Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means
With the advancement of technology and science, the power system is getting more intelligent and flexible, and the way people use electric energy in their daily lives is changing. Monitoring the condition of electrical energy loads, particularly in the early detection of aberrant loads and behaviors...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-10-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2021.779587/full |
| _version_ | 1818737754028113920 |
|---|---|
| author | Junfeng Zhang Hui Zhang Song Ding Xiaoxiong Zhang |
| author_facet | Junfeng Zhang Hui Zhang Song Ding Xiaoxiong Zhang |
| author_sort | Junfeng Zhang |
| collection | DOAJ |
| description | With the advancement of technology and science, the power system is getting more intelligent and flexible, and the way people use electric energy in their daily lives is changing. Monitoring the condition of electrical energy loads, particularly in the early detection of aberrant loads and behaviors, is critical for power grid maintenance and power theft detection. In this paper, we combine the widely used deep learning model Transformer with the clustering approach K-means to estimate power consumption over time and detect anomalies. The Transformer model is used to forecast the following hour’s power usage, and the K-means clustering method is utilized to optimize the prediction results, finally, the anomalies is detected by comparing the predicted value and the test value. On real hourly electric energy consumption data, we test the proposed model, and the results show that our method outperforms the most commonly used LSTM time series model. |
| first_indexed | 2024-12-18T00:58:04Z |
| format | Article |
| id | doaj.art-2f2a1f79118146d9a7533755f15e52bb |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-12-18T00:58:04Z |
| publishDate | 2021-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-2f2a1f79118146d9a7533755f15e52bb2022-12-21T21:26:27ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2021-10-01910.3389/fenrg.2021.779587779587Power Consumption Predicting and Anomaly Detection Based on Transformer and K-MeansJunfeng Zhang0Hui Zhang1Song Ding2Xiaoxiong Zhang3Data Mining Laboratory, College of Mathematics and Information Technology, Hebei University, Baoding, ChinaThe Sixty-Third Research Institute, National University of Defense Technology, Nanjing, ChinaSchool of Economics, Zhejiang University of Finance and Economics, Hangzhou, ChinaThe Sixty-Third Research Institute, National University of Defense Technology, Nanjing, ChinaWith the advancement of technology and science, the power system is getting more intelligent and flexible, and the way people use electric energy in their daily lives is changing. Monitoring the condition of electrical energy loads, particularly in the early detection of aberrant loads and behaviors, is critical for power grid maintenance and power theft detection. In this paper, we combine the widely used deep learning model Transformer with the clustering approach K-means to estimate power consumption over time and detect anomalies. The Transformer model is used to forecast the following hour’s power usage, and the K-means clustering method is utilized to optimize the prediction results, finally, the anomalies is detected by comparing the predicted value and the test value. On real hourly electric energy consumption data, we test the proposed model, and the results show that our method outperforms the most commonly used LSTM time series model.https://www.frontiersin.org/articles/10.3389/fenrg.2021.779587/fullpower consumption predictionanomaly detectiontransformerK-meansLSTM |
| spellingShingle | Junfeng Zhang Hui Zhang Song Ding Xiaoxiong Zhang Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means Frontiers in Energy Research power consumption prediction anomaly detection transformer K-means LSTM |
| title | Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means |
| title_full | Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means |
| title_fullStr | Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means |
| title_full_unstemmed | Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means |
| title_short | Power Consumption Predicting and Anomaly Detection Based on Transformer and K-Means |
| title_sort | power consumption predicting and anomaly detection based on transformer and k means |
| topic | power consumption prediction anomaly detection transformer K-means LSTM |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2021.779587/full |
| work_keys_str_mv | AT junfengzhang powerconsumptionpredictingandanomalydetectionbasedontransformerandkmeans AT huizhang powerconsumptionpredictingandanomalydetectionbasedontransformerandkmeans AT songding powerconsumptionpredictingandanomalydetectionbasedontransformerandkmeans AT xiaoxiongzhang powerconsumptionpredictingandanomalydetectionbasedontransformerandkmeans |