Implementation of crow search algorithm for optimal allocation of DG and DSTATCOM in practical distribution system

Sannigrahi, Surajit; Acharjee, Parimal

doi:10.1109/picc.2018.8384745

Cited by 13 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The researchers [20] developed CS algorithm on the assumptions of nature of crow with respect to hiding and grabbing the food. By seeking the crow's nature, the features of CSA is illustrated as follows (a) It is in the form of a flock, (b) it saves food hiding places, (c) for the purpose of stealing, they follow each other along with (d) by probability, and they guard their caches against being pilfered.…”

Section: ) Crow Search (Cs) Algorithmmentioning

confidence: 99%

Optimal Feature Selection-Based Medical Image Classification Using Deep Learning Model in Internet of Medical Things

Shobana²,

et al. 2020

View full text Add to dashboard Cite

Internet of Medical Things (IoMT) is the collection of medical devices and related applications which link the healthcare IT systems through online computer networks. In the field of diagnosis, medical image classification plays an important role in prediction and early diagnosis of critical diseases. Medical images form an indispensable part of a patient's health record which can be applied to control, handle and treat the diseases. But, classification of images is a challenging task in computer-based diagnostics. In this research article, we have introduced a improved classifier i.e., Optimal Deep Learning (DL) for classification of lung cancer, brain image, and Alzheimer's disease. The researchers proposed the Optimal Feature Selection based Medical Image Classification using DL model by incorporating preprocessing, feature selection and classification. The main goal of the paper is to derive an optimal feature selection model for effective medical image classification. To enhance the performance of the DL classifier, Oppositionbased Crow Search (OCS) algorithm is proposed. The OCS algorithm picks the optimal features from pre-processed images, here Multi-texture, grey level features were selected for the analysis. Finally, the optimal features improved the classification result and increased the accuracy, specificity and sensitivity in the diagnosis of medical images. The proposed results were implemented in MATLAB and compared with existing feature selection models and other classification approaches. The proposed model achieved the maximum performance in terms of accuracy, sensitivity and specificity being 95.22%, 86.45 % and 100% for the applied set of images.

show abstract

Section: ) Crow Search (Cs) Algorithmmentioning

confidence: 99%

Optimal Feature Selection-Based Medical Image Classification Using Deep Learning Model in Internet of Medical Things

Shobana²,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…When AP increases, the algorithm tends to search in global optima therefore, the diversification increases. In [19][20][21][22][23], the original CSA is applied to get the optimal size and site of DGs where the variable represents the position of the crows in the space is assumed randomly based on lower (L B ) and upper (U B ) bounds of the variable. A modified CSA is proposed in this article, where the CSA variable is calculated depending on Gaussian and Cauchy density functions [32], which are shown in Figure 2.…”

Section: Modified Crow Search Algorithm (Csa) Optimizermentioning

confidence: 99%

“…In the recent decade, the new Crow Search Algorithm (CSA) is applied in several research studies to get the optimal size and site of DGs [19][20][21][22][23]. The simultaneous optimal placement of DGs and capacitor units in RDS is studied in [20].…”

Section: Introductionmentioning

confidence: 99%

“…Reducing the power loss and improving the voltage profile of the RDS using multiple DGs were the goals of [21,23], while maximizing the overall saving and reducing the network losses were the main objectives of [22]. Obtaining the optimal size and site of DG and DSTATCOM in practical distribution system, to reduce the distribution system loss, is fully introduced in [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing active radial distribution networks by optimal sizing and placement of DGs using modified crow search algorithm

