Fast detection method for mixed bad data in power system under long short-term memory network
This paper proposes a fast detection method for mixed bad data in power systems based on long short-term memory networks to address the problems of low detection accuracy and poor detection efficiency. This method utilizes the powerful processing capability and memory characteristics of LSTM network...
Uloženo v:
| Vydáno v: | Journal of physics. Conference series Ročník 3079; číslo 1; s. 12007 - 12011 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Bristol
IOP Publishing
01.08.2025
|
| Témata: | |
| ISSN: | 1742-6588, 1742-6596 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | This paper proposes a fast detection method for mixed bad data in power systems based on long short-term memory networks to address the problems of low detection accuracy and poor detection efficiency. This method utilizes the powerful processing capability and memory characteristics of LSTM networks for time series data, effectively addressing issues such as data loss, data corruption, synchronization anomalies, and noise impact in complex environments of power systems. By constructing a dual-layer LSTM network architecture, mixed bad data in the power system can be filtered out. By further standardizing the processing and improving the specific detection process, the rapid and effective detection of mixed bad data in the power system has been achieved. Simulation and actual data verification show that this method can significantly improve the data quality of the power system, enhance the accuracy and efficiency of detecting mixed bad data in the power system, and provide solid data support for the safe and stable operation of the power system. |
|---|---|
| Bibliografie: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ISSN: | 1742-6588 1742-6596 |
| DOI: | 10.1088/1742-6596/3079/1/012007 |