Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission
This paper presents an intelligent model for the recognition of high-voltage direct current interference in geomagnetic observation stations. Firstly, it introduces the history and current status of geomagnetic observation in China, highlighting the issue of station interference from HVDC. Next, it...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10354315/ |
| _version_ | 1797373170336923648 |
|---|---|
| author | Yin Cai Zhaoliang An Guannan Si Jun Chen Miaomiao Meng Shiying Li |
| author_facet | Yin Cai Zhaoliang An Guannan Si Jun Chen Miaomiao Meng Shiying Li |
| author_sort | Yin Cai |
| collection | DOAJ |
| description | This paper presents an intelligent model for the recognition of high-voltage direct current interference in geomagnetic observation stations. Firstly, it introduces the history and current status of geomagnetic observation in China, highlighting the issue of station interference from HVDC. Next, it discusses the application of traditional methods and deep learning techniques in the identification of geomagnetic data interference, along with related research. To address these issues, the paper emphasizes the proposed model framework, which includes four main components: data preprocessing, model training, interference recognition, and visualization. Data preprocessing is carried out to eliminate dimensional differences between data by using standardization and data augmentation techniques, increasing the diversity and robustness of training data. Model training involves the use of an LSTM network, which learns temporal patterns and relevant features in the input data, implicitly performing feature extraction and representation learning. In the interference recognition stage, the concept of anomaly scores is introduced, and the anomaly score for each data point is calculated using mean and covariance to determine if the point is an anomaly. Finally, the results of interference recognition are presented through visualization. In the experimental section, the paper conducts a comprehensive evaluation of four different models (LSTM, RNN_TANH, RNN_RELU, and GRU) when used as the training network for the proposed model. The evaluation focuses on three aspects: model performance, computational cost, and Friedman’s test. The experimental results demonstrate that selecting LSTM as the training network with a time step of 3 achieves optimal performance in all three aspects, showcasing strong generalization capabilities. |
| first_indexed | 2024-03-08T18:46:26Z |
| format | Article |
| id | doaj.art-dd405c893d39407783464d5aa35a6bdd |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T18:46:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dd405c893d39407783464d5aa35a6bdd2023-12-29T00:03:50ZengIEEEIEEE Access2169-35362023-01-011114556614557810.1109/ACCESS.2023.334192410354315Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC TransmissionYin Cai0Zhaoliang An1Guannan Si2https://orcid.org/0009-0004-4152-5994Jun Chen3Miaomiao Meng4Shiying Li5Shandong Earthquake Agency, Jinan, ChinaSchool of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, ChinaSchool of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, ChinaAnhui Earthquake Agency, Hefei, ChinaShandong Earthquake Agency, Jinan, ChinaShandong Earthquake Agency, Jinan, ChinaThis paper presents an intelligent model for the recognition of high-voltage direct current interference in geomagnetic observation stations. Firstly, it introduces the history and current status of geomagnetic observation in China, highlighting the issue of station interference from HVDC. Next, it discusses the application of traditional methods and deep learning techniques in the identification of geomagnetic data interference, along with related research. To address these issues, the paper emphasizes the proposed model framework, which includes four main components: data preprocessing, model training, interference recognition, and visualization. Data preprocessing is carried out to eliminate dimensional differences between data by using standardization and data augmentation techniques, increasing the diversity and robustness of training data. Model training involves the use of an LSTM network, which learns temporal patterns and relevant features in the input data, implicitly performing feature extraction and representation learning. In the interference recognition stage, the concept of anomaly scores is introduced, and the anomaly score for each data point is calculated using mean and covariance to determine if the point is an anomaly. Finally, the results of interference recognition are presented through visualization. In the experimental section, the paper conducts a comprehensive evaluation of four different models (LSTM, RNN_TANH, RNN_RELU, and GRU) when used as the training network for the proposed model. The evaluation focuses on three aspects: model performance, computational cost, and Friedman’s test. The experimental results demonstrate that selecting LSTM as the training network with a time step of 3 achieves optimal performance in all three aspects, showcasing strong generalization capabilities.https://ieeexplore.ieee.org/document/10354315/High-voltage direct current transmissiongeomagnetic observationinterference identificationFriedman test |
| spellingShingle | Yin Cai Zhaoliang An Guannan Si Jun Chen Miaomiao Meng Shiying Li Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission IEEE Access High-voltage direct current transmission geomagnetic observation interference identification Friedman test |
| title | Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission |
| title_full | Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission |
| title_fullStr | Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission |
| title_full_unstemmed | Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission |
| title_short | Multi-Step Ahead Prediction for Anomaly Detection of Geomagnetic Observation in HVDC Transmission |
| title_sort | multi step ahead prediction for anomaly detection of geomagnetic observation in hvdc transmission |
| topic | High-voltage direct current transmission geomagnetic observation interference identification Friedman test |
| url | https://ieeexplore.ieee.org/document/10354315/ |
| work_keys_str_mv | AT yincai multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission AT zhaoliangan multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission AT guannansi multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission AT junchen multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission AT miaomiaomeng multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission AT shiyingli multistepaheadpredictionforanomalydetectionofgeomagneticobservationinhvdctransmission |