A binary particle swarm optimization approach for power system security enhancement

Improvement of power system security manages the errand of making healing move against conceivable system overloads in the framework following the events of contingencies. Generation re-dispatching is answer for the evacuation of line overloads. The issue is the minimization of different goals viz. minimization of fuel cost, minimization of line loadings and minimization of overall severity index. Binary particle swarm optimization (BPSO) method was utilized to take care of optimal power flow issue with different targets under system contingencies. The inspiration to introduce BPSO gets from the way that, in rivalry with other meta-heuristics, BPSO has demonstrated to be a champ by and large, putting a technique as a genuine alternative when one needs to take care of a complex optimization problem. The positioning is assessed utilizing fuzzy logic. Simulation Results on IEEE-14 and IEEE-30 bus systems are presented with different objectives.

Integration of Electric Vehicles and Energy Storage System in Home Energy Management System with Home to Grid Capability

In this paper, we proposed a home energy management system (HEMS) that includes photovoltaic (PV), electric vehicle (EV), and energy storage systems (ESS). The proposed HEMS fully utilizes the PV power in operating domestic appliances and charging EV/ESS. The surplus power is fed back to the grid to achieve economic benefits. A novel charging and discharging scheme of EV/ESS is presented to minimize the energy cost, control the maximum load demand, increase the battery life, and satisfy the user’s-traveling needs. The EV/ESS charges during low pricing periods and discharges in high pricing periods. In the proposed method, a multi-objective problem is formulated, which simultaneously minimizes the energy cost, peak to average ratio (PAR), and customer dissatisfaction. The multi-objective optimization is solved using binary particle swarm optimization (BPSO). The results clearly show that it minimizes the operating cost from 402.89 cents to 191.46 cents, so that a reduction of 52.47% is obtained. Moreover, it reduces the PAR and discomfort index by 15.11% and 16.67%, respectively, in a 24 h time span. Furthermore, the home has home to grid (H2G) capability as it sells the surplus energy, and the total cost is further reduced by 29.41%.

Automatic Classification of Covid-19 Chest X-Ray Images Using Local Binary Pattern and Binary Particle Swarm Optimization for Feature Selection

Novel Coronavirus disease 2019 (COVID-19) is a type of pandemic viruses that cause respiratory tract infection in humans. The clinical imaging of Chest X-Ray (CXR) by Computer Aided Diagnosis (CAD) plays an important role to identify the patients who infected by COVID-19. The objective of this paper presents a Computer Aided Diagnosis (CAD) method for automatically classify 110 frontal CXR images of contagious people according to Normal and COVID-19 infection. The proposed method contains of four phases: image enhancement, feature extraction, feature selection and classification. Gaussian filter is performed to de-noise the images and Adaptive Histogram Equalization (AHE) for image enhancement in pre-processing step for better decision-making process. Local Binary Pattern (LBP) features set are extracted from the dataset. Binary Particle Swarm Optimization (BPSO) is considered to select the clinically relevant features and developing the robust model. The successive features are fed to Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. The experimental results show that the system robustness in classification COVID-19 from Normal images with average accuracy 94.6%, sensitivity 96.2% and specificity 93%.

Increased Resilience Using Close Loop Renewable Microgrids in the Surabaya Distribution System as a Self-Healing Application

Distribution system reconfiguration has two main objectives, namely as optimization of network operations and as system recovery in case of disturbances. It is necessary to consider the reconfiguration process and the process of using Distributed Generation (DG) or microgrid as an additional supply to reduce the possibility of failure, loss of power, or a voltage drop. Therefore the first step in research This results in the candidate bus 14 and bus 52 on the Mulyosari feeder which must be reconfigured by cutting off the flow at L13 and L50 because the losses on both buses are the worst with a value of 0.01370MW and 0.00900MW using the calculation algorithm of Binary Particle Swarm Optimization (BPSO) to predict the location of possible failures and the placement DG, and selected on bus 29 and bus 45 which were injected DG with a PV capacity of 15 kW each, after the self-healing was applied to the system, power flow analysis was carried out, and get good results g is very satisfactory with the total losses in the system decreased from 0.363MW to 0.116MW from this study we can conclude that self-healing can only be done if the distribution system is a complex radial.

A PROPOSED RECOGNITION SYSTEM FOR ALZHEIMER’S DISEASE BASED ON DEEP LEARNING AND OPTIMIZATION ALGORITHMS

Alzheimer's disease (AD) is an advanced and incurable neurodegenerative disease that causes progressive impairment of memory and cognitive functions due to the deterioration of brain cells. Early diagnosis is substantial to avoid permanent memory loss and develop treatments that will be subtracted in the future. Deep learning (DL) is a vital technique for medical imaging systems for AD diagnostics. The problem is multi-class classification seeking high accuracy. DL models have shown strong performance accuracy for multi-class prediction. In this paper, a proposed DL architecture is created to classify magnetic resonance imaging (MRI) to predict different stages of AD-based pre-trained Convolutional Neural Network (CNN) models and optimization algorithms. The proposed model architecture attempts to find the optimal subset of features to improve classification accuracy and reduce classification time. The pre-trained DL models, ResNet-101 and DenseNet-201, are utilized to extract features based on the last layer, and the Rival Genetic algorithm (RGA) and Pbest-Guide Binary Particle Swarm Optimization (PBPSO) are applied to select the optimal features. Then, the DL features and selected features are passed separately through created classifier for classification. The results are compared and analyzed by accuracy, performance metrics, and execution time. Experimental results showed that the most efficient accuracies were obtained by PBPSO selected features which reached 87.3% and 94.8% accuracy with less time of 46.7 sec, 32.7 sec for features based ResNet-101 and DenseNet-201, receptively.