Back propagation algorithm based controller for autonomous wind-DG microgrid

Pathak, Geeta; Singh, Bhim; Panigrahi, Bijaya Ketan

doi:10.1109/34084poweri.2014.7117766

Cited by 4 publications

(4 citation statements)

References 10 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hybrid DG model with the combined effect of wind and DE under unbalanced nonlinear loading was studied in papers [29,30]. The papers [31,32] have studied the modeling of hybrid PVES and DE, where the impact of uncertain PVES power generation was considered.…”

Section: Hybrid Dgs For Economical Operationmentioning

confidence: 99%

Performance Enhancement for Microgrids Under the Demand Uncertainties with the Presence of Multiple DGs Through Stochastic Ranking Algorithm

Srinivasan

Wang

Kim

2020

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

The integration of Distributed Generators (DGs) in the reconfigurable microgrid is evolved to enhance the power delivery performance. The DGs are categorized as controllable and uncontrollable based on their power generation control behaviors. In addition to the control behavior, under the uncertain conditions of the microgrid, the performance of DGs is limited due to their respective drawbacks. Therefore, the identification of the most suitable DG under uncertain situation becomes more critical. This paper investigates the performance behavior of the hybrid DG, which uses the benefits of two kinds of DGs and overcomes their limitations. This work addresses five objective functions namely minimization of power loss, total generation cost, total emission cost and voltage deviation, and the maximization of the percentage DG penetration. The performance investigation of DGs is carried out for the system under five different test cases, including the uncertainty in power supply and demand. The modeling of the demand variation is done with the support of Probability Density Function (PDF). The many objective multi-indicator Stochastic Ranking Algorithm (SRA) is used for the optimization purposes. The simulations are performed on IEEE 33-bus Radial Distribution System (RDS) to assess the capability of the proposed investigation. Furthermore, the proposed strategy is applied under 24-h timely varying load pattern of IEEE 33-bus RDS to verify its applicability in uncertain load conditions. Moreover, the performance enhancement realization with the presence of hybrid DG is observed from the obtained simulation results.

show abstract

Section: Hybrid Dgs For Economical Operationmentioning

confidence: 99%

Performance Enhancement for Microgrids Under the Demand Uncertainties with the Presence of Multiple DGs Through Stochastic Ranking Algorithm

Srinivasan

Wang

Kim

2020

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

show abstract

“…Supposing L is the output layer, a L will represent the final actual output vector. The Back Propagation (BP) algorithm [28], which is a supervised learning method, is commonly used to iteratively update parameters of W l and b l . It first applies the actual output and the targeted values to construct a cost function, and then applies the Gradient Descent (GD) along the negative gradient direction of cost function to adjust and parameters.…”

Section: Deep Convolutional Neural Networkmentioning

confidence: 99%

A New Algorithm for SAR Image Target Recognition Based on an Improved Deep Convolutional Neural Network

et al. 2018

View full text Add to dashboard Cite

Background: To effectively make use of deep learning technology automatic feature extraction ability, and enhance the ability of depth learning method to learn and recognize features, this paper proposed a deep learning algorithm combining Deep Convolutional Neural Network (DCNN) trained with an improved cost function and Support Vector Machine (SVM). Methods: The class separation information, which explicitly facilitates intra-class compactness and interclass separability in the process of learning features, is added to an improved cost function as a regularization term to enhance the feature extraction ability of DCNN. Then the improved DCNN is applied to learn the features of SAR images. Finally, SVM is utilized to map the features into output labels. Results: Experiments are performed on SAR image data in Moving and Stationary Target Acquisition and Recognition (MSTAR) database. The experiment results prove the effectiveness of our method, achieving an average accuracy of 99% on ten types of targets, some variants, and some articulated targets. Conclusion: It proves that our method is effective and CNN enjoys a certain potential to be applied in SAR image target recognition. Keywords synthetic aperture radar (SAR) images • automatic target recognition (ATR) • deep convolutional neural Network (DCNN) • support vector machine (SVM) • class separation information

show abstract

“…In addition to reactive power management, harmonic management using droop control is presented in [26]. Single-point reactive power control method described in [27]; P-Q control using Finite Hybrid Automata (FHA) counting droop control, designed for switch-mode microgrids is discussed in [28]. A Modified One-Cycle-Control and an Autonomous Control of Current-and Voltage Controlled DG Interface Inverters is sketched in [29].…”

Section: Reactive Power Management Techniques In Renewable Energymentioning

confidence: 99%

A Probe into Reactive Power Management in Renewable Energy System using Facts Devices

Baby*¹,

Jayakumar²

2019

IJITEE

View full text Add to dashboard Cite

In the modern era, most of the utility grid is connected with Renewable Energy resources (RERs). In addition to this, many power electronic converters and reactive power compensating devices are also incorporated into the existing grid. This makes the system complicated. Penetration of renewable energy resources affect many power system parameters like grid stability, quality of power, reactive power balance and Sufficient energy utilization. However, the Distributed Generation (DG) towards the power electronic interface creates some critical power quality events such as reactive power management, harmonics and voltage profile which makes the distributed system become a polluted one. This paper depicts the review of modelling and incorporation of various reactive power compensating devices like TCSC, SVC and STATCOM into RES. Power generation model of solar, wind and fuel farm is discussed in this paper. Reactive power compensating devices and its location and sizing are important for the stable and secure operation of the electric grid. Consequently, power quality issues, real-time interconnection issues and policies related to reactive power management are in this paper.

show abstract

Back propagation algorithm based controller for autonomous wind-DG microgrid

Cited by 4 publications

References 10 publications

Performance Enhancement for Microgrids Under the Demand Uncertainties with the Presence of Multiple DGs Through Stochastic Ranking Algorithm

Performance Enhancement for Microgrids Under the Demand Uncertainties with the Presence of Multiple DGs Through Stochastic Ranking Algorithm

A New Algorithm for SAR Image Target Recognition Based on an Improved Deep Convolutional Neural Network

A Probe into Reactive Power Management in Renewable Energy System using Facts Devices

Contact Info

Product

Resources

About