Nothing Special   »   [go: up one dir, main page]
Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Power System Voltage Stability

    Uploaded by

    noor almosawie
    The document discusses using artificial neural networks to assess power system voltage stability. It proposes using a feedforward backpropagation neural network (FFBPNN) trained with Newton-Raphson results on IEEE test systems to predict voltage stability metrics like Lmn. The FFBPNN approach provides high accuracy compared to traditional calculations, reduces the complexity of stability monitoring, and allows early detection of unstable buses. Future work could explore improving voltage stability monitoring and control using ANN-based approaches.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Power System Voltage Stability

    Uploaded by

    noor almosawie
    18 views12 pages
    The document discusses using artificial neural networks to assess power system voltage stability. It proposes using a feedforward backpropagation neural network (FFBPNN) trained with Newton-Raphson results on IEEE test systems to predict voltage stability metrics like Lmn. The FFBPNN approach provides high accuracy compared to traditional calculations, reduces the complexity of stability monitoring, and allows early detection of unstable buses. Future work could explore improving voltage stability monitoring and control using ANN-based approaches.

    Original Description:

    Original Title

    Power system voltage stability

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses using artificial neural networks to assess power system voltage stability. It proposes using a feedforward backpropagation neural network (FFBPNN) trained with Newton-Raphson results on IEEE test systems to predict voltage stability metrics like Lmn. The FFBPNN approach provides high accuracy compared to traditional calculations, reduces the complexity of stability monitoring, and allows early detection of unstable buses. Future work could explore improving voltage stability monitoring and control using ANN-based approaches.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    18 views12 pages

    Power System Voltage Stability

    Uploaded by

    noor almosawie
    The document discusses using artificial neural networks to assess power system voltage stability. It proposes using a feedforward backpropagation neural network (FFBPNN) trained with Newton-Raphson results on IEEE test systems to predict voltage stability metrics like Lmn. The FFBPNN approach provides high accuracy compared to traditional calculations, reduces the complexity of stability monitoring, and allows early detection of unstable buses. Future work could explore improving voltage stability monitoring and control using ANN-based approaches.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 12

    IEEE TEMSMET-2023

    IEEE Third International Conference on


    Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent

    Paper ID:374
    Title of the paper :Assessment of power system voltage stability using ANN
    Author details :Maha Saad Dawood Salman
    Electrical Power Engineering Technique ,Electrical Engineering Technical Collage
    Middle Technical University
    Iraq, Baghdad
    maha93saad93@gmail.com
    1 ieee.org
    Table of contents

    01 02 03
    Introduction Novelty Motivation

    04 05
    Literature review Methodology

    06 07
    Results and Conclusion Future Scope
    2
    01 Introduction
    ▸ Voltage stability in electrical power systems is of great importance because its
    measurement of:
    Systems
    Development

    loadability
    Increasing the load on
    the system requires Stability
    increasing the Provide stabily
    loadability of the power voltage to load
    system area
    3
    01 Introduction
    Electrical power systems go through several scenarios as a result of overload:

    Load Reactive power


    increment

    Voltage
    breakdown
    and power
    4
    failure
    02 Novelty
    Introduce AINN with NR in order to provide high effective and
    accuracy method for voltage stability assessment

    + NR
    5
    03 Motivation PSNs
    Using ANN in order to:
    Early detection of critical bus.

    Reduce the complications .

    Reduce the time factor . Load


    area

    Provide high effective tool. Voltage stability


    monitoring

    6
    04 Literature review
    ▸ According to following table:

    Authors and year Objective System Method

    Bahmanyar, A. R., Voltage stability analysis 30-IEEE bus Newton Raphson based on QV
    and voltage collapse system. curve.
    et al.,2014 point based on reactive
    power change .

    Asija, D., et al., Power flow analysis and WSCC 9 IEEE CPF
    contingency analysis for bus power system.
    2015 power system .

    L. Rodriguez-Garciaa, Detect the voltage 2 and 30 IEEE bus Traditional equations for the PV
    collapse point of the load system. Curve solution .
    et al.,2019
    margin using d-index.

    Elemary, A. A., et Power system voltage 2 and 6 IEEE bus Traditional equations and
    stability monitoring using system. calculations.
    al., 2022 indexes.

    7
    05 Methodology/Implementation
    Matlab Simulink

    Base(a) , +25%(b) , 50 %(c)

    ≤1

    CPF
    Vb , ang ,Vl ,Pr , Qr

    8
    05 Methodology/Implementation

    Parameter Detail
    Input layer 6 input layers
    Output layer 1 output layer
    Hidden layer 10 hidden for each input
    Network type Feed forward backpropagation
    Adaption learning LEARNGDM
    Performance MSE

    Using
    Matpower7.0

    9
    06 Results and conclusion 1
    0.9
    0.8
    Lmn for Case a
    0.7
    0.8
    0.6
    0.6
    Lmn value

    Lmn for Case c 0.5


    0.4
    0.4
    0.2 1
    0.3
    0 0.9
    1 2 3 4 5 6 7 8 9 0.8 0.2
    Bus no. 0.7 0.1

    Lmn Value
    0.6 0
    0.5 1 3 5 7 9 11 13 15 17 19 21 23 25 27
    0.4
    0.3 lmn target lmn by FFBPNN
    0.2
    Lmn for Case b NR Target Lmn FFBPNN Lmn
    0.1
    1 0
    0.0612 0.63262 0.637183928
    1 2 3 4 5 6 7 8 9 0.030801 0.329032 0.357499476
    0.8
    0.007143 0.073446 0.074443015
    Lmn Value

    0.6 Bus no.


    0 0 0.000633234
    0.4
    B NO.5 0.093661 0.951824 0.937894378
    0.2
    0.058982 0.596035 0.600188414
    0
    1 2 3 4 5 6 7 8 9 0 0 0.000619606
    0.06945 0.70296 0.705356299
    Bus no. 0.0002 0 0.000564082

    10
    06 Results and conclusion
    The effect of the load
    The FFBPNN using Matlab shows: increment and reactive power
    on the voltage stability
    High accuracy
    Because the MSE between the target and trained network was less the 0.0003
    and validate with NR.

    Reduce time of monitoring


    The complex calculation for the voltage stability using traditional equation of
    the Lmn was reduced and become unnecessary

    11
    07 Future scope
    Using the FFBPNN to:
    Improve the voltage stability

    Using
    compensation
    devices

    Voltage
    stability
    12 monitoring

    You might also like