SPSO Based Optimal Integration of DGs in Local Distribution Systems under Extreme Load Growth for Smart Cities

Rizwan, Mian; Waseem, Muhammad; Liaqat, Rehan; Sajjad, Intisar Ali; Dampage, Udaya; Salmen, Saleh H.; Obaid, Sami Al; Mohamed, Mohamed A.; Annuk, Andres

doi:10.3390/electronics10202542

Cited by 29 publications

(17 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the outcomes, it can be concluded that odds and GWO have similar results. PSO outperformed the odds and GWO [ 29 , 30 ]. Table 3 illustrates the summary of the response times of each method.…”

Section: Simulation Results and Explanationmentioning

confidence: 99%

An Innovative Cloud-Fog-Based Smart Grid Scheme for Efficient Resource Utilization

Alsokhiry

Annuk

Mohamed

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Smart grids (SGs) enhance the effectiveness, reliability, resilience, and energy-efficient operation of electrical networks. Nonetheless, SGs suffer from big data transactions which limit their capabilities and can cause delays in the optimal operation and management tasks. Therefore, it is clear that a fast and reliable architecture is needed to make big data management in SGs more efficient. This paper assesses the optimal operation of the SGs using cloud computing (CC), fog computing, and resource allocation to enhance the management problem. Technically, big data management makes SG more efficient if cloud and fog computing (CFC) are integrated. The integration of fog computing (FC) with CC minimizes cloud burden and maximizes resource allocation. There are three key features for the proposed fog layer: awareness of position, short latency, and mobility. Moreover, a CFC-driven framework is proposed to manage data among different agents. In order to make the system more efficient, FC allocates virtual machines (VMs) according to load-balancing techniques. In addition, the present study proposes a hybrid gray wolf differential evolution optimization algorithm (HGWDE) that brings gray wolf optimization (GWO) and improved differential evolution (IDE) together. Simulation results conducted in MATLAB verify the efficiency of the suggested algorithm according to the high data transaction and computational time. According to the results, the response time of HGWDE is 54 ms, 82.1 ms, and 81.6 ms faster than particle swarm optimization (PSO), differential evolution (DE), and GWO. HGWDE’s processing time is 53 ms, 81.2 ms, and 80.6 ms faster than PSO, DE, and GWO. Although GWO is a bit more efficient than HGWDE, the difference is not very significant.

show abstract

Section: Simulation Results and Explanationmentioning

confidence: 99%

An Innovative Cloud-Fog-Based Smart Grid Scheme for Efficient Resource Utilization

Alsokhiry

Annuk

Mohamed

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…PSO was successfully used for numerous parameter optimization problems in the last few decades, with recent achievements ranging from engineering applications, such as distributed generator integration of smart cities [36] to federated learning aggregation [37] and large-scale hyperparameter optimization of deep learning networks [38].…”

Section: Particle Swarm Optimization Of Derivative Ordermentioning

confidence: 99%

Exploring the Effects of Caputo Fractional Derivative in Spiking Neural Network Training

Gyongyossy

Eros²,

Botzheim³

2022

Electronics

View full text Add to dashboard Cite

Fractional calculus is an emerging topic in artificial neural network training, especially when using gradient-based methods. This paper brings the idea of fractional derivatives to spiking neural network training using Caputo derivative-based gradient calculation. We focus on conducting an extensive investigation of performance improvements via a case study of small-scale networks using derivative orders in the unit interval. With particle swarm optimization we provide an example of handling the derivative order as an optimizable hyperparameter to find viable values for it. Using multiple benchmark datasets we empirically show that there is no single generally optimal derivative order, rather this value is data-dependent. However, statistics show that a range of derivative orders can be determined where the Caputo derivative outperforms first-order gradient descent with high confidence. Improvements in convergence speed and training time are also examined and explained by the reformulation of the Caputo derivative-based training as an adaptive weight normalization technique.

show abstract

“…Ref. [26] presented a selective particle swarm optimization (SPSO) algorithm to solve an optimization model for optimal placement and sizing of distributed generators to reduce the distribution power losses, keeping technical constraints intact.…”

Section: Introductionmentioning

confidence: 99%

CVR Study and Active Power Loss Estimation Based on Analytical and ANN Method

Yadav

Liao

Jewell³

et al. 2022

Energies

View full text Add to dashboard Cite

Conservation through voltage reduction (CVR) aims to reduce the peak load and energy savings in electric power systems and is being deployed at various utilities. The effectiveness of the CVR program depends on the load characteristics, i.e., the sensitivity of the load to voltage variation, and voltage regulation device settings. In the current literature, there is a lack of discussion on the CVR factor calculation using different measurements, and there is a lack of method for active power loss estimation using substation measurements. This paper provides insights into CVR factor calculation based on the measurements captured at the substation and those at the load location. This paper also proposes a new method based on curve fitting and artificial neural network to estimate the active power loss using input active power, input reactive power and input voltage at the substation. The CVR comparison study conducted in this paper helps in understanding the factors affecting CVR factor and may provide guidance in CVR implementation and impact assessment. The proposed loss estimation method sheds light on the impacts of CVR in terms of load and loss reduction. The results based on simulation studies using the IEEE 13-bus and 34-bus systems are reported in this paper, noting that the proposed methods are applicable to larger systems, as long as the required measurements at the substation are available. Future research includes testing and refining the methods using large IEEE and utility distribution systems and considering the stochastic nature of the CVR factor with changing load and voltage regulator control schemes.

show abstract

SPSO Based Optimal Integration of DGs in Local Distribution Systems under Extreme Load Growth for Smart Cities

Cited by 29 publications

References 49 publications

An Innovative Cloud-Fog-Based Smart Grid Scheme for Efficient Resource Utilization

An Innovative Cloud-Fog-Based Smart Grid Scheme for Efficient Resource Utilization

Exploring the Effects of Caputo Fractional Derivative in Spiking Neural Network Training

CVR Study and Active Power Loss Estimation Based on Analytical and ANN Method

Contact Info

Product

Resources

About