[go: up one dir, main page]

 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (1)

Search Parameters:
Keywords = SVScout

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 8005 KiB  
Article
Analysis of IEC 61850-9-2LE Measured Values Using a Neural Network
by Kinan Wannous, Petr Toman, Viktor Jurák and Vojtěch Wasserbauer
Energies 2019, 12(9), 1618; https://doi.org/10.3390/en12091618 - 28 Apr 2019
Cited by 8 | Viewed by 6381
Abstract
Process bus communication has an important role to digitalize substations. The IEC 61850-9-2 standard specifies the requirements to transmit digital data over Ethernet networks. The paper analyses the impact of IEC 61850-9-2LE on physical protections with (analog-digital) input data of voltage and current. [...] Read more.
Process bus communication has an important role to digitalize substations. The IEC 61850-9-2 standard specifies the requirements to transmit digital data over Ethernet networks. The paper analyses the impact of IEC 61850-9-2LE on physical protections with (analog-digital) input data of voltage and current. With the increased interaction between physical devices and communication components, the test proposes a communication analysis for a substation with the conventional method (analog input) and digital method based on the IEC 61850 standard. The use of IEC 61850 as the basis for smart grids includes the use of merging units (MUs) and deployment of relays based on microprocessors. The paper analyses the merging unit’s functions for relays using IEC 61850-9-2LE. The proposed method defines the sampled measured values source and analysis of the traffic. By using neural net pattern recognition that solves the pattern recognition problem, a relation between the inputs (number of samples/ms—interval time between the packets) and the source of the data is found. The benefit of this approach is to reduce the time to test the merging unit by getting the feedback from the merging unit and using the neural network to get the data structure of the publisher IED. Tests examine the GOOSE message and performance using the IEC standard based on a network traffic perspective. Full article
(This article belongs to the Special Issue Data Analytics in Energy Systems)
Show Figures

Figure 1

Figure 1
<p>IEC 61850 structure.</p>
Full article ">Figure 2
<p>IEC 61850 Object Name Structure.</p>
Full article ">Figure 3
<p>The full scheme of testing the IEC 61850 (SMV-GOOSE).</p>
Full article ">Figure 4
<p>The measured interval time between synchronization announcement messages.</p>
Full article ">Figure 5
<p>The measured interval time between announcement messages—follow up messages—synch messages of synchronization.</p>
Full article ">Figure 6
<p>Wiring of CMLIB A.</p>
Full article ">Figure 7
<p>Experiment structure and network devices.</p>
Full article ">Figure 8
<p>Omicron sampled measured values test configuration.</p>
Full article ">Figure 9
<p>The interval time in microseconds between packets of CMC—Simulator, an IED.</p>
Full article ">Figure 10
<p>The calculation of time duration to publish the sampled values. The CMC publisher sends packets with interval 250 µs and IED-72 follows by sending packets to keep the system synchronized.</p>
Full article ">Figure 11
<p>The interval time + delay time in µsec between publisher/subscriber IEDs.</p>
Full article ">Figure 12
<p>The interval time + delay time in µsec between publisher/subscriber (CMC &amp; IED-72).</p>
Full article ">Figure 13
<p>Number of packets per ms for IED publisher/CMC MU.</p>
Full article ">Figure 14
<p>The full scheme of testing the IEC 61850 (SMV-GOOSE). (<b>a</b>) Shows the mapping of a GOOSE message with the dataset details. It shows the tripping signal is false before increasing the current and overcurrent function of IED takes action, (<b>b</b>) shows changing of the status to true, which means the GOOSE message (tripping signal) is sent to the subscriber.</p>
Full article ">Figure 15
<p>The structure of IED SCL and GOOSE mapping.</p>
Full article ">Figure 16
<p>GOOSE Messages duplicities for five different GOOSE messages. n-repetition.</p>
Full article ">Figure 17
<p>Data preparation of parameters.</p>
Full article ">Figure 18
<p>The best validation performance at epoch 23, validation error at the lowest point.</p>
Full article ">Figure 19
<p>The receiver operation characteristic curve (<b>a</b>) shows the training ROC that is exploring the tradeoff between true positives and false positives, this curve is a metric used to examine the quality classifier, (<b>b</b>) represents the validation ROC, (<b>c</b>) represents the test ROC, (<b>d</b>) represents the All ROC.</p>
Full article ">Figure 19 Cont.
<p>The receiver operation characteristic curve (<b>a</b>) shows the training ROC that is exploring the tradeoff between true positives and false positives, this curve is a metric used to examine the quality classifier, (<b>b</b>) represents the validation ROC, (<b>c</b>) represents the test ROC, (<b>d</b>) represents the All ROC.</p>
Full article ">
Back to TopTop