Distributed Outage Detection in Power Distribution Networks

Samudrala, Ananth Narayan; Amini, M. Hadi; Kar, Soummya; Blum, Rick S.

doi:10.1109/tsg.2020.2999921

Cited by 20 publications

(19 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The numbers of layers and nodes in the hidden layer directly affect the performance of the BP neural network. (13) To improve the prediction accuracy, on the basis of the existing results, the golden section (14) and gradient descent methods are further used to optimize the number of hidden layer nodes in the neural network. (15) The calculation steps are as follows:…”

Section: Resultsmentioning

confidence: 99%

Realization of Initiative Repair of Power Distribution Network Based on Backpropagation Neural Network Optimization

Guo¹,

Li²,

Qiao³

et al. 2021

Sensors and Materials

View full text Add to dashboard Cite

Protection and maintenance systems are necessary for transmission systems to ensure an efficient and reliable power supply when faults occur. However, most fault detection and location methods rely on the electricity measurement provided by current and voltage transformers. In addition, the initiative repair of a power distribution network is a very considerable portion of power grid operation, and the initiative repair efficiency is crucial for power supply enterprises to provide high-quality services. To give full attention to the value of perceived data and improve the accuracy of fault diagnosis, the technical performance of high-speed power line carriers is extensively investigated, and intelligent sensing devices are installed in power distribution network lines, stations, branch boxes, table boxes, and other parts to realize the initiative repair. To improve the accuracy and timeliness of fault diagnosis for the power distribution network, in this paper, we propose an initiative repair and judgment mechanism based on backpropagation (BP) neural network optimization for the power distribution network. After acquiring information data such as power consumption, the mechanism first takes advantage of the filtered data information to train the BP neural network to predict fault information and other data. Finally, the initiative repair of the power distribution network obtains the forecast data of the BP neural network to judge the fault of the power distribution network. The proposed mechanism considerably shortens the time for the initiative repair and improves the traditional repair mode of the power distribution network, thereby improving the initiative repair efficiency of the power distribution network.

show abstract

Section: Resultsmentioning

confidence: 99%

Realization of Initiative Repair of Power Distribution Network Based on Backpropagation Neural Network Optimization

Guo¹,

Li²,

Qiao³

et al. 2021

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…Finally, as a vital advantage, the proposed detection method can be extended to more possible scenarios of the network such as double or multiple line outage contingencies just by defining the related fuzzy-based rules in the FIS to cover all possible outage contingencies that can be considered for future works. Phasor measurementbased [16]- [18] Non-phasor measurementbased [19] Phasor measurementbased [20]- [34] Less computational burden      Less complexity in analyzing data…”

Section: Methods Comparisonmentioning

confidence: 99%

“…On the other hand, there are methods to detect the networks' topological changes known as line outage detection methods including non-phasor measurements of network parameters and characteristics analyses [19], and phasor measurements data [20]- [34]. In study [19] a line outage detection algorithm is proposed that used a divide-based procedure. First, the distribution network is divided into sub-networks, which communicate with their neighbors with separate control areas.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive fuzzy-based scheme for online detection of operational and topological changes

Damanjani

Abardeh

Azarfar

et al. 2022

IJECE

View full text Add to dashboard Cite

<span>Operational modes and topological changes affect power flow in the power systems. As a result, a broad spectrum of protection issues may happen in the power system. So, both the operational and topological changes should be detected fast to prevent blackouts. On the other hand, the existing detection schemes are complex in analyzing and implementation. Therefore, there is a need for an online scheme to identify the network's topology and operation mode simultaneously without complex computations and additional communication infrastructures. To this end, a comprehensive scheme is proposed in which the changes are detected by analyzing the power flow obtained from the network. For this purpose, line outage contingencies and operation modes are defined in rules to be used in a fuzzy inference system (FIS) as a decision-making tool. The proposed scheme can be implemented on existing lines as a communication infrastructure and determines the network’s status in an online manner. Also, in comparison to the existing schemes, the proposed scheme reduces the complexity and the computational burden. The proposed scheme is implemented on IEEE 8-bus system and the results proved its efficiency.</span>

show abstract

“…Using a novel mathematical model and an algorithm capable of matching optimal solutions rather than the physical constraints of the power grid, we focus on reconfiguring the graph topology using sectionalizing switches to enhance resilience on the basis of the identified indicator. In our prior works on power distribution networks, we developed abstract algorithms for optimal sensor placement [ 43 ] and outage detection [ 44 ] in power distribution networks on the basis of the topology of the grid. This class of studies mainly tackled the structural challenges that the power distribution grid may face, and complemented existing work with several layers of real-world details, including unbalanced three-phase models.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Scalable Reconfiguration Model for the Postdisaster Network Connectivity of Resilient Power Distribution Systems

Imteaj

Akbari

Amini

2023

Sensors

View full text Add to dashboard Cite

The resilient operation of power distribution networks requires efficient optimization models to enable situational awareness. One of the pivotal tools to enhance resilience is a network reconfiguration to ensure secure and reliable energy delivery while minimizing the number of disconnected loads in outage conditions. Power outages are caused by natural hazards, e.g., hurricanes, or system malfunction, e.g., line failure due to aging. In this paper, we first propose a distribution-network optimal power flow formulation (DOPF) and define a new resilience evaluation indicator, the demand satisfaction rate (DSR). DSR is the rate of satisfied load demand in the reconfigured network over the load demand satisfied in the DOPF. Then, we propose a novel model to efficiently find the optimal network reconfiguration by deploying sectionalizing switches during line outages that maximize resilience indicators. Moreover, we analyze a multiobjective scenario to maximize the DSR and minimize the number of utilized sectionalizing switches, which provides an efficient reconfiguration model preventing additional costs associated with closing unutilized sectionalizing switches. We tested our model on a virtually generated 33-bus distribution network and a real 234-bus power distribution network, demonstrating how using the sectionalizing switches can increase power accessibility in outage conditions.

show abstract

Distributed Outage Detection in Power Distribution Networks

Cited by 20 publications

References 37 publications

Realization of Initiative Repair of Power Distribution Network Based on Backpropagation Neural Network Optimization

Realization of Initiative Repair of Power Distribution Network Based on Backpropagation Neural Network Optimization

A comprehensive fuzzy-based scheme for online detection of operational and topological changes

A Novel Scalable Reconfiguration Model for the Postdisaster Network Connectivity of Resilient Power Distribution Systems

Contact Info

Product

Resources

About