Enhancement of Electric Supply Quality by Reconfiguration of Network for Loss Reduction Using Artificial Neural Network
Sabah Ibrahim Mohamed;
Abstract
Feeder reconfiguration allows the transfer of load from heavily- loaded pmtions of the system to locations that are relatively lightly loaded in order to obtain the optimal configuration. That configuration achieves the maximum saving by reducing the active power loSs, improves the operating conditions of the system and enables the full utilization of system equipment capabilities.
Loads in the distribution system of Cairo (EGYPT) vary between three levels per day basis. Therefore, the configuration of the network needs to be changed accordingly, aiming to obtain fue optimal configuration that achieves the•maximum reduction in the power loss.
In view of the increasing use of supervisory control and data acquisition systems (SCADA), and distribution automation and control (DAC), distribution systems reconfiguration becomes more viable altemative for loss reduction. This means those distribution systems equipped with SCADA and DAC already possess the necessary automated switches and remote monitming facilities.
A technique for on-line disnibution system reconfiguration, based on the Attificial Neural Network (ANN) is proposed in order to determine the optimal topology, that economically reduces the active power loss and improves the system performance, according to the variation of load pattem. Keeping in mind that the practical and recommended system operating conditions and constraints: (maximum voltage drop, maximum feeder load and maximum number of switchings) are satisfied. ANNs have gained a high attention in the power area. They are widely applied in different topics: load forecasting, fault diagnosis, disnibution system restoration
...etc. They are designed to handle highly non-linear relationships. They are parallel
data processing tools capable ofleaming function non-linearity.
Based on radial (open loop) network analysis technique, two ANN based approaches to be uiilized for power loss reduction in distribution networks is presented. In the first approach, two ANNs are designed.
Loads in the distribution system of Cairo (EGYPT) vary between three levels per day basis. Therefore, the configuration of the network needs to be changed accordingly, aiming to obtain fue optimal configuration that achieves the•maximum reduction in the power loss.
In view of the increasing use of supervisory control and data acquisition systems (SCADA), and distribution automation and control (DAC), distribution systems reconfiguration becomes more viable altemative for loss reduction. This means those distribution systems equipped with SCADA and DAC already possess the necessary automated switches and remote monitming facilities.
A technique for on-line disnibution system reconfiguration, based on the Attificial Neural Network (ANN) is proposed in order to determine the optimal topology, that economically reduces the active power loss and improves the system performance, according to the variation of load pattem. Keeping in mind that the practical and recommended system operating conditions and constraints: (maximum voltage drop, maximum feeder load and maximum number of switchings) are satisfied. ANNs have gained a high attention in the power area. They are widely applied in different topics: load forecasting, fault diagnosis, disnibution system restoration
...etc. They are designed to handle highly non-linear relationships. They are parallel
data processing tools capable ofleaming function non-linearity.
Based on radial (open loop) network analysis technique, two ANN based approaches to be uiilized for power loss reduction in distribution networks is presented. In the first approach, two ANNs are designed.
Other data
| Title | Enhancement of Electric Supply Quality by Reconfiguration of Network for Loss Reduction Using Artificial Neural Network | Other Titles | تحسين جودة التغذية الكهربائية باعادة هيكلة نظم توزيع القوى لتقليل الفقد باستخدام الشبكات العصبية الاصطناعية | Authors | Sabah Ibrahim Mohamed | Issue Date | 2001 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.