and the measured DI value of the BP neural network algorithm was 13% and 6% higher than that of the CC analysis method and DBPSO algorithm, respectively, and the RMSE_V was reduced by 21% and 10% respectively. The MDBPSO algorithm can improve the remote sensing detection accuracy of wheat stripe rust. Among the three feature selection algorithms of MDBPSO, DBPSO, and CC analysis, the accuracy of the model constructed by the RF algorithm was higher than that by the BP neural network algorithm. The <italic>R</italic>²_V between the predicted DI value and the measured DI value of the RF model was at least 7% higher than that of BP neural network algorithm, with an average increase of 9%; RMSE_V had reduced by at least 15%, with an average reduction of 20%. The MDBPSO-RF model for wheat stripe rust remote sensing detection constructed by RF method using the characteristic parameters selected by the MDBPSO algorithm as independent variables is an appropriate model for wheat stripe rust remote sensing detection. The research results provide new ideas for further realizing large-area high-precision remote sensing monitoring of crop health.

Collaborative Optimal Operation of AC/DC Hybrid Microgrid with High Proportion of Renewable Energy

Complexity of collaborative optimal dispatching and uncertainty of system are enhanced with the increase ratio of renewable energy in AC/DC hybrid microgrid. The prediction error of the output of renewable energy as a fuzzy variable is treated in this paper. Then a fuzzy chance constrained collaborative optimal model of AC/DC hybrid microgrid considering economy and flexibility is established. In view of the problems that both uncertain programming and mixed integer programming are contained in the model, where conventional algorithms have difficulty in solving it, the thought of fuzzy simulation into the neural network algorithm is introduced in this paper and the uncertainty of the source side by training the neuron to simulate the uncertainty is solved. Finally, the discrete binary particle swarm optimization to solve the integer programming is introduced. Based on the field data of a certain AC/DC hybrid microgrid demonstration project in Zhejiang Province, the effectiveness of the model and algorithm are verified.

The optimized allocation of emergency resources for power system restoration

In recent years, there have been frequent blackout accidents in foreign countries. For power system, the configuration of emergency resources affects the process of the power system restoration. It is the key to ensure the smooth restoration of power system that the emergency generating vehicle and the operations staff arrive at the substation in time after the blackout. In this paper, the optimal allocation scheme of the emergency generating vehicle considering the comprehensive importance of load nodes and traffic network constraints is proposed. The comprehensive importance degree of nodes is calculated by considering the spectral importance degree, the importance degree of load amount and the comprehensive importance degree of load of nodes. The blackout economic loss of node is evaluated by node’s comprehensive importance degree. In addition, the cost of configuration and maintenance of the emergency generating vehicle and the transmission cost under the constraint of traffic network are considered to establish the optimal configuration model of the emergency generating vehicle. Finally, the Discrete Binary Particle Swarm Optimization (DBPSO) is used to obtain the optimal configuration location of emergency generating vehicle and the optimal route for recovery. The validity and feasibility of the proposed method are verified by the results of IEEE39.

An Improved Selective Ensemble Learning Method for Highway Traffic Flow State Identification

Reliable and accurate real-time traffic flow state identification is crucial for an intelligent transportation system (ITS). This identification is a prerequisite for alleviating traffic congestion and improving highway operation efficiency. In this paper, we propose an improved traffic flow state identification model that is based on selective ensemble learning (SEL). First, we adopted the fuzzy C-means (FCM) clustering method to divide the traffic flow data into three main kinds of traffic flow states and obtained the parameters that correspond to each kind of traffic flow state. Second, we applied the random subspace (RS) algorithm as the ensemble method and support vector machine (SVM) model as base learners to construct the RS-SVM ensemble model for traffic flow identification. Significantly, the discrete binary particle swarm optimization (BPSO) algorithm with global optimization search ability was employed to select the classifiers obtained by the random subspace training in the ensemble system. We experimentally validated the effectiveness of the proposed BPSO–RS-SVM-SEL approach. The research results reveal that compared with other classical traffic flow state identification methods, the proposed model has a higher maximum accuracy of 98.68%. It can be seen that our model improves the classification accuracy of traffic flow state identification and the difference in the ensemble system to a certain extent.

Solving Optimization of a Mine Gas Sensor Layout Based on a Hybrid GA-DBPSO Algorithm

To expand the monitoring range of the coal mine gas monitoring subsystem and achieve the timely early-warning of the local gas transfinite accident, the covering model of sensor was established. It can realize the function of using the least number of gas sensors to monitor the change of gas concentration in the whole mine. The objective function and constraint conditions of the established model were determined. A hybrid GA-DBPSO algorithm combining the genetic algorithm with the discrete binary particle swarm optimization algorithm was proposed to solve the gas sensor location set covering model. This research result was applied to investigate the gas sensor layout of Baoxin Coal Mine in China, and gas sensor layout schemes were obtained under the condition of different gas sensor shortest alarm time. The relationship between the shortest alarm time and the number of additional gas sensor was given, which can provide guidance and reference for the enterprises managers to make decisions on layout scheme of gas sensors.

Area-to-point heat conduction enhancement using binary particle swarm optimization

The area-to-point heat conduction problem is solved using a discrete binary particle swarm optimization (BPSO) algorithm. The distribution of conductive materials is optimized to form a tree-shaped conducting path, which can significantly reduce the maximum temperature of the heat-generating domain. The effects of the conductivity ratio and the quantity of conductive materials on the geometric structure of the conducting path are investigated. As conductivity ratio and filling ratio increase, the maximum temperature decreases. In addition to the conductivity ratio and filling ratio, the heat sink location is found to have an impact on cooling capacity. That is, the maximum temperature decreases with decrease in distance between the hot spot and heat sink. In addition, the structural features of the conducting path produced according to different objectives are characterized.