A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding
This paper suggests an under-voltage load shedding (UVLS) approach to avoid voltage collapse in stressed distribution systems. Prior to a blackout, a failing system reaches an emergency state, and UVLS is executed as the final option to prevent voltage collapse. Hence, this article introduces a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/10485/1/J16050_015ea7b1ef862d03660635135064b672.pdf |
| _version_ | 1796870177333182464 |
|---|---|
| author | Sharman Sundarajoo, Sharman Sundarajoo Dur Muhammad Soomro, Dur Muhammad Soomro |
| author_facet | Sharman Sundarajoo, Sharman Sundarajoo Dur Muhammad Soomro, Dur Muhammad Soomro |
| author_sort | Sharman Sundarajoo, Sharman Sundarajoo |
| collection | UTHM |
| description | This paper suggests an under-voltage load shedding
(UVLS) approach to avoid voltage collapse in stressed
distribution systems. Prior to a blackout, a failing system
reaches an emergency state, and UVLS is executed as
the final option to prevent voltage collapse. Hence,
this article introduces an optimal UVLS method using
a feedforward artificial neural network (ANN) model
trained with the particle swarm optimization (PSO)
algorithm to obtain the optimal load shedding amount
for a distribution system. PSO is used to obtain the
best topology and optimum initial weights of the ANN
model to enhance the precision of the ANN model. Thus,
the dispute between the optimum fitting regression of
the allocation of ANN nodes and computational time
was disclosed, while the MSE of the ANN model was
minimized. Moreover, the proposed method uses the
stability index (SI) to identify the weak buses in the
system following an emergency state. Different overload
scenarios are examined on the IEEE 33-bus distribution
network to validate the efficacy of the suggested UVLS
scheme. A comparative study is performed to further
assess the performance of the proposed technique. The
comparison indicates that the recommended method is
effective in terms of voltage stability and remaining load. |
| first_indexed | 2024-03-05T22:05:40Z |
| format | Article |
| id | uthm.eprints-10485 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:05:40Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | uthm.eprints-104852023-11-27T07:24:18Z http://eprints.uthm.edu.my/10485/ A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding Sharman Sundarajoo, Sharman Sundarajoo Dur Muhammad Soomro, Dur Muhammad Soomro T Technology (General) This paper suggests an under-voltage load shedding (UVLS) approach to avoid voltage collapse in stressed distribution systems. Prior to a blackout, a failing system reaches an emergency state, and UVLS is executed as the final option to prevent voltage collapse. Hence, this article introduces an optimal UVLS method using a feedforward artificial neural network (ANN) model trained with the particle swarm optimization (PSO) algorithm to obtain the optimal load shedding amount for a distribution system. PSO is used to obtain the best topology and optimum initial weights of the ANN model to enhance the precision of the ANN model. Thus, the dispute between the optimum fitting regression of the allocation of ANN nodes and computational time was disclosed, while the MSE of the ANN model was minimized. Moreover, the proposed method uses the stability index (SI) to identify the weak buses in the system following an emergency state. Different overload scenarios are examined on the IEEE 33-bus distribution network to validate the efficacy of the suggested UVLS scheme. A comparative study is performed to further assess the performance of the proposed technique. The comparison indicates that the recommended method is effective in terms of voltage stability and remaining load. 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/10485/1/J16050_015ea7b1ef862d03660635135064b672.pdf Sharman Sundarajoo, Sharman Sundarajoo and Dur Muhammad Soomro, Dur Muhammad Soomro (2023) A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding. A PARTICLE SWARM OPTIMIZATION TRAINED FEEDFORWARD NEURAL NETWORK FOR UNDER-VOLTAGE LOAD SHEDDING 1, 21 (2). pp. 1-16. |
| spellingShingle | T Technology (General) Sharman Sundarajoo, Sharman Sundarajoo Dur Muhammad Soomro, Dur Muhammad Soomro A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title | A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title_full | A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title_fullStr | A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title_full_unstemmed | A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title_short | A Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding |
| title_sort | particle swarm optimization trained feedforward neural network for under voltage load shedding |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/10485/1/J16050_015ea7b1ef862d03660635135064b672.pdf |
| work_keys_str_mv | AT sharmansundarajoosharmansundarajoo aparticleswarmoptimizationtrainedfeedforwardneuralnetworkforundervoltageloadshedding AT durmuhammadsoomrodurmuhammadsoomro aparticleswarmoptimizationtrainedfeedforwardneuralnetworkforundervoltageloadshedding AT sharmansundarajoosharmansundarajoo particleswarmoptimizationtrainedfeedforwardneuralnetworkforundervoltageloadshedding AT durmuhammadsoomrodurmuhammadsoomro particleswarmoptimizationtrainedfeedforwardneuralnetworkforundervoltageloadshedding |