Abdelbadea

Boghdady

Ibrahim

2019

IJEECS

View full text Add to dashboard Cite

<p>Incorporating many Distributed Generators (DGs) technologies in power system networks has grown rapidly in recent years. Distributed generation (DG) plays a key role in reducing power loss and enhancing the voltage profile in radial distribution networks. However, inappropriate DGs site or size may cut network efficiency; moreover, injecting harmonics is one of the integration concerns of inverter-based DGs. Two-procedure based approach is introduced in this paper. The first procedure solves the DGs siting and sizing problem, as a multi-objective one by improving the voltage profile of the whole distribution network and also reducing its power loss. A weighted sum method is presented to create the Pareto optimal front in this procedure and get the compromised solution by applying a novel metaheuristic optimizer, named Crow Search Algorithm (CSA). A modification on CSA is also proposed and applied to improve its performance. The achieved solution for inverter-based DGs placement and size is checked in the second procedure to make sure the accepted voltage THD at all buses by implementing detailed simulation for the tested system using Matlab/Simulink. The proposed approach has been tested on IEEE 33-bus radial distribution system with photovoltaic DGs. To confirm the superiority of the modified CSA algorithm in terms of quality of solution, its achieved results are compared with the results offered by the original CSA algorithm and published results of some other nature-inspired algorithms.</p>

show abstract

“…The drawbacks encountered by analytical approaches in DSTATCOM allocation have been addressed to a large extent by several meta-heuristic techniques such as crow search algorithm [13], hybridized PSO and general algebraic modeling system [14], differential evolution algorithm [15,16], imperialistic competitive algorithm [17], cuckoo search algorithm [18], hybridized fuzz-ACO [19], particle swarm optimization algorithm [20], immune algorithm [21], harmony search algorithm [5], bacterial foraging algorithm [4], quadratic adaptive bacterial foraging algorithm [6], firefly algorithm [22], grasshopper optimization algorithm [2] and weighted artificial fish swarm algorithm [23].…”

Section: Introductionmentioning

confidence: 99%

Application of Bacterial Foraging Algorithm in The Allocation of DSTATCOM in 50-bus Canteen Feeder

2019

View full text Add to dashboard Cite

Voltage instability has been identified as the most critical factor responsible for poor power quality in electric power systems. The high losses experienced at the distribution level of these systems has become a major concern to power system operators, with about 10-13% of the total generation being dissipated as heat. Maintaining the system voltage within an acceptable limit will go a long way in reducing these losses and enhancing the overall system operational capability. The objective of this paper is to improve the voltage magnitude and reduce overall power losses in an existing 50-bus radial distribution feeder via the allocation of Distribution Static Compensator (DSTATCOM) using an established bacterial foraging algorithm (BFA) based model. The application of the swarm-based meta-heuristic model is extended to a three-quarter (75%) loading condition of the standard IEEE 33-bus test network and then, employed on the 50-bus Canteen feeder for both normal (100%) and three-quarter (75%) loading conditions. Comprehensive analysis was performed for both networks and the results were compared with their respective base-case scenarios. The final results of the evaluation obtained through simulation showed appreciable reduction in power losses and improvement in overall voltage profile with the allocation of DSTATCOM in both networks using the BFA based model. Voltage improvement in the region of 20.04% and active power loss reduction of 24.86% were recorded for three-quarter loading of the IEEE test network. For the 50-bus Canteen feeder, an overall voltage profile improvement of 6.13% and active power loss reduction of 22.84% were achieved for normal loading condition, whereas 2.99% and 19.71% improvement in total voltage profile and active power loss respectively were attained under three-quarter loading condition.

show abstract

Implementation of crow search algorithm for optimal allocation of DG and DSTATCOM in practical distribution system

Cited by 13 publications

References 14 publications

Optimal Feature Selection-Based Medical Image Classification Using Deep Learning Model in Internet of Medical Things

Optimal Feature Selection-Based Medical Image Classification Using Deep Learning Model in Internet of Medical Things

Enhancing active radial distribution networks by optimal sizing and placement of DGs using modified crow search algorithm

Application of Bacterial Foraging Algorithm in The Allocation of DSTATCOM in 50-bus Canteen Feeder

Contact Info

Product

Resources

About