Power losses and voltage drop are existing problems in radial distribution networks. This power losses and voltage drop affect the voltage stability level. Reconfiguring the network is a form of approach to improve the quality of electrical power. The network reconfiguration aims to minimize power losses and voltage drop as well as decreasing the Voltage Stability Index (VSI). In this research, network reconfiguration uses binary particle swarm optimization algorithm and Bus Injection to Branch Current-Branch Current to Bus Voltage (BIBC-BCBV) method to analyze the radial system power flow. This scheme was tested on the 33-bus IEEE radial distribution system 12.66 kV. The simulation results show that before reconfiguration, the active power loss is 202.7126 kW and the VSI is 0.20012. After reconfiguration, the active power loss and VSI decreased to 139.5697 kW and 0.14662, respectively. It has decreased the power loss for 31.3136% significantly while the VSI value is closer to zero.

Abstract-To improve the operating performance of a distribution network, on line monitoring is required. For this purpose, sensors (metering devices) are installed. To reduce the number of sensors, state estimation approach can be used to estimate the voltage of buses which do not have sensors. This paper proposes online state estimator for three phase active distribution networks using Neural Network and displayed the results on Geographic Information System (GIS). Neural Network based state estimation is used to estimate the bus voltages by using learning approach from power flow patterns. K-matrix three phase distribution power flow is used in this method as an analytical tool. The K-matrix approach is combined with Particle Swarm Optimization (PSO) in handling a Distributed Generation (DG) which is operated as a voltage controlled (PV) bus. The test results show that the proposed method can reduce the number of sensors significantly (almost 50%). Index Terms-rk, K-matrrix, PSO and GIS.

AbstractOn line monitoring in distribution system suppose to keep the operation safe and reliable. It is connected measuring sensor that placed in nodes. To minimize great cost of sensors placement, state estimator is needed. This paper proposes online state estimator using neural network. Neural network distribution state estimation solves voltage estimation by using learning approach from power flow patterns. K-matrix distribution power flow is used as analysis method. Detailed information and position of network utility is displayed by Geographic Information System (GIS), control can easily do. NNDSE was design and test for single and three phase network. The results show that NNDSE reduce sensor almost 50%.