Optimal Placement Strategy of Distributed Generators based on Radial Basis Function Neural Network in Distribution Networks

Gupta, Swati; Saxena, Akash; Soni, Bhanu Pratap

doi:10.1016/j.procs.2015.07.478

Cited by 23 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are many types of ANNs, which are recognized as quite effective in solving various applied problems . Among them, neural networks based on radial basis functions have better performance compared with other neural networks.…”

Section: Discussionmentioning

confidence: 99%

“…There are many types of ANNs, which are recognized as quite effective in solving various applied problems. [22][23][24] Among them, neural networks based on radial basis functions have better performance compared with other neural networks. Because in most cases the volume of data for data mining are very large, it requires a mechanism of random choice of data for training the network.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Some methods of training radial basis neural networks in solving the Navier‐Stokes equations

Sinchev¹,

Sibanbayeva

Mukhanova

et al. 2017

Numerical Methods in Fluids

View full text Add to dashboard Cite

Summary The purpose of this research is to analyze the application of neural networks and specific features of training radial basis functions for solving 2‐dimensional Navier‐Stokes equations. The authors developed an algorithm for solving hydrodynamic equations with representation of their solution by the method of weighted residuals upon the general neural network approximation throughout the entire computational domain. The article deals with testing of the developed algorithm through solving the 2‐dimensional Navier‐Stokes equations. Artificial neural networks are widely used for solving problems of mathematical physics; however, their use for modeling of hydrodynamic problems is very limited. At the same time, the problem of hydrodynamic modeling can be solved through neural network modeling, and our study demonstrates an example of its solution. The choice of neural networks based on radial basis functions is due to the ease of implementation and organization of the training process, the accuracy of the approximations, and smoothness of solutions. Radial basis neural networks in the solution of differential equations in partial derivatives allow obtaining a sufficiently accurate solution with a relatively small size of the neural network model. The authors propose to consider the neural network as an approximation of the unknown solution of the equation. The Gaussian distribution is used as the activation function.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Some methods of training radial basis neural networks in solving the Navier‐Stokes equations

Sinchev¹,

Sibanbayeva

Mukhanova

et al. 2017

Numerical Methods in Fluids

View full text Add to dashboard Cite

show abstract

“…Bansal, Jagdish Chand et al [33] developed Spider Monkey Optimization which was based on the social behavior of spider monkeys and Simon, Dan [34] developed Biogeography Based Optimization which was based on Biogeography is the study of the geographical distribution of biological organisms. Saxena Akash et al [35] used a radial basis function neural network based optimization technique for optimal placement and sizing of DG, also performed a comprehensive study of chaos embedded bridging mechanisms and crossover operators for grasshopper optimization in [36], ambient air quality classification using Grey Wolf Optimization (GWO) in [37] and used Gravitational Search Algorithm (GSA) for optimal allocation of SVC in [38]. These researches are evidences of applications solved through bio inspired optimization techniques.…”

Section: Whale Optimization Algorithmmentioning

confidence: 99%

A demand side management control strategy using Whale optimization algorithm

Sharma

2019

SN Appl. Sci.

Self Cite

View full text Add to dashboard Cite

In recent years, demand side management programs are in the spotlight due to the evolution of the smart grid and consumer-centric policies. Demand side management program contains many objectives one of the prime objective is to manage energy demand by certain change in consumer demand. This can be achieved by various methods such as financial discount and change in behavior through imparting education to support the stressed conditions of the grid. This paper demonstrates demand side management strategies based upon strategic conservation, peak clipping and load shifting techniques for future smart grids. The grid contains large number of controllable devices. The day before strategic conservation, peak clipping and load shifting techniques discussed in this paper are mathematically derived for minimization problem. A heuristic-based Whale optimization algorithm (WOA) was developed for solving this problem of minimization. Simulations are conducted on a test smart grid that contains a variation in loads in two service areas, one with residential consumers, and another with commercial consumers. WOA proves its efficacy by comparing the results with spider monkey optimization and biogeography based optimization. The simulation results show that proposed demand side management strategies achieve substantial savings, while reducing the peak load demand of the smart grid.

show abstract

“…In this paper, DG is used for relieving congestion in the transmission line, where the congested line has been found by Power Performance Index (PPI) and the finest location of DG has been identified by the LRS based method. The congestion in the system can be found by the PPI and it is denoted by [5,9,10]: (8) If the PPI for a line is above 1, then the line is supposed to be overloaded. Line Relief sensitivity can be defined as the inverse of Transfer Distribution Factors (TDFs).…”

Section: Optimal Placement Of Distributed Generation (Dg) Unitmentioning

confidence: 99%

“…Huiling Li et al have [8] concluded an algorithm based on the combination of power from the wind and Pumped Hydro to decrease the wind power curtailment and the variation caused in the wind power on the power grid. Swati Gupta et al [9] have proposed an optimization technique based on Radial Basis Function Neural Network (RBFNN) to penetrate the DG at IEEE 69 bus distribution system to curtail the power loss and to improve the voltage profile of the same system. This work describes the congestion management method in restructured power system with Distributed Generation Unit.…”

Section: Introductionmentioning

confidence: 99%

Congestion Management in a Restructured Power System Using Solar Photovoltaics

Subramaniyan¹,

Gomathi²

2018

IJET

View full text Add to dashboard Cite

The modern power grid is one of the most complex engineering machines in existence. There is a continuous transformation in the grid conditions that necessitate variations in the electricity production. Energy is a remarkable donor in environmental change, representing around 60 percent of the aggregate worldwide greenhouse gas outflow. Lessening the carbon force of energy, the share of non-conventional energy sources in the worldwide vitality blend is relied upon to expand supportability. So renewable energy is one of the most capable results for taking care of expanding energy demand. This paper proposed a method to lessen the congestion in the deregulated environment. The congestion in the transmission lines is identified by optimal power flow (Newton Raphson) method. Congestion in the transmission lines is lessened by connecting a dispersed generating unit called as Solar Photovoltaic at PQ (load) bus. A way to decide the ideal position of a Dispersed Generating unit has been suggested based on the Line Relief Sensitivity (LRS) based attitude. The effectiveness of methodology has been validated using standard IEEE 30 bus system.

show abstract

Optimal Placement Strategy of Distributed Generators based on Radial Basis Function Neural Network in Distribution Networks

Cited by 23 publications

References 21 publications

Some methods of training radial basis neural networks in solving the Navier‐Stokes equations

Some methods of training radial basis neural networks in solving the Navier‐Stokes equations

A demand side management control strategy using Whale optimization algorithm

Congestion Management in a Restructured Power System Using Solar Photovoltaics

Contact Info

Product

Resources

About