A hybrid artificial neural network - genetic algorithm for load shedding

Nghia, Le Trong; Anh, Quyen Huy; Tan, Phung Trieu; An, Na

doi:10.11591/ijece.v10i3.pp2250-2258

Cited by 4 publications

(2 citation statements)

References 14 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, Back-Propagation (BP) method is used in deep learning processes to find results with good accuracy. BP has some disadvantages such as weight transport, update locking, vanishing gradients, and exploding gradients [25] [26] [27] [28]. In smart grids, BP takes additional computation time on top of that caused by huge centralized data aggregates [96].…”

Section: Deep Learning Process Contains Artificialmentioning

confidence: 99%

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

Load forecasting is a vital part of smart grids for predicting the required electrical power using artificial intelligence (AI). Deep learning is broadly used for load forecasting in the smart grid using the artificial neural network (ANN). Generally, computing the deep learning in the smart grid requires massive data aggregation or centralization and significant computational time. This paper presents a survey of deep learning-based load forecasting techniques from 2015 to 2020. This survey discusses the studies based on their deep learning techniques, Distributed Deep Learning (DDL) techniques, Back Propagation (BP) based works, and non-BP based works in the load forecasting process. Consequent to the survey, it was determined that data aggregation dependency would be beneficial for reducing computational time in load forecasting. Therefore, a conceptual model of DDL for smart grids has been presented, where the HSIC (Hilbert-Schmidt Independence Criterion) Bottleneck technique has been incorporated to provide higher accuracy.

show abstract

Section: Deep Learning Process Contains Artificialmentioning

confidence: 99%

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The authors in [13] used the GA scheme as an offline method to obtain the appropriate amount of load shedding, on the other hand, the ANN-based scheme is presented as an online method. The authors in [14] used the genetic algorithm to support the training of backpropagation neural networks (BPNNs) to lead the minimum load shedding. A review of recent adaptive load-shedding schemes focusing on distribution system application based on the intelligent method is summarized in [15].…”

Section: Introductionmentioning

confidence: 99%

A New Adaptive Under-Frequency Load Shedding Scheme for Multi-Area Power System, 1-10.

Tiguercha,

Ladjici,

Saboune

2023

International Journal of Power and Energy Systems

View full text Add to dashboard Cite

Under-frequency load shedding (UFLS) is a critical function of frequency control in a power system. This paper presents a new adaptive UFLS scheme in multi-area power systems, where the frequency thresholds and load to be shed are adapted to the severity of the disturbance in each control area. In this approach, the frequency thresholds are adapted by a fuzzy logic controller using the rate of change of frequency (RoCoF), the tie-line transit, the amount of load to be shed is estimated according to the available tie-line capacity and spinning reserve. The objective is to avoid the collapse of the power system following a major disturbance, by shedding a sufficient amount of load while avoiding the tripping of the tie-lines. Numerical simulations are performed on the multi-area Algerian transmission power system and used to demonstrate the effectiveness of the proposed approach compared to the conventional and adaptive approaches. The results show the effectiveness of the proposed approach, with a better quality of frequency control by adapting the amount of load shedding to the severity of the disturbance, and ensuring a better stability of the system by avoiding tripping of the tie-lines.

show abstract

Optimal Rescheduling of Generators to Alleviate Congestion in Transmission System: A Novel Modified Whale Optimization Approach

Paul¹,

Dalapati

Kumar

2021

Arab J Sci Eng

View full text Add to dashboard Cite

A hybrid artificial neural network - genetic algorithm for load shedding

Cited by 4 publications

References 14 publications

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

A New Adaptive Under-Frequency Load Shedding Scheme for Multi-Area Power System, 1-10.

Optimal Rescheduling of Generators to Alleviate Congestion in Transmission System: A Novel Modified Whale Optimization Approach

Contact Info

Product

Resources

